Search results for: video annotation

Authors: Wen-jing Shan

Abstract:

The Chinese annotated edition of “Experience and education: The 60th anniversary edition,” originally written in English by John Dewey (1859-1952), was published in 2015 by this author. A report of the process and results of the translation and annotation of the book is the purpose of this paper. It is worth mentioning that the original 1938 edition was considered as the best concise statement on education by John Dewey, one the most important educational theorists of the twentieth century. One of the features of this The 60th anniversary edition is that the original publisher, Kappa Delta Pi International Honor Society, invited four contemporary Deweyan scholars who had been awarded the Society’s Laureate Scholar to write a review of the book published by Dewey, who was the first to receive this honor. The four scholars are Maxine Greene(1917-2014), Philip W. Jackson(1928-2015), Linda Darling-Hammond(1951-), and O. L. Davis, Jr.(1928-). The original 1938 edition, the best concise statement on education by the most important educational theorist of the twentieth century, was translated into Chinese for five times after its publication in the U.S.A, three in the 1940s, one in the 1990s, and one in 2010s. Nonetheless, the five translations have few or no annotations and have some flaws of mis-interpretations and lack of information. The author retranslated and annotated the book to make the interpretations more faithful, expressive, and elegant, and providing the readers with more understanding and more correct information. This author started the project of translation and annotation sponsored by Taiwan Ministry of Science and Technology in August 2011 and finished and published by July 2015. The work, the author, did was divided into three stages. First, in the preparatory stage of the project, the summary of each chapter, the rationale of the book, the textual commentary, the development of the original and Chinese editions, and reviews and criticisms, as well as Dewey’s biography and bibliography were initially investigated. Secondly, on the basis of the above preliminary work, the translation with annotation of Experience and Education, an epitome of Dewey’s biography and bibliography, a chronology, and a critical introduction for the Experience and Education were written. In the critical introduction, Dewey’s philosophy of experience and educational ideas will be examined along the timeline of human thought. And the vast literature about Dewey and his work will be instrumental to reveal the historical significance of Experience and Education on the modern age and make the critical introduction more knowledgeable. Third, the final stage took another two years to review and revise the draft of the work and send it for publication. There are two parts in the book. The first part is a scholarly introduction including Dewey’s chronicle (in short form), Dewey’s mind, people and life, the importance of “Experience and education”, the necessity of re-translation and re-annotation of “Experience and education” into Chinese. The second part is the re-translation and re-annotation version, including Dewey’s “Experience and education” and four papers written by contemporary scholars.

Keywords: John Dewey, experience and education: the 60th anniversary edition, translation, annotation

Procedia PDF Downloads 159

Authors: B. O. Olawale, C. R. Chatwin, R. C. D. Young, P. M. Birch, F. O. Faithpraise, A. O. Olukiran

Abstract:

Ortho-rectification is the process of geometrically correcting an aerial image such that the scale is uniform. The ortho-image formed from the process is corrected for lens distortion, topographic relief, and camera tilt. This can be used to measure true distances, because it is an accurate representation of the Earth’s surface. Ortho-rectification and geo-referencing are essential to pin point the exact location of targets in video imagery acquired at the UAV platform. This can only be achieved by comparing such video imagery with an existing digital map. However, it is only when the image is ortho-rectified with the same co-ordinate system as an existing map that such a comparison is possible. The video image sequences from the UAV platform must be geo-registered, that is, each video frame must carry the necessary camera information before performing the ortho-rectification process. Each rectified image frame can then be mosaicked together to form a seamless image map covering the selected area. This can then be used for comparison with an existing map for geo-referencing. In this paper, we present a four-step ortho-rectification procedure for real-time geo-referencing of video data from a low-cost UAV equipped with multi-sensor system. The basic procedures for the real-time ortho-rectification are: (1) Decompilation of video stream into individual frames; (2) Finding of interior camera orientation parameters; (3) Finding the relative exterior orientation parameters for each video frames with respect to each other; (4) Finding the absolute exterior orientation parameters, using self-calibration adjustment with the aid of a mathematical model. Each ortho-rectified video frame is then mosaicked together to produce a 2-D planimetric mapping, which can be compared with a well referenced existing digital map for the purpose of georeferencing and aerial surveillance. A test field located in Abuja, Nigeria was used for testing our method. Fifteen minutes video and telemetry data were collected using the UAV and the data collected were processed using the four-step ortho-rectification procedure. The results demonstrated that the geometric measurement of the control field from ortho-images are more reliable than those from original perspective photographs when used to pin point the exact location of targets on the video imagery acquired by the UAV. The 2-D planimetric accuracy when compared with the 6 control points measured by a GPS receiver is between 3 to 5 meters.

