Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 16

Search results for: ADAS

16 Self-Calibration of Fish-Eye Camera for Advanced Driver Assistance Systems

Authors: Atef Alaaeddine Sarraj, Brendan Jackman, Frank Walsh


Tomorrow’s car will be more automated and increasingly connected. Innovative and intuitive interfaces are essential to accompany this functional enrichment. For that, today the automotive companies are competing to offer an advanced driver assistance system (ADAS) which will be able to provide enhanced navigation, collision avoidance, intersection support and lane keeping. These vision-based functions require an accurately calibrated camera. To achieve such differentiation in ADAS requires sophisticated sensors and efficient algorithms. This paper explores the different calibration methods applicable to vehicle-mounted fish-eye cameras with arbitrary fields of view and defines the first steps towards a self-calibration method that adequately addresses ADAS requirements. In particular, we present a self-calibration method after comparing different camera calibration algorithms in the context of ADAS requirements. Our method gathers data from unknown scenes while the car is moving, estimates the camera intrinsic and extrinsic parameters and corrects the wide-angle distortion. Our solution enables continuous and real-time detection of objects, pedestrians, road markings and other cars. In contrast, other camera calibration algorithms for ADAS need pre-calibration, while the presented method calibrates the camera without prior knowledge of the scene and in real-time.

Keywords: advanced driver assistance system (ADAS), fish-eye, real-time, self-calibration

Procedia PDF Downloads 155
15 Vehicle Risk Evaluation in Low Speed Accidents: Consequences for Relevant Test Scenarios

Authors: Philip Feig, Klaus Gschwendtner, Julian Schatz, Frank Diermeyer


Projects of accident research analysis are mostly focused on accidents involving personal damage. Property damage only has a high frequency of occurrence combined with high economic impact. This paper describes main influencing parameters for the extent of damage and presents a repair cost model. For a prospective evaluation method of the monetary effect of advanced driver assistance systems (ADAS), it is necessary to be aware of and quantify all influencing parameters. Furthermore, this method allows the evaluation of vehicle concepts in combination with an ADAS at an early point in time of the product development process. In combination with a property damage database and the introduced repair cost model relevant test scenarios for specific vehicle configurations and their individual property damage risk may be determined. Currently, equipment rates of ADAS are low and a purchase incentive for customers would be beneficial. The next ADAS generation will prevent property damage to a large extent or at least reduce damage severity. Both effects may be a purchasing incentive for the customer and furthermore contribute to increased traffic safety.

Keywords: accident research, accident scenarios, ADAS, effectiveness, property damage analysis

Procedia PDF Downloads 258
14 Real-Time Lane Marking Detection Using Weighted Filter

Authors: Ayhan Kucukmanisa, Orhan Akbulut, Oguzhan Urhan


Nowadays, advanced driver assistance systems (ADAS) have become popular, since they enable safe driving. Lane detection is a vital step for ADAS. The performance of the lane detection process is critical to obtain a high accuracy lane departure warning system (LDWS). Challenging factors such as road cracks, erosion of lane markings, weather conditions might affect the performance of a lane detection system. In this paper, 1-D weighted filter based on row filtering to detect lane marking is proposed. 2-D input image is filtered by 1-D weighted filter considering four-pixel values located symmetrically around the center of candidate pixel. Performance evaluation is carried out by two metrics which are true positive rate (TPR) and false positive rate (FPR). Experimental results demonstrate that the proposed approach provides better lane marking detection accuracy compared to the previous methods while providing real-time processing performance.

Keywords: lane marking filter, lane detection, ADAS, LDWS

Procedia PDF Downloads 109
13 Adjustable Aperture with Liquid Crystal for Real-Time Range Sensor

Authors: Yumee Kim, Seung-Guk Hyeon, Kukjin Chun


An adjustable aperture using a liquid crystal is proposed for real-time range detection and obtaining images simultaneously. The adjustable aperture operates as two types of aperture stops which can create two different Depth of Field images. By analyzing these two images, the distance can be extracted from camera to object. Initially, the aperture stop has large size with zero voltage. When the input voltage is applied, the aperture stop transfer to smaller size by orientational transition of liquid crystal molecules in the device. The diameter of aperture stop is 1.94mm and 1.06mm. The proposed device has low driving voltage of 7.0V and fast response time of 6.22m. Compact size aperture of 6×6×1.1 mm3 is assembled in conventional camera which contain 1/3” HD image sensor and focal length of 3.3mm that can be used in autonomous. The measured range was up to 5m. The adjustable aperture has high stability due to no mechanically moving parts. This range sensor can be applied to the various field of 3D depth map application which is the Advanced Driving Assistance System (ADAS), drones and manufacturing machine.

