Search results for: Vision
390 Optimizing Machine Vision System Setup Accuracy by Six-Sigma DMAIC Approach
Authors: Joseph C. Chen
Abstract:
Machine vision system provides automatic inspection to reduce manufacturing costs considerably. However, only a few principles have been found to optimize machine vision system and help it function more accurately in industrial practice. Mostly, there were complicated and impractical design techniques to improve the accuracy of machine vision system. This paper discusses implementing the Six Sigma Define, Measure, Analyze, Improve, and Control (DMAIC) approach to optimize the setup parameters of machine vision system when it is used as a direct measurement technique. This research follows a case study showing how Six Sigma DMAIC methodology has been put into use.
Keywords: DMAIC, machine vision system, process capability, Taguchi parameter design.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1240389 Machine Vision for the Inspection of Surgical Tasks: Applications to Robotic Surgery Systems
Authors: M. Ovinis, D. Kerr, K. Bouazza-Marouf, M. Vloeberghs
Abstract:
The use of machine vision to inspect the outcome of surgical tasks is investigated, with the aim of incorporating this approach in robotic surgery systems. Machine vision is a non-contact form of inspection i.e. no part of the vision system is in direct contact with the patient, and is therefore well suited for surgery where sterility is an important consideration,. As a proof-of-concept, three primary surgical tasks for a common neurosurgical procedure were inspected using machine vision. Experiments were performed on cadaveric pig heads to simulate the two possible outcomes i.e. satisfactory or unsatisfactory, for tasks involved in making a burr hole, namely incision, retraction, and drilling. We identify low level image features to distinguish the two outcomes, as well as report on results that validate our proposed approach. The potential of using machine vision in a surgical environment, and the challenges that must be addressed, are identified and discussed.Keywords: Visual inspection, machine vision, robotic surgery.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1790388 Partial 3D Reconstruction using Evolutionary Algorithms
Authors: Mónica Pérez-Meza, Rodrigo Montúfar-Chaveznava
Abstract:
When reconstructing a scenario, it is necessary to know the structure of the elements present on the scene to have an interpretation. In this work we link 3D scenes reconstruction to evolutionary algorithms through the vision stereo theory. We consider vision stereo as a method that provides the reconstruction of a scene using only a couple of images of the scene and performing some computation. Through several images of a scene, captured from different positions, vision stereo can give us an idea about the threedimensional characteristics of the world. Vision stereo usually requires of two cameras, making an analogy to the mammalian vision system. In this work we employ only a camera, which is translated along a path, capturing images every certain distance. As we can not perform all computations required for an exhaustive reconstruction, we employ an evolutionary algorithm to partially reconstruct the scene in real time. The algorithm employed is the fly algorithm, which employ “flies" to reconstruct the principal characteristics of the world following certain evolutionary rules.Keywords: 3D Reconstruction, Computer Vision, EvolutionaryAlgorithms, Vision Stereo.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1876387 A 2D-3D Hybrid Vision System for Robotic Manipulation of Randomly Oriented Objects
Authors: Moulay A. Akhloufi
Abstract:
This paper presents an new vision technique for robotic manipulation of randomly oriented objects in industrial applications. The proposed approach uses 2D and 3D vision for efficiently extracting the 3D pose of an object in the presence of multiple randomly positioned objects. 2D vision permits to quickly select the objects of interest for 3D processing with a new modified ICP algorithm (FaR-ICP), thus reducing significantly the processing time. The extracted 3D pose is then sent to the robot manipulator for picking. The tests show that the proposed system achieves high performancesKeywords: 3D vision, Hand-Eye calibration, robot visual servoing, random bin picking.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1805386 The Visual Inspection of Surgical Tasks Using Machine Vision: Applications to Robotic Surgery
Authors: M. Ovinis, D. Kerr, K. Bouazza-Marouf, M. Vloeberghs
Abstract:
In this paper, the feasibility of using machine vision to assess task completion in a surgical intervention is investigated, with the aim of incorporating vision based inspection in robotic surgery systems. The visually rich operative field presents a good environment for the development of automated visual inspection techniques in these systems, for a more comprehensive approach when performing a surgical task. As a proof of concept, machine vision techniques were used to distinguish the two possible outcomes i.e. satisfactory or unsatisfactory, of three primary surgical tasks involved in creating a burr hole in the skull, namely incision, retraction, and drilling. Encouraging results were obtained for the three tasks under consideration, which has been demonstrated by experiments on cadaveric pig heads. These findings are suggestive for the potential use of machine vision to validate successful task completion in robotic surgery systems. Finally, the potential of using machine vision in the operating theatre, and the challenges that must be addressed, are identified and discussed.