Keywords: geo-referencing, ortho-rectification, video frame, self-calibration

Procedia PDF Downloads 477

Authors: Tanveer Hussain, Khan Muhammad, Amin Ullah, Mi Young Lee, Sung Wook Baik

Abstract:

The Big Data generated from distributed vision sensors installed on large scale in smart cities create hurdles in its efficient and beneficial exploration for browsing, retrieval, and indexing. This paper presents a three-folded framework for effective video summarization of such data and provide a compact and representative format of Big Video Data. In the first fold, the paper acquires input video data from the installed cameras and collect clues such as type and count of objects and clarity of the view from a chunk of pre-defined number of frames of each view. The decision of representative view selection for a particular interval is based on fuzzy inference system, acquiring a precise and human resembling decision, reinforced by the known clues as a part of the second fold. In the third fold, the paper forwards the selected view frames to the summary generation mechanism that is supported by a saliency-aware convolution neural network (CNN) model. The new trend of fuzzy rules for view selection followed by CNN architecture for saliency computation makes the multi-view video summarization (MVS) framework a suitable candidate for real-world practice in smart cities.

Keywords: big video data analysis, fuzzy logic, multi-view video summarization, saliency detection

Procedia PDF Downloads 187

Authors: Alex Vakaloudis, Juan Manuel Escano-Gonzalez

Abstract:

Setting up a system to broadcast live lectures on the web is a procedure which on the surface does not require any serious technical skills mainly due to the facilities provided by popular learning management systems and their plugins. Nevertheless, producing a system of outstanding quality is a multidisciplinary and by no means a straightforward task. This complicatedness may be responsible for the delivery of an overall poor experience to the learners, and it calls for a formal rating framework that takes into account the diverse aspects of an architecture for synchronous video e-learning systems. We discuss the specifications of such a framework which at its final stage employs fuzzy logic technique to transform from qualitative to quantitative results.

Keywords: synchronous video, fuzzy logic, rating framework, e-learning

Procedia PDF Downloads 557

Authors: Shola Haruna Adeosun, F. Adebiyi Ajoke, Odedeji Adeoye

Abstract:

Video billboard advertising by networks and brand switching was conceived out of inquisition at the huge billboard advertising expenditures made by the three major GSM network operators in Nigeria. The study was anchored on Lagos State Metropolis with a current census population over 1,000,000. From this population, a purposive sample of 400 was adopted, and the questionnaire designed for the survey was carefully allocated to members of this ample in the five geographical zones of the city so that each rung of the society was well represented. The data obtained were analyzed using tables and simple percentages. The results obtained showed that subscribers of these networks were hardly influenced by the video billboard advertisements. They overwhelmingly showed that rather than the slogans of the GSM networks carried on the video billboards, it was the incentives to subscribers as well as the promotional strategies of these organizations that moved them to switch from one network to another. These switching lasted only as long as the incentives and promotions were in effect. The results of the study also seemed to rekindle the age-old debate on media effects, by the unyielding schools of the theory of ‘all-powerful media’, ‘the limited effects media’, ‘the controlled effects media’ and ‘the negotiated media influence’.