Keywords: adjustable aperture, dual aperture, liquid crystal, ranging and imaging, ADAS, range sensor

Procedia PDF Downloads 309
12 Moving Object Detection Using Histogram of Uniformly Oriented Gradient

Authors: Wei-Jong Yang, Yu-Siang Su, Pau-Choo Chung, Jar-Ferr Yang


Moving object detection (MOD) is an important issue in advanced driver assistance systems (ADAS). There are two important moving objects, pedestrians and scooters in ADAS. In real-world systems, there exist two important challenges for MOD, including the computational complexity and the detection accuracy. The histogram of oriented gradient (HOG) features can easily detect the edge of object without invariance to changes in illumination and shadowing. However, to reduce the execution time for real-time systems, the image size should be down sampled which would lead the outlier influence to increase. For this reason, we propose the histogram of uniformly-oriented gradient (HUG) features to get better accurate description of the contour of human body. In the testing phase, the support vector machine (SVM) with linear kernel function is involved. Experimental results show the correctness and effectiveness of the proposed method. With SVM classifiers, the real testing results show the proposed HUG features achieve better than classification performance than the HOG ones.

Keywords: moving object detection, histogram of oriented gradient, histogram of uniformly-oriented gradient, linear support vector machine

Procedia PDF Downloads 321
11 Embedded Hardware and Software Design of Omnidirectional Autonomous Robotic Platform Suitable for Advanced Driver Assistance Systems Testing with Focus on Modularity and Safety

Authors: Ondrej Lufinka, Jan Kaderabek, Juraj Prstek, Jiri Skala, Kamil Kosturik


This paper deals with the problem of using Autonomous Robotic Platforms (ARP) for the ADAS (Advanced Driver Assistance Systems) testing in automotive. There are different possibilities of the testing already in development, and lately, the autonomous robotic platforms are beginning to be used more and more widely. Autonomous Robotic Platform discussed in this paper explores the hardware and software design possibilities related to the field of embedded systems. The paper focuses on its chapters on the introduction of the problem in general; then, it describes the proposed prototype concept and its principles from the embedded HW and SW point of view. It talks about the key features that can be used for the innovation of these platforms (e.g., modularity, omnidirectional movement, common and non-traditional sensors used for localization, synchronization of more platforms and cars together, or safety mechanisms). In the end, the future possible development of the project is discussed as well.

Keywords: advanced driver assistance systems, ADAS, autonomous robotic platform, embedded systems, hardware, localization, modularity, multiple robots synchronization, omnidirectional movement, safety mechanisms, software

Procedia PDF Downloads 61
10 A Review of In-Vehicle Network for Cloud Connected Vehicle

Authors: Hanbhin Ryu, Ilkwon Yun


Automotive industry targets to provide an improvement in safety and convenience through realizing fully autonomous vehicle. For partially realizing fully automated driving, Current vehicles already feature varieties of advanced driver assistance system (ADAS) for safety and infotainment systems for the driver’s convenience. This paper presents Cloud Connected Vehicle (CCV) which connected vehicles with cloud data center via the access network to control the vehicle for achieving next autonomous driving form and describes its features. This paper also describes the shortcoming of the existing In-Vehicle Network (IVN) to be a next generation IVN of CCV and organize the 802.3 Ethernet, the next generation of IVN, related research issue to verify the feasibility of using Ethernet. At last, this paper refers to additional considerations to adopting Ethernet-based IVN for CCV.