Keywords: Machine vision, robotic surgery, visual inspection.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1646385 A Study on the Location and Range of Obstacle Region in Robot's Point Placement Task based on the Vision Control Algorithm
Authors: Jae Kyung Son, Wan Shik Jang, Sung hyun Shim, Yoon Gyung Sung
Abstract:
This paper is concerned with the application of the vision control algorithm for robot's point placement task in discontinuous trajectory caused by obstacle. The presented vision control algorithm consists of four models, which are the robot kinematic model, vision system model, parameters estimation model, and robot joint angle estimation model.When the robot moves toward a target along discontinuous trajectory, several types of obstacles appear in two obstacle regions. Then, this study is to investigate how these changes will affect the presented vision control algorithm.Thus, the practicality of the vision control algorithm is demonstrated experimentally by performing the robot's point placement task in discontinuous trajectory by obstacle.
Keywords: Vision control algorithm, location of obstacle region, range of obstacle region, point placement.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1393384 K-best Night Vision Devices by Multi-Criteria Mixed-Integer Optimization Modeling
Authors: Daniela I. Borissova, Ivan C. Mustakerov
Abstract:
The paper describes an approach for defining of k-best night vision devices based on multi-criteria mixed-integer optimization modeling. The parameters of night vision devices are considered as criteria that have to be optimized. Using different user preferences for the relative importance between parameters different choice of k-best devices can be defined. An ideal device with all of its parameters at their optimum is used to determine how far the particular device from the ideal one is. A procedure for evaluation of deviation between ideal solution and k-best solutions is presented. The applicability of the proposed approach is numerically illustrated using real night vision devices data. The proposed approach contributes to quality of decisions about choice of night vision devices by making the decision making process more certain, rational and efficient.
Keywords: K-best devices, mixed-integer model, multi-criteria problem, night vision devices.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1794383 A Stereo Image Processing System for Visually Impaired
Authors: G. Balakrishnan, G. Sainarayanan, R. Nagarajan, Sazali Yaacob
Abstract:
This paper presents a review on vision aided systems and proposes an approach for visual rehabilitation using stereo vision technology. The proposed system utilizes stereo vision, image processing methodology and a sonification procedure to support blind navigation. The developed system includes a wearable computer, stereo cameras as vision sensor and stereo earphones, all moulded in a helmet. The image of the scene infront of visually handicapped is captured by the vision sensors. The captured images are processed to enhance the important features in the scene in front, for navigation assistance. The image processing is designed as model of human vision by identifying the obstacles and their depth information. The processed image is mapped on to musical stereo sound for the blind-s understanding of the scene infront. The developed method has been tested in the indoor and outdoor environments and the proposed image processing methodology is found to be effective for object identification.Keywords: Blind navigation, stereo vision, image processing, object preference, music tones.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4102382 Vision Based Robot Experiment: Measurement of Path Related Characteristics
Authors: M. H. Korayem, K. Khoshhal, H. Aliakbarpour
Abstract:
In this paper, a vision based system has been used for controlling an industrial 3P Cartesian robot. The vision system will recognize the target and control the robot by obtaining images from environment and processing them. At the first stage, images from environment are changed to a grayscale mode then it can diverse and identify objects and noises by using a threshold objects which are stored in different frames and then the main object will be recognized. This will control the robot to achieve the target. A vision system can be an appropriate tool for measuring errors of a robot in a situation where the experimental test is conducted for a 3P robot. Finally, the international standard ANSI/RIA R15.05-2 is used for evaluating the path-related characteristics of the robot. To evaluate the performance of the proposed method experimental test is carried out.Keywords: Robot, Vision, Experiment, Standard.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1248381 Web-Based Architecture of a System for Design Assessment of Night Vision Devices
Authors: Daniela I. Borissova, Ivan C. Mustakerov, Evgeni D. Bantutov
Abstract:
Nowadays the devices of night vision are widely used both for military and civil applications. The variety of night vision applications require a variety of the night vision devices designs. A web-based architecture of a software system for design assessment before producing of night vision devices is developed. The proposed architecture of the web-based system is based on the application of a mathematical model for designing of night vision devices. An algorithm with two components – for iterative design and for intelligent design is developed and integrated into system architecture. The iterative component suggests compatible modules combinations to choose from. The intelligent component provides compatible combinations of modules satisfying given user requirements to device parameters. The proposed web-based architecture of a system for design assessment of night vision devices is tested via a prototype of the system. The testing showed the applicability of both iterative and intelligent components of algorithm.