Keywords: evaluation, impact, video billboard, marketing, services

Procedia PDF Downloads 252

Authors: Cui Li, Xu Yuping

Abstract:

Based on the question of, "Are short video creators who are digital workers controlled by platform rules?" this study discusses the specific ways of platform rules control and the impact on short video creators. Based on the theory of digital labor, this paper adopts the method of in-depth interview and participant observation and chooses 24 producers of short video content of Tiktok to conduct in-depth interview. At the same time, through entering the short video creation field, the author carries on the four-month field investigation, obtains the creation process related data, and analyzes how the short video creator, as the digital labor, is controlled by the platform rule, as well as the creator in this process of compromise and resistance, a more comprehensive presentation of the short video creators of the labor process. It is found that the short video creators are controlled by the platform rules, mainly in the control of traffic rules, and the creators create content, compromise and resist under the guidance of traffic. First, while the platform seems to offer a flexible and autonomous way for creators to monetize, the threshold for participating in the event is actually very high for creators, and the rules for monetizing the event are vague. Under the influence of the flow rule, the creator is faced unstable incomes and high costs. Therefore, creators have to follow the rules of traffic to guide their own creation, began to flow-oriented content production, mainly reflected in the need to keep up-to-date, the pursuit of traffic to ride on the hot spots, in order to flow regardless, set up people "Born for the show", by the label solidified content creation. Secondly, the irregular working hours lead to the extension and overwork of the working hours, which leads to the internal friction of the short video creators at the spiritual level, and finally leads to the Rat Race of video creation. Thirdly, the video creator has completed the internalization and compromise of the platform rules in practice, which promotes the creator to continue to create independently, and forms the intrinsic motive force of the creator. Finally, the rule-controlled short video creators resist and fight in flexible ways, make use of the mechanism and rules of the platform to carry on the second creation, carry on the routine production, purchase the false flow, transfer the creation position to maintain own creation autonomy.

Keywords: short videos, tiktok, production, digital labors

Procedia PDF Downloads 60

Authors: Ari Istiany, Guspri Devi Artanti, M. Si

Abstract:

Based on the results Riskesdas, it is known that breastfeeding awareness about the importance of exclusive breastfeeding is still low at only 15.3 %. These conditions resulted in a very infant at risk for infectious diseases, such as diarrhea and acute respiratory infection. Therefore, the aim of this study to evaluate the video development about exclusive breastfeeding as a nutrition education media for posyandu cadre. This research used development methods for making the video about exclusive breastfeeding. The study was conducted in urban areas Rawamangun, East Jakarta. Respondents of this study were 1 media experts from the Department of Educational Technology - UNJ, 2 subject matter experts from Department of Home Economics - UNJ and 20 posyandu cadres to assess the quality of the video. Aspects assessed include the legibility of text, image display quality, color composition, clarity of sound, music appropriateness, duration, suitability of the material and language. Data were analyzed descriptively likes frequency distribution table, the average value, and deviation standard. The result of this study showed that the average score assessment according to media experts, subject matter experts, and posyandu cadres respectively was 3.43 ± 0.51 (good), 4.37 ± 0.52 (very good) and 3.6 ± 0.73 (good). The conclusion is on exclusive breastfeeding video as feasible as a media for nutrition education. While suggestions for the improvement of visual media is multiply illustrations, add material about the correct way of breastfeeding and healthy baby pictures.

Keywords: exclusive breastfeeding, posyandu cadre, video, nutrition education

Procedia PDF Downloads 410

Authors: Ganna Zakharova

Abstract:

The persuasive influence of tourism promotional materials is very much experienced nowadays. In order to attract the attention of viewers, marketers choose various techniques in their digital texts. Video is an essential element for attraction and seduction; it is a trigger element for tourists. This solution for web marketing engages and convinces potential tourists to book a tourism product. Embedding video materials into a website provides useful information, create different feelings in viewers, and help them finalize their decisions. The present article discusses video solutions for health tourism websites used to allure potential tourists. The paper reviews the influential elements of persuasive tourism marketing videos. The article highlights how these components as persuasive strategies of tourism promotional materials can influence the decisions of tourism websites’ users. The result section provides the real examples of the deployment of the mentioned technique to convince the audience by the website of 'Karpaty' resort (Ukraine). This technique is worth attention as it plays an important role in the promotion of tourism services. The data collection of this study will provide updated information in relation to the rhetoric of tourism.

Keywords: tourism discourse, persuasive video, influential videos in marketing, persuasive discourse, tourism promotion

Procedia PDF Downloads 116

Authors: Vinay P., Srinivas K. S.