Keywords: autonomous vehicle, cloud connected vehicle, ethernet, in-vehicle network

Procedia PDF Downloads 398
9 Lane Detection Using Labeling Based RANSAC Algorithm

Authors: Yeongyu Choi, Ju H. Park, Ho-Youl Jung


In this paper, we propose labeling based RANSAC algorithm for lane detection. Advanced driver assistance systems (ADAS) have been widely researched to avoid unexpected accidents. Lane detection is a necessary system to assist keeping lane and lane departure prevention. The proposed vision based lane detection method applies Canny edge detection, inverse perspective mapping (IPM), K-means algorithm, mathematical morphology operations and 8 connected-component labeling. Next, random samples are selected from each labeling region for RANSAC. The sampling method selects the points of lane with a high probability. Finally, lane parameters of straight line or curve equations are estimated. Through the simulations tested on video recorded at daytime and nighttime, we show that the proposed method has better performance than the existing RANSAC algorithm in various environments.

Keywords: Canny edge detection, k-means algorithm, RANSAC, inverse perspective mapping

Procedia PDF Downloads 119
8 Automated Driving Deep Neural Networks Model Accuracy and Performance Assessment in a Simulated Environment

Authors: David Tena-Gago, Jose M. Alcaraz Calero, Qi Wang


The evolution and integration of automated vehicles have become more and more tangible in recent years. State-of-the-art technological advances in the field of camera-based Artificial Intelligence (AI) and computer vision greatly favor the performance and reliability of the Advanced Driver Assistance System (ADAS), leading to a greater knowledge of vehicular operation and resembling human behavior. However, the exclusive use of this technology still seems insufficient to control vehicular operation at 100%. To reveal the degree of accuracy of the current camera-based automated driving AI modules, this paper studies the structure and behavior of one of the main solutions in a controlled testing environment. The results obtained clearly outline the lack of reliability when using exclusively the AI model in the perception stage, thereby entailing using additional complementary sensors to improve its safety and performance.

Keywords: accuracy assessment, AI-driven mobility, artificial intelligence, automated vehicles

Procedia PDF Downloads 31
7 Enhancement Dynamic Cars Detection Based on Optimized HOG Descriptor

Authors: Mansouri Nabila, Ben Jemaa Yousra, Motamed Cina, Watelain Eric


Research and development efforts in intelligent Advanced Driver Assistance Systems (ADAS) seek to save lives and reduce the number of on-road fatalities. For traffic and emergency monitoring, the essential but challenging task is vehicle detection and tracking in reasonably short time. This purpose needs first of all a powerful dynamic car detector model. In fact, this paper presents an optimized HOG process based on shape and motion parameters fusion. Our proposed approach mains to compute HOG by bloc feature from foreground blobs using configurable research window and pathway in order to overcome the shortcoming in term of computing time of HOG descriptor and improve their dynamic application performance. Indeed we prove in this paper that HOG by bloc descriptor combined with motion parameters is a very suitable car detector which reaches in record time a satisfactory recognition rate in dynamic outside area and bypasses several popular works without using sophisticated and expensive architectures such as GPU and FPGA.

Keywords: car-detector, HOG, motion, computing time

Procedia PDF Downloads 240
6 The Need for a One Health and Welfare Approach to Industrial Animal Farming

Authors: Clinton Adas


Industrial animal farming contributes to numerous problems that humans face, and among these, antimicrobial resistance (AMR) has been identified by the World Health Organisation as a real possibility for the 21st Century. While numerous factors contribute to AMR, one of them is industrial animal farming and its effect on the food chain and environment. In 2017, livestock were given around 73% of all antibiotics worldwide to make them grow faster for profit purposes, to prevent illness caused by unhealthy living conditions, and to treat disease when it breaks out. Many of the antibiotics used provide little benefit to animals, and most are the same as those used by humans - including many deemed critical to human health that should be used sparingly. AMR contributes to millions of illnesses, and in 2019 was responsible for around 4.95 million deaths worldwide. It costs Europe around nine billion euros per year, while it costs the United States (US) around 20 billion dollars per year. While not a simple or quick solution, one way to begin to address the challenge of AMR and other harms from this type of farming is to focus on animal welfare as part of a One Health and Welfare approach, as better welfare requires less antibiotics usage, which may begin to break the cycle.