Keywords: Night vision devices, design modeling, software architecture, web-based system.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2142380 Machine Vision System for Automatic Weeding Strategy in Oil Palm Plantation using Image Filtering Technique
Authors: Kamarul Hawari Ghazali, Mohd. Marzuki Mustafa, Aini Hussain
Abstract:
Machine vision is an application of computer vision to automate conventional work in industry, manufacturing or any other field. Nowadays, people in agriculture industry have embarked into research on implementation of engineering technology in their farming activities. One of the precision farming activities that involve machine vision system is automatic weeding strategy. Automatic weeding strategy in oil palm plantation could minimize the volume of herbicides that is sprayed to the fields. This paper discusses an automatic weeding strategy in oil palm plantation using machine vision system for the detection and differential spraying of weeds. The implementation of vision system involved the used of image processing technique to analyze weed images in order to recognized and distinguished its types. Image filtering technique has been used to process the images as well as a feature extraction method to classify the type of weed images. As a result, the image processing technique contributes a promising result of classification to be implemented in machine vision system for automated weeding strategy.Keywords: Machine vision, Automatic Weeding Strategy, filter, feature extraction
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1855379 The Role of Synthetic Data in Aerial Object Detection
Authors: Ava Dodd, Jonathan Adams
Abstract:
The purpose of this study is to explore the characteristics of developing a machine learning application using synthetic data. The study is structured to develop the application for the purpose of deploying the computer vision model. The findings discuss the realities of attempting to develop a computer vision model for practical purpose, and detail the processes, tools and techniques that were used to meet accuracy requirements. The research reveals that synthetic data represent another variable that can be adjusted to improve the performance of a computer vision model. Further, a suite of tools and tuning recommendations are provided.
Keywords: computer vision, machine learning, synthetic data, YOLOv4
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 838378 An Approach for Integration of Industrial Robot with Vision System and Simulation Software
Authors: Ahmed Sh. Khusheef, Ganesh Kothapalli, Majid Tolouei-Rad
Abstract:
Utilization of various sensors has made it possible to extend capabilities of industrial robots. Among these are vision sensors that are used for providing visual information to assist robot controllers. This paper presents a method of integrating a vision system and a simulation program with an industrial robot. The vision system is employed to detect a target object and compute its location in the robot environment. Then, the target object-s information is sent to the robot controller via parallel communication port. The robot controller uses the extracted object information and the simulation program to control the robot arm for approaching, grasping and relocating the object. This paper presents technical details of system components and describes the methodology used for this integration. It also provides a case study to prove the validity of the methodology developed.Keywords: industrial robot, integration, simulation, vision system
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2218377 Development of a Computer Vision System for the Blind and Visually Impaired Person
Authors: Roselyn A. Maaño
Abstract:
Eyes are an essential and conspicuous organ of the human body. Human eyes are outward and inward portals of the body that allows to see the outside world and provides glimpses into ones inner thoughts and feelings. Inevitable blindness and visual impairments may results from eye-related disease, trauma, or congenital or degenerative conditions that cannot be corrected by conventional means. The study emphasizes innovative tools that will serve as an aid to the blind and visually impaired (VI) individuals. The researchers fabricated a prototype that utilizes the Microsoft Kinect for Windows and Arduino microcontroller board. The prototype facilitates advanced gesture recognition, voice recognition, obstacle detection and indoor environment navigation. Open Computer Vision (OpenCV) performs image analysis, and gesture tracking to transform Kinect data to the desired output. A computer vision technology device provides greater accessibility for those with vision impairments.