Abstract:

Low Light Image Enhancement is of utmost impor- tance in computer vision based tasks. Applications include vision systems for autonomous driving, night vision devices for defence systems, low light object detection tasks. Many of the existing deep learning methods are resource intensive during the inference step and take considerable time for processing. The algorithm should take considerably less than 41 milliseconds in order to process a real-time video feed with 24 frames per second and should be even less for a video with 30 or 60 frames per second. The paper presents a fast and efficient solution which has two main advantages, it has the potential to be used for a real-time video feed, and it can be used in low compute environments because of the lightweight nature. The proposed solution is a pipeline of three steps, the first one is the use of a simple function to map input RGB values to output RGB values, the second is to balance the colors and the final step is to adjust the contrast of the image. Hence a custom dataset is carefully prepared using images taken in low and bright lighting conditions. The preparation of the dataset, the proposed model, the processing time are discussed in detail and the quality of the enhanced images using different methods is shown.

Keywords: low light image enhancement, real-time video, computer vision, machine learning

Procedia PDF Downloads 201

Authors: Geoff Skinner, Ilung Pranata

Abstract:

The advancement of ICT innovations provides us with a comfortable and convenient modern lifestyle. However, this modern easy lifestyle is proving to have some serious health consequences. Such technological advancements that have dramatically increased ones time in front of screens have been a contributing factor to increasing rates of obesity. In particular the youth obesity issue has gained more and more attention from researchers and health institutions around the world. Although technology innovations may lead to a sedate modern life, they also have a potential to solve the obesity issue in children. This paper provides a review of the issues in child obesity and the potential of active video games to mitigate these issues. Additionally, the paper also discusses the key requirements to develop an active video game that hopes to help combat child obesity through motivating youth to exergame. A framework is introduced to meet the requirements, from which a prototype was implemented. Discussion of the simulation and testing that were performed to verify the attainment of objectives is also detailed.

Keywords: e-video games, exergaming, health informatics, human computer interaction

Procedia PDF Downloads 442

Authors: Seda Yavuz, Anıl Çelebi, Aysun Taşyapı Çelebi, Oğuzhan Urhan

Abstract:

Nowadays, demand for using real-time video transmission capable devices is ever-increasing. So, high resolution videos have made efficient video compression techniques an essential component for capturing and transmitting video data. Motion estimation has a critical role in encoding raw video. Hence, various motion estimation methods are introduced to efficiently compress the video. Low bit‑depth representation based motion estimation methods facilitate computation of matching criteria and thus, provide small hardware footprint. In this paper, a hardware implementation of a two-bit transformation based low-complexity motion estimation method using local binary pattern approach is proposed. Image frames are represented in two-bit depth instead of full-depth by making use of the local binary pattern as a binarization approach and the binarization part of the hardware architecture is explained in detail. Experimental results demonstrate the difference between the proposed hardware architecture and the architectures of well-known low-complexity motion estimation methods in terms of important aspects such as resource utilization, energy and power consumption.

Keywords: binarization, hardware architecture, local binary pattern, motion estimation, two-bit transform

Procedia PDF Downloads 309

Authors: Rex Hsieh, Kosei Yamamura, Satoshi Cho, Hisashi Sato

Abstract:

This project took place in the fall semester of 2019 from September 2019 to February 2020. It improves upon the design of a previous vTuber based eLearning video system by correcting criticisms from students and enhancing the positive aspects of the previous system. The transformed audio which has proven to be ineffective in previous experiments was not used in this experiment. The result is videos featuring 3 avatars covering different Ray Tracing subject matters being released weekly. Students are free to pick which videos they want to watch and can also re-watch any videos they want. The students' subjective impressions of each video is recorded and analysed to help further improve the system.