Keywords: animal and human welfare, industrial animal farming, antimicrobial resistance, one health and welfare, sustainable development goals

Procedia PDF Downloads 6
5 Atypical Familial Amyotrophic Lateral Sclerosis Secondary to Superoxide Dismutase 1 Gene Mutation With Coexistent Axonal Polyneuropathy: A Challenging Diagnosis

Authors: Seraj Makkawi, Abdulaziz A. Alqarni, Himyan Alghaythee, Suzan Y. Alharbi, Anmar Fatani, Reem Adas, Ahmad R. Abuzinadah


Amyotrophic lateral sclerosis (ALS), also known as Lou Gehrig's disease, is a neurodegenerative disease that involves both the upper and lower motor neurons. Familial ALS, including superoxide dismutase 1 (SOD1) mutation, accounts for 5-10% of all cases of ALS. Typically, the symptoms of ALS are purely motor, though coexistent sensory symptoms have been reported in rare cases. In this report, we describe the case of a 47- year-old man who presented with progressive bilateral lower limb weakness and numbness for the last four years. A nerve conduction study (NCS) showed evidence of coexistent axonal sensorimotor polyneuropathy in addition to the typical findings of ALS in needle electromyography. Genetic testing confirmed the diagnosis of familial ALS secondary to the SOD1 genetic mutation. This report highlights that the presence of sensory symptoms should not exclude the possibility of ALS in an appropriate clinical setting.

Keywords: Saudi Arabia, polyneuropathy, SOD1 gene mutation, familial amyotrophic lateral sclerosis, amyotrophic lateral sclerosis

Procedia PDF Downloads 28
4 Advanced Driver Assistance System: Veibra

Authors: C. Fernanda da S. Sampaio, M. Gabriela Sadith Perez Paredes, V. Antonio de O. Martins


Today the transport sector is undergoing a revolution, with the rise of Advanced Driver Assistance Systems (ADAS), industry and society itself will undergo a major transformation. However, the technological development of these applications is a challenge that requires new techniques and great machine learning and artificial intelligence. The study proposes to develop a vehicular perception system called Veibra, which consists of two front cameras for day/night viewing and an embedded device capable of working with Yolov2 image processing algorithms with low computational cost. The strategic version for the market is to assist the driver on the road with the detection of day/night objects, such as road signs, pedestrians, and animals that will be viewed through the screen of the phone or tablet through an application. The system has the ability to perform real-time driver detection and recognition to identify muscle movements and pupils to determine if the driver is tired or inattentive, analyzing the student's characteristic change and following the subtle movements of the whole face and issuing alerts through beta waves to ensure the concentration and attention of the driver. The system will also be able to perform tracking and monitoring through GSM (Global System for Mobile Communications) technology and the cameras installed in the vehicle.

Keywords: advanced driver assistance systems, tracking, traffic signal detection, vehicle perception system

Procedia PDF Downloads 76
3 Visual Inspection of Road Conditions Using Deep Convolutional Neural Networks

Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas


This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).

Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems

Procedia PDF Downloads 54
2 Active Displacement Areas (ADA) Tools for Satellite InSAR-Based Ground Displacement Analysis: The Granada Region

Authors: M. Cuevas-González, O. Monserrat, A. Barra, C. Reyes-Carmona, R. M. Mateos, J. P. Galves, R. Sarro, M. Cantalejo, E. Peña, M. Martínez-Corbella, J.A. Luque, J. M. Azañón, A. Millares, M. Béjar, J. A. Navarro, L. Solari