Keywords: Algorithms, Blind, Computer Vision, Embedded Systems, Image Analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3592376 Human Motion Capture: New Innovations in the Field of Computer Vision
Authors: Najm Alotaibi
Abstract:
Human motion capture has become one of the major area of interest in the field of computer vision. Some of the major application areas that have been rapidly evolving include the advanced human interfaces, virtual reality and security/surveillance systems. This study provides a brief overview of the techniques and applications used for the markerless human motion capture, which deals with analyzing the human motion in the form of mathematical formulations. The major contribution of this research is that it classifies the computer vision based techniques of human motion capture based on the taxonomy, and then breaks its down into four systematically different categories of tracking, initialization, pose estimation and recognition. The detailed descriptions and the relationships descriptions are given for the techniques of tracking and pose estimation. The subcategories of each process are further described. Various hypotheses have been used by the researchers in this domain are surveyed and the evolution of these techniques have been explained. It has been concluded in the survey that most researchers have focused on using the mathematical body models for the markerless motion capture.
Keywords: Human Motion Capture, Computer Vision, Vision based, Tracking.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2480375 Capturing an Unknown Moving Target in Unknown Territory using Vision and Coordination
Authors: Kiran Ijaz, Umar Manzoor, Arshad Ali Shahid
Abstract:
In this paper we present an extension to Vision Based LRTA* (VLRTA*) known as Vision Based Moving Target Search (VMTS) for capturing unknown moving target in unknown territory with randomly generated obstacles. Target position is unknown to the agents and they cannot predict its position using any probability method. Agents have omni directional vision but can see in one direction at some point in time. Agent-s vision will be blocked by the obstacles in the search space so agent can not see through the obstacles. Proposed algorithm is evaluated on large number of scenarios. Scenarios include grids of sizes from 10x10 to 100x100. Grids had obstacles randomly placed, occupying 0% to 50%, in increments of 10%, of the search space. Experiments used 2 to 9 agents for each randomly generated maze with same obstacle ratio. Observed results suggests that VMTS is effective in locate target time, solution quality and virtual target. In addition, VMTS becomes more efficient if the number of agents is increased with proportion to obstacle ratio.Keywords: Vision, MTS, Unknown Target, Coordination, VMTS, Multi-Agent.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1456374 Powerful Laser Diode Matrixes for Active Vision Systems
Authors: Dzmitry M. Kabanau, Vladimir V. Kabanov, Yahor V. Lebiadok, Denis V. Shabrov, Pavel V. Shpak, Gevork T. Mikaelyan, Alexandr P. Bunichev
Abstract:
This article is deal with the experimental investigations of the laser diode matrixes (LDM) based on the AlGaAs/GaAs heterostructures (lasing wavelength 790-880 nm) to find optimal LDM parameters for active vision systems. In particular, the dependence of LDM radiation pulse power on the pulse duration and LDA active layer heating as well as the LDM radiation divergence are discussed.
Keywords: Active vision systems, laser diode matrixes, thermal properties, radiation divergence.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2113373 Usability Evaluation Framework for Computer Vision Based Interfaces
Authors: Muhammad Raza Ali, Tim Morris
Abstract:
Human computer interaction has progressed considerably from the traditional modes of interaction. Vision based interfaces are a revolutionary technology, allowing interaction through human actions, gestures. Researchers have developed numerous accurate techniques, however, with an exception to few these techniques are not evaluated using standard HCI techniques. In this paper we present a comprehensive framework to address this issue. Our evaluation of a computer vision application shows that in addition to the accuracy, it is vital to address human factorsKeywords: Usability evaluation, cognitive walkthrough, think aloud, gesture recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1656372 A Stereo Vision System for Top View Book Scanners
Authors: Erik Lilienblum, Robert Niese, Bernd Michaelis
Abstract:
This paper proposes a novel stereo vision technique for top view book scanners which provide us with dense 3d point clouds of page surfaces. This is a precondition to dewarp bound volumes independent of 2d information on the page. Our method is based on algorithms, which normally require the projection of pattern sequences with structured light. We use image sequences of the moving stripe lighting of the top view scanner instead of an additional light projection. Thus the stereo vision setup is simplified without losing measurement accuracy. Furthermore we improve a surface model dewarping method through introducing a difference vector based on real measurements. Although our proposed method is hardly expensive neither in calculation time nor in hardware requirements we present good dewarping results even for difficult examples.Keywords: stereo vision, 3d surface reconstruction, dewarpingdocuments, book scanner
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1579371 Double Aperture Camera for High Resolution Measurement
Authors: Venkatesh Bagaria, Nagesh AS, Varun AV
Abstract:
In the domain of machine vision, the measurement of length is done using cameras where the accuracy is directly proportional to the resolution of the camera and inversely to the size of the object. Since most of the pixels are wasted imaging the entire body as opposed to just imaging the edges in a conventional system, a double aperture system is constructed to focus on the edges to measure at higher resolution. The paper discusses the complexities and how they are mitigated to realize a practical machine vision system.Keywords: Machine Vision, double aperture camera, accurate length measurement