Keywords: vTuber, eLearning, Ray Tracing, Avatar

Procedia PDF Downloads 186

Authors: Mulugeta K. Tefera, Xiaolong Yang, Jian Liu

Abstract:

Detection and tracking of moving objects are very important in many application contexts such as detection and recognition of people, visual surveillance and automatic generation of video effect and so on. However, the task of detecting a real shape of an object in motion becomes tricky due to various challenges like dynamic scene changes, presence of shadow, and illumination variations due to light switch. For such systems, once the moving object is detected, tracking is also a crucial step for those applications that used in military defense, video surveillance, human computer interaction, and medical diagnostics as well as in commercial fields such as video games. In this paper, an object presents in dynamic background is detected using adaptive mixture of Gaussian based analysis of the video sequences. Then the detected moving object is tracked using the region based moving object tracking and inter-frame differential mechanisms to address the partial overlapping and occlusion problems. Firstly, the detection algorithm effectively detects and extracts the moving object target by enhancing and post processing morphological operations. Secondly, the extracted object uses region based moving object tracking and inter-frame difference to improve the tracking speed of real-time moving objects in different video frames. Finally, the plotting method was applied to detect the moving objects effectively and describes the object’s motion being tracked. The experiment has been performed on image sequences acquired both indoor and outdoor environments and one stationary and web camera has been used.

Keywords: background modeling, Gaussian mixture model, inter-frame difference, object detection and tracking, video surveillance

Procedia PDF Downloads 475

Authors: Shu-Chen Wu

Abstract:

This qualitative study investigated Chinese teachers’ perspectives on learning at play. Six kindergarten teachers were interviewed to obtain their understanding of learning at play. Exemplary play episodes from their classrooms were selected with the assistance of the participating teachers. Four three-minute videos containing the largest amount of learning elements based on the teachers’ views were selected for analysis. Applying video-stimulated interviews, the selected video clips were shown to eight teachers in two focus groups to elicit their perspectives on learning at play. The findings revealed that Chinese teachers have a very structured representation of learning at play, which should contribute to the development of professional practices and curricular policies.

Keywords: learning at play, teachers’ perspectives, co-constructed views, video-stimulated interviews

Procedia PDF Downloads 229

Authors: Hyoup-Sang Yoon

Abstract:

The quality of video transmitted by mobile ad hoc networks (MANETs) can be influenced by several factors, including protocol layers; parameter settings of each protocol. In this paper, we are concerned with understanding the functional relationship between these influential factors and objective video quality in MANETs. We illustrate a systematic statistical design of experiments (DOE) strategy can be used to analyse MANET parameters and performance. Using a 2k factorial design, we quantify the main and interactive effects of 7 factors on a response metric (i.e., mean opinion score (MOS) calculated by PSNR with Evalvid package) we then develop a first-order linear regression model between the influential factors and the performance metric.

Keywords: evalvid, full factorial design, mobile ad hoc networks, ns-2

Procedia PDF Downloads 412

Authors: Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

Abstract:

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.

Keywords: machine learning, pattern clustering, pooling, classification

Procedia PDF Downloads 454

Authors: Adolfo Cangas, Noelia Navarro

Abstract:

The current study shows the assessment made by university students of a video game entitled Stigma-Stop where the characters present different mental disorders. The objective is that players have more real information about mental disorders and empathize with them and thus reduce stigma. The sample consisted of 169 university students studying degrees related to education, social care and welfare (i.e., Social Education, Psychology, Early Childhood Education, Special Education, and Social Work). The participants valued the video game positively, especially in relation to utility, being somewhat lower the score awarded to the degree of entertainment. They detect the disorders and point out that in many occasions they felt the same (particularly in the case of depression, being lower in agoraphobia and bipolar disorder, and even lower in the case of schizophrenia), most students recommend the use of the video game. They emphasize that Stigma-Stop offers intervention strategies, information regarding the symptomatology and sensitizes against stigma.

Keywords: schizophrenia, social stigma, students, mental health

Procedia PDF Downloads 281

Authors: Emmanuel Barrantes Chaves, Ernesto Rivera Alvarado

Abstract:

This paper presents a method to enable agents for the Terraria game to evaluate algorithms commonly used in general video game artificial intelligence competitions. The usage of the ‘You Only Look Once’ model in the first layer of the process obtains information from the screen, translating this information into a video game description language known as “Video Game Description Language”; the agents take that as input to make decisions. For this, the state-of-the-art algorithms were tested and compared; Monte Carlo Tree Search and Rolling Horizon Evolutionary; in this case, Rolling Horizon Evolutionary shows a better performance. This approach’s main advantage is that a VGDL beforehand is unnecessary. It will be built on the fly and opens the road for using more games as a framework for AI.