Satellite interferometry (InSAR) has become a consolidated technique for ground movement detection and monitoring in the last few years. InSAR-based techniques allow processing areas from regional/national scale up to very detailed scale such as single buildings, providing a high number of displacement measurements at low cost. However, the outputs provided by such techniques are usually not easy to understand, requiring an expert to interpret those results, which might turn out to be a time-consuming task for users who are not familiar with radar data. The availability of Sentinel-1 data at no cost since 2014 has prompted the tendency of increasingly using this technique in institutional risk management activities. The consolidation of the use of InSAR is promoted by the funding of regional, national and European programs to investigate and improve the processing performances and broaden the operational use and application of the InSAR results to monitor ground displacements. In this scenario, the development of methodologies and tools to automatize the retrieval of information and to ease the interpretation of the results is a need to improve its operational use. In this work, a series of tools developed in the framework of the projects MOMIT, SAFETY and U-Geohaz is presented and an example of use in the framework of the project RiskCoast is shown. Riskcoast focuses on the development of tools, methodologies and innovative solutions focused on the prevention and management of geological risks on the coast linked to climate change. The presented work is an example of multi-scale (medium to large) application of InSAR for geohazard applications exploiting the ADA (Active Displacement Areas) tools developed with the aim of facilitating the management, use and interpretation of InSAR-based results. The velocity of the deformation map and the displacement time series have been estimated over the test area of Granada (Spain) by processing 210 Sentinel-1 (A and B) SAR images. From these initial InSAR outputs, a semi-automatic extraction of the most significant Active Displacement Areas (ADAs) is carried out using the ADAFinder tool. The next step consists of an automatic preliminary assessment of the phenomena that are behind the detected movement using the ADAClassifier tool. The application of the ADA tools to the Riskcoast project test site encompassing the coast of Granada is shown. All these tools go in the same direction as the European Ground Motion Service (EU-GMS) project, which will provide consistent, regular and reliable information regarding natural and anthropogenic ground motion phenomena all over Europe.

Keywords: ground displacements, InSAR, natural hazards, satellite imagery

Procedia PDF Downloads 90
1 Training Scenarios for an Omnidirectional Motorized VR Pedestrian Simulator

Authors: Gerald Temme, Fabian Utesch, Kilian Gröne, Michaela Rehm, Martin Fischer


Simulation is one of the central tools to test and evaluate Advanced Driver Assistance Systems (ADAS) in an effective, repeatable and safe manner. Especially for human-centered evaluation, Human-in-the-Loop (HiL) simulators become an essential tool. With an increasing research focus on traffic in urban areas Vulnerable Road Users (VRU) and the interaction between VRUs and motorized vehicles becomes more important. While in a vehicle the focus of a driver is primary outside the chassis on the virtual environment, the attention range of VRUs already starts directly at their feet. This makes it difficult to realise a pedestrian simulator with traditional monitor and projector-based visualization systems. Head Mounted Display (HMD) based Virtual Reality (VR) solves this problem. However, when using VR, it is still difficult to provide free, unrestricted and natural walking or cycling in large virtual environments. For a VRU pedestrian simulator, the Omnideck, a motorized omnidirectional 360° treadmill is the state-of-the-art solution for free walking. Although the human motion sequence on such a system is approaching real walking behavior, walking on this system still differs from walking on a flat and stable surface. Hence, for preparation of an experiment a training scenario is mandatory in order to let the simulator users get accommodated with the facility. Main goal of such a training is to enable a stable, safe and as natural as possible walking behavior on the Omnideck. An additional goal is to bring all simulator users to an acceptable and comparable minimum skill level as starting point for experiments. Initially, the biggest challenge for training moving behavior was that new users often focused their attention strongly on their feet atop the omnidirectional motorized treadmill. As a consequence, the users often start feeling insecure and train more artificial motion sequences than necessary. To divert the user's attention away from their feet, a gamification of the training has been conducted. An increasing detailed environment together with cover story’s and a series of predefined tasks (such as: interaction with the environment or searching and counting of things) attempts to hold the attention of the user away from their feet. At the same time, these tasks guide the user through the scenarios in a structured way. Thereby, a casual training of specific movement aspects like cornering, stop and go, acceleration and deceleration is realized. The paper presents an overview about the novel DLR's multi-user laboratory (MoSAIC) pedestrian simulator hardware and describes the Unreal Engine 4 based simulation framework. Starting from this information’s the addressed requirements and the resulting three training scenarios for the Omnideck are described in detail. Finally, a questionnaire-based expert-rating from investigators of recently executed experiments on the Omnideck is given. The rating will demonstrate the usability of the new training scenarios. An outlook shows the next planned steps for further optimization and gamification of the training scenarios. Subsuming, the paper presents the importance of well-designed training scenarios in order to enable users to walk as natural as possible in a VRU simulator.

Keywords: gamification, human in the loop simulation, virtual reality, vulnerable road user, omnidirectional motorized treadmill, motion-based locomotion, pedestrian simulator, Unreal Engine 4, training scenarios

Procedia PDF Downloads 23