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1562370 The Conception of Implementation of Vision for European Forensic Science 2020 in Lithuania
Authors: Eglė Bilevičiūtė, Vidmantas Egidijus Kurapka, Snieguolė Matulienė, Sigutė Stankevičiūtė
Abstract:
The Council of European Union (EU Council) has stressed on several occasions the need for a concerted, comprehensive and effective solution to delinquency problems in EU communities. In the context of establishing a European Forensic Science Area and the development of forensic science infrastructure in Europe, EU Council believes that forensic science can significantly contribute to the efficiency of law enforcement, crime prevention and combating crimes. Lithuanian scientists have consolidated to implement a project named “Conception of the vision for European Forensic Science 2020 implementation in Lithuania” (the project is funded for the period of 1 March 2014 - 31 December 2016) with the objective to create a conception of implementation of the vision for European Forensic Science 2020 in Lithuania by 1) evaluating the current status of Lithuania’s forensic system and opportunities for its improvement; 2) analysing achievements and knowledge in investigation of crimes listed in conclusions of EU Council on the vision for European Forensic Science 2020 including creation of a European Forensic Science Area and the development of forensic science infrastructure in Europe: trafficking in human beings, organised crime and terrorism; 3) analysing conceptions of criminalistics, which differ in different EU member states due to the variety of forensic schools, and finding means for their harmonization. Apart from the conception of implementation of the vision for European Forensic Science 2020 in Lithuania, the Project is expected to suggest provisions that will be relevant to other EU countries as well. Consequently, the presented conception of implementation of vision for European Forensic Science 2020 in Lithuania could initiate a project for a common vision of European Forensic Science and contribute to the development of the EU as an area of freedom, security and justice. The article presents main ideas of the project of the conception of the vision for European Forensic Science 2020 of EU Council and analyses its legal background, as well as prospects of and challenges for its implementation in Lithuania and the EU.
Keywords: EUROVIFOR, standardization, Vision for European Forensic Science 2020.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3122369 Computer Vision Applied to Flower, Fruit and Vegetable Processing
Authors: Luis Gracia, Carlos Perez-Vidal, Carlos Gracia
Abstract:
This paper presents the theoretical background and the real implementation of an automated computer system to introduce machine vision in flower, fruit and vegetable processing for recollection, cutting, packaging, classification, or fumigation tasks. The considerations and implementation issues presented in this work can be applied to a wide range of varieties of flowers, fruits and vegetables, although some of them are especially relevant due to the great amount of units that are manipulated and processed each year over the world. The computer vision algorithms developed in this work are shown in detail, and can be easily extended to other applications. A special attention is given to the electromagnetic compatibility in order to avoid noisy images. Furthermore, real experimentation has been carried out in order to validate the developed application. In particular, the tests show that the method has good robustness and high success percentage in the object characterization.Keywords: Image processing, Vision system, Automation
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3315368 Dead-Reckoning Error Calibration using Celling Looking Vision Camera
Authors: Jae-Young Choi, Sung-Gaun Kim
Abstract:
This paper suggests a calibration method to reduce errors occurring due to mobile robot sliding during location estimation using the Dead-reckoning. Due to sliding of the mobile robot caused between its wheels and the road surface while on free run, location estimation can be erroneous. Sliding especially occurs during cornering of mobile robot. Therefore, in order to reduce these frequent sliding errors in cornering, we calibrated the mobile robot-s heading values using a vision camera and templates of the ceiling.Keywords: Dead-reckoning, Localization, Odomerty, Vision Camera
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1775367 The Corporate Vision Effect on Rajabhat University Brand Building in Thailand
Authors: Pisit Potjanajaruwit
Abstract:
This study aims to (1) investigate the corporate vision factor influencing Rajabhat University brand building in Thailand and (2) explore influences of brand building upon Rajabhat University stakeholders’ loyalty, and the research method will use mixed methods to conduct qualitative research with the quantitative research. The qualitative will approach by Indebt-interview the executive of Rathanagosin Rajabhat University group for 6 key informants and the quantitative data was collected by questionnaires distributed to stakeholder including instructors, staff, students and parents of the Rathanagosin Rajabhat University group for 400 sampling were selected by multi-stage sampling method. Data was analyzed by Structural Equation Modeling: SEM and also provide the focus group interview for confirming the model. Findings corporate vision had a direct and positive influence on Rajabhat University brand building were showed direct and positive influence on stakeholder’s loyalty and stakeholder’s loyalty was indirectly influenced by corporate vision through Rajabhat University brand building.