Keywords: AI, MCTS, RHEA, Terraria, VGDL, YOLOv5

Procedia PDF Downloads 93

Authors: S. M. Kulkarni, D. S. Bormane, S. L. Nalbalwar

Abstract:

The rapid development in the technology have dramatic impact on the medical health care field. Medical data base obtained with latest machines like CT Machine, MRI scanner requires large amount of memory storage and also it requires large bandwidth for transmission of data in telemedicine applications. Thus, there is need for video compression. As the database of medical images contain number of frames (slices), hence while coding of these images there is need of motion estimation. Motion estimation finds out movement of objects in an image sequence and gets motion vectors which represents estimated motion of object in the frame. In order to reduce temporal redundancy between successive frames of video sequence, motion compensation is preformed. In this paper three step search (TSS) block matching algorithm is implemented on different types of video sequences. It is shown that three step search algorithm produces better quality performance and less computational time compared with exhaustive full search algorithm.

Keywords: block matching, exhaustive search motion estimation, three step search, video compression

Procedia PDF Downloads 489

Authors: M. Prema Kumar, P. Rajesh Kumar

Abstract:

The increasing interest in image fusion (combining images of two or more modalities such as infrared and visible light radiation) has led to a need for accurate and reliable image assessment methods. This paper gives a novel approach of merging the information content from several videos taken from the same scene in order to rack up a combined video that contains the finest information coming from different source videos. This process is known as video fusion which helps in providing superior quality (The term quality, connote measurement on the particular application.) image than the source images. In this technique different sensors (whose redundant information can be reduced) are used for various cameras that are imperative for capturing the required images and also help in reducing. In this paper Image fusion technique based on multi-resolution singular value decomposition (MSVD) has been used. The image fusion by MSVD is almost similar to that of wavelets. The idea behind MSVD is to replace the FIR filters in wavelet transform with singular value decomposition (SVD). It is computationally very simple and is well suited for real time applications like in remote sensing and in astronomy.

Keywords: multi sensor image fusion, MSVD, image processing, monochrome video

Procedia PDF Downloads 570

Authors: Chen Wang, Chun Liang

Abstract:

Microsatellite instability (MSI) is characterized by high degree of polymorphism in microsatellite (MS) length due to a deficiency in mismatch repair (MMR) system. MSI is associated with several tumor types and its status can be considered as an important indicator for tumor prognostic. Conventional clinical diagnosis of MSI examines PCR products of a panel of MS markers using electrophoresis (MSI-PCR) which is laborious, time consuming, and less reliable. MSIpred, a python 2 package for automatic classification of MSI was released by this study. It computes important somatic mutation features from files in mutation annotation format (MAF) generated from paired tumor-normal exome sequencing data, subsequently using these to predict tumor MSI status with a support vector machine (SVM) classifier trained by MAF files of 1074 tumors belonging to four types. Evaluation of MSIpred on an independent 358-tumor test set achieved overall accuracy of over 98% and area under receiver operating characteristic (ROC) curve of 0.967. These results indicated that MSIpred is a robust pan-cancer MSI classification tool and can serve as a complementary diagnostic to MSI-PCR in MSI diagnosis.

Keywords: microsatellite instability, pan-cancer classification, somatic mutation, support vector machine

Procedia PDF Downloads 168

Authors: Jérémie Ochin

Abstract:

Soccer analytics are built on two data sources: the frame-by-frame position of each player on the terrain and the sequences of events, such as ball drive, pass, cross, shot, throw-in... With more than 2000 ball-events per soccer game, their precise and exhaustive annotation, based on a monocular video stream such as a TV broadcast, remains a tedious and costly manual task. State-of-the-art methods for spatio-temporal action detection from a monocular video stream, often based on 3D convolutional neural networks, are close to reach levels of performances in mean Average Precision (mAP) compatibles with the automation of such task. Nevertheless, to meet their expectation of exhaustiveness in the context of data analytics, such methods must be applied in a regime of high recall – low precision, using low confidence score thresholds. This setting unavoidably leads to the detection of false positives that are the product of the well documented overconfidence behaviour of neural networks and, in this case, their limited access to contextual information and understanding of the game: their predictions are highly unstructured. Based on the assumption that professional soccer players’ behaviour, pose, positions and velocity are highly interrelated and locally driven by the player performing a ball-action, it is hypothesized that the addition of information regarding surrounding player’s appearance, positions and velocity in the prediction methods can improve their metrics. Several methods are compared to build a proper representation of the game surrounding a player, from handcrafted features of the local graph, based on domain knowledge, to the use of Graph Neural Networks trained in an end-to-end fashion with existing state-of-the-art 3D convolutional neural networks. It is shown that the inclusion of information regarding surrounding players helps reaching higher metrics.

Keywords: fine-grained action recognition, human action recognition, convolutional neural networks, graph neural networks, spatio-temporal action recognition

Procedia PDF Downloads 22

Authors: Mr. P. Suryaprasad, R. Lalitha

Abstract:

This paper presents an efficient area and delay architectures for the implementation of one dimensional and two dimensional discrete cosine transform (DCT). These are supported to different lengths (4, 8, 16, and 32). DCT blocks are used in the different video coding standards for the image compression. The 2D- DCT calculation is made using the 2D-DCT separability property, such that the whole architecture is divided into two 1D-DCT calculations by using a transpose buffer. Based on the existing 1D-DCT architecture two different types of 2D-DCT architectures, folded and parallel types are implemented. Both of these two structures use the same transpose buffer. Proposed transpose buffer occupies less area and high speed than existing transpose buffer. Hence the area, low power and delay of both the 2D-DCT architectures are reduced.

Keywords: transposition buffer, video compression, discrete cosine transform, high efficiency video coding, two dimensional picture

Procedia PDF Downloads 519

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 98

Authors: Kamellia Reshadi, Pranav Ragji, Theodoros Soldatos

Abstract:

Recent advancements in cloud computing and storage, along with rapid progress in artificial intelligence (AI), have transformed approaches to developing efficient, scalable applications. However, integrating AI with cloud computing poses challenges as these fields are often disjointed, and many advancements remain difficult to access, obscured in complex documentation, or scattered across research reports. For this reason, we share experiences from prototype projects combining these technologies. Specifically, we focus on Google Cloud Platform (GCP) functionalities and describe vision and speech activities applied to labeling, subtitling, and urban traffic flow tasks. We describe challenges, pricing, architecture, and other key features, considering the goal of real-time performance. We hope our demonstrations provide not only essential guidelines for using these functionalities but also enable more similar approaches.

Keywords: artificial intelligence, cloud computing, real-time applications, case studies, knowledge management, research and development, text labeling, video annotation, urban traffic analysis, public safety, prototyping, Google Cloud Platform

Procedia PDF Downloads 0

Authors: Somsak Klaysung

Abstract:

This study purpose to develop video to promote cultural tourism in Taling Chan District. For qualitative research, the sample size was 40 people from 5 group of the tourism entrepreneur in Taling Chan district, conducted the key informants’ content analysis by using focus group and structures in-depth interview from all stakeholders. Quota sampling was used for this kind of research. The findings indicated that get media video marketing and tourism contribute a set length 11.35 9 minutes there is plenty of social capital in Taling Chan District including detail like local wisdom, knowledge, and way of thinking related to nature, history, historic document, occupation, administration and attribute of local people. Additional research found the new path of travel through the water route according to Khlong Bang Ramat called Route 9 temples that travelers can travel by boat are available in the market in four areas Taling Chan also as well.

Keywords: digital video, integrated marketing communication, online media development, Taling Chan district

Procedia PDF Downloads 357

Authors: Samir Benzegane, Said Sadoudi, Mustapha Djeddou

Abstract:

In this paper, we present a software development of video streaming encryption for Device-to-Device (D2D) communications by using Hyperchaos-based Random Number Generator (HRNG) implemented in C#. The software implements and uses the proposed HRNG to generate key stream for encrypting and decrypting real-time video data. The used HRNG consists of Hyperchaos Lorenz system which produces four signal outputs taken as encryption keys. The generated keys are characterized by high quality randomness which is confirmed by passing standard NIST statistical tests. Security analysis of the proposed encryption scheme confirms its robustness against different attacks.