Keywords: Brand building, corporate vision, Rajabhat University, stakeholders’ loyalty.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 797366 An Evaluation of Neural Network Efficacies for Image Recognition on Edge-AI Computer Vision Platform
Abstract:
Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.
Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 190365 FPGA Implementation of a Vision-Based Blind Spot Warning System
Authors: Yu Ren Lin, Yu Hong Li
Abstract:
Vision-based intelligent vehicle applications often require large amounts of memory to handle video streaming and image processing, which in turn increases complexity of hardware and software. This paper presents an FPGA implement of a vision-based blind spot warning system. Using video frames, the information of the blind spot area turns into one-dimensional information. Analysis of the estimated entropy of image allows the detection of an object in time. This idea has been implemented in the XtremeDSP video starter kit. The blind spot warning system uses only 13% of its logic resources and 95k bits block memory, and its frame rate is over 30 frames per sec (fps).
Keywords: blind-spot area, image, FPGA
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1826364 FPGA Implement of a Vision Based Lane Departure Warning System
Authors: Yu Ren Lin, Yi Feng Su
Abstract:
Using vision based solution in intelligent vehicle application often needs large memory to handle video stream and image process which increase complexity of hardware and software. In this paper, we present a FPGA implement of a vision based lane departure warning system. By taking frame of videos, the line gradient of line is estimated and the lane marks are found. By analysis the position of lane mark, departure of vehicle will be detected in time. This idea has been implemented in Xilinx Spartan6 FPGA. The lane departure warning system used 39% logic resources and no memory of the device. The average availability is 92.5%. The frame rate is more than 30 frames per second (fps).
Keywords: Lane departure warning system, image, FPGA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2068363 Vision Based People Tracking System
Authors: Boukerch Haroun, Luo Qing Sheng, Li Hua Shi, Boukraa Sebti
Abstract:
In this paper we present the design and the implementation of a target tracking system where the target is set to be a moving person in a video sequence. The system can be applied easily as a vision system for mobile robot. The system is composed of two major parts the first is the detection of the person in the video frame using the SVM learning machine based on the “HOG” descriptors. The second part is the tracking of a moving person it’s done by using a combination of the Kalman filter and a modified version of the Camshift tracking algorithm by adding the target motion feature to the color feature, the experimental results had shown that the new algorithm had overcame the traditional Camshift algorithm in robustness and in case of occlusion.
Keywords: Camshift Algorithm, Computer Vision, Kalman Filter, Object tracking.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1325362 Hand Gesture Recognition using Blob Detection for Immersive Projection Display System
Authors: Hasup Lee, Yoshisuke Tateyama, Tetsuro Ogi
Abstract:
We developed a vision interface immersive projection system, CAVE in virtual rea using hand gesture recognition with computer vis background image was subtracted from current webcam and we convert the color space of the imag Then we mask skin regions using skin color range t a noise reduction operation. We made blobs fro gestures were recognized using these blobs. Using recognition, we could implement an effective bothering devices for CAVE. e framework for an reality research field vision techniques. ent image frame age into HSV space. e threshold and apply from the image and ing our hand gesture e interface without
Keywords: CAVE, Computer Vision, Ges Virtual Reality esture Recognition,
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2741361 LINUX Cluster Possibilities in 3-D PHOTO Quality Imaging and Animation
Authors: Arjun Jain, Himanshu Agrawal, Nalini Vasudevan
Abstract:
In this paper we present the PC cluster built at R.V. College of Engineering (with great help from the Department of Computer Science and Electrical Engineering). The structure of the cluster is described and the performance is evaluated by rendering of complex 3D Persistence of Vision (POV) images by the Ray-Tracing algorithm. Here, we propose an unexampled method to render such images, distributedly on a low cost scalable.Keywords: PC cluster, parallel computations, ray tracing, persistence of vision, rendering.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1543