Keywords: hyperchaos Lorenz system, hyperchaos-based random number generator, D2D communications, C#

Procedia PDF Downloads 369

Authors: Andrew Fife, Jean-Francois Esculier, Codi Ramsey, Kim Hebert-Losier

Abstract:

Objectives: We aimed to identify how an evidence-based educational video influences how runners select shoes, and perceive shoe comfort, satisfaction, and performance over three months in comparison with a control video. Design: Two groups participated in a double-blind randomised controlled trial. Method: Fifty-six runners were randomly assigned to view one of two video presentations prior to purchasing new shoes for road running in speciality stores. Runners completed a survey with regards to their own shoes and one in reference to the new shoes purchased at three timepoints: before first use, onemonth post-purchase, and three-months post-purchase. Perceived shoe comfort, satisfaction, and performance were assessed using 100 mm visual analogue scales. Factors that influenced their shoe purchase were ranked in order of importance. Results: Comfort and satisfaction were not significantly different between groups and timepoints. The perceived performance of new shoes (75.6 mm) was significantly greater than own shoes (mean: 67.6 mm) before first use, but ratings returned to own-shoe levels one month later in both groups. The group receiving the evidence-based presentation reported their purchased shoes as being influenced more by the video (55.4 mm) than the control group (21.8 mm), although both chose the same brand and model as previously worn over half of the time. Runners in both groups prioritised fit, comfort, and choosing similar shoes to the ones they previously used. Conclusions: In contrast to expectations, the evidence-based educational video did not appear to influence running shoe selection, or overall perceived shoe comfort, satisfaction, or performance.

Keywords: comfort, consumer behaviour, consciousness, education, running, shoes

Procedia PDF Downloads 29

Authors: Yuan-Hsiang Chang, Pin-Chi Lin, Li-Der Jeng

Abstract:

Advance in techniques of image and video processing has enabled the development of intelligent video surveillance systems. This study was aimed to automatically detect moving human objects and to analyze events of dual human interaction in a surveillance scene. Our system was developed in four major steps: image preprocessing, human object detection, human object tracking, and motion trajectory analysis. The adaptive background subtraction and image processing techniques were used to detect and track moving human objects. To solve the occlusion problem during the interaction, the Kalman filter was used to retain a complete trajectory for each human object. Finally, the motion trajectory analysis was developed to distinguish between the interaction and non-interaction events based on derivatives of trajectories related to the speed of the moving objects. Using a database of 60 video sequences, our system could achieve the classification accuracy of 80% in interaction events and 95% in non-interaction events, respectively. In summary, we have explored the idea to investigate a system for the automatic classification of events for interaction and non-interaction events using surveillance cameras. Ultimately, this system could be incorporated in an intelligent surveillance system for the detection and/or classification of abnormal or criminal events (e.g., theft, snatch, fighting, etc.).

Keywords: motion detection, motion tracking, trajectory analysis, video surveillance

Procedia PDF Downloads 545

Authors: Andre Peres Ramos, Franklin Cesar Flores

Abstract:

Colorization is the process of add colors to a monochromatic image or video. Usually, the process involves to segment the image in regions of interest and then apply colors to each one, for videos, this process is repeated for each frame, which makes it a tedious and time-consuming job. We propose a new assisted method for video colorization; the user only has to colorize one frame, and then the colors are propagated to following frames. The user can intervene at any time to correct eventual errors in color assignment. The method consists of to extract intensity and texture descriptors from the frames and then perform a feature matching to determine the best color for each segment. To reduce computation time and give a better spatial coherence we narrow the area of search and give weights for each feature to emphasize texture descriptors. To give a more natural result, we use an optimization algorithm to make the color propagation. Experimental results in several image sequences, compared to others existing methods, demonstrates that the proposed method perform a better colorization with less time and user interference.

Keywords: colorization, feature matching, texture descriptors, video segmentation

Procedia PDF Downloads 160