In recent years, State Road Route 114 which is located in Montgomery County, Virginia, has gained a bad reputation because of numerous traffic accidents. Most of these accidents resulted in loss of lives and property. Although there are many suggestions and proposals designed to prevent these acidents, to date no actions is taken yet. The focus of this research is to explore a technology-based, low cost solution that will lower or eliminate the risk of accidents on this two-lane rural highway. / Master of Science

Keeping a safe distance from the forward-leading vehicle is an essential feature of modern Advanced Driver Assistant Systems (ADAS), especially for transportation companies with a fleet of trucks. We propose in this thesis a Forward Collision Warning (FCW) system, which collects visual information using smartphones attached for instance to the windshield of a vehicle. The basic idea is to detect the forward-leading vehicle and estimate its distance from the vehicle. Given the limited resources of computation and memory of mobile devices, the main challenge of this work is running CNN-based object detectors at real-time without hurting the performance. In this thesis, we analyze the bounding boxes distribution of the vehicles, then propose an efficient and customized deep neural network for forward-leading vehicle detection. We apply a detection-tracking scheme to increase the frame rate of vehicle detection and maintain good performance. Then we propose a simple leading vehicle distance estimation approach for monocular cameras. With the techniques above, we build an FCW system that has low computation and memory requirements that are suitable for mobile devices. Our FCW system has 49% less allocated memory, 7.5% higher frame rate, and 21% less battery consumption speed than popular deep object detectors. A sample video is available at https://youtu.be/-ptvfabBZWA.

Collision warning systems represent a promising means to reduce rear-end crash involvement. However, these systems experience failures in the real-world that may promote driver distrust and diminish drivers' willingness to comply with warnings. Recent research suggests that not all false alarms (FAs) are detrimental to drivers. However, very few studies have examined how different alarms influence different driving populations. The purpose of this research was to examine how younger, middle-aged, and older drivers (with and without UFOV impairments) evaluated and responded to four different alarm contexts - false alarm (FA), nuisance alarm (NA), unnecessary alarm (UA) and true alarm (TA) - when they did and did not receive warnings. FA contexts represent out-of-path conflict scenarios where it is difficult for the driver to identify the source of the alarm. NA contexts represent out-of-path conflict scenarios that occur in a predictable manner that allows drivers to identify the source of the alarm. UA contexts are transitioning host conflict scenarios where the system issues an alert but the situation resolves itself before the driver needs to intervene. TA contexts represent in-host conflict scenarios where the situation requires the driver to intervene to avoid a collision. The results suggest that alarm context does matter. Compared to response data that differentiates FA and NA from UA and TA, subjective data shows greater sensitivity and differentiates between all four alarm contexts (FA Younger drivers indicated a high degree of confidence in their own ability across the different conditions. While they adopted a similar response pattern as middle-aged drivers during the TA contexts, these drivers responded less frequently than middle-aged and older drivers during the UA context. Diminished hazard perception ability and the tendency to consider these situations less hazardous likely account for the fewer responses made during these situations by younger drivers. Older drivers with and without UFOV impairments indicated similar hazard ratings for UA and TA contexts, yet drivers with UFOV impairments responded less frequently in both alarm contexts. Diminished hazard perception ability, slower simple response times, and degraded contrast sensitivity likely account for the fewer and slower responses. Interestingly older drivers with impairments did respond more frequently when warned during the TA context. They also rated FAs and NAs more positively than the other driver groups. The results of this study suggest applying signal detection theory without concern for the alarm context and driver characteristics is insufficient for understanding how different alarms influence operators and that subjective data can inform design. Researchers are encouraged to combine multiple perspectives that incorporate of both an engineering and human perspective.

No description available.

Objective: Systems that can warn the driver of a possible collision with a vulnerable road user (VRU) have significant safety benefits. However, incorrect warning times can have adverse effects on the driver. If the warning is too late, drivers might not be able to react; if the warning is too early, drivers can become annoyed and might turn off the system. Currently, there are no methods to determine the right timing for a warning to achieve high effectiveness and acceptance by the driver. This study aims to validate a driver model as the basis for selecting appropriate warning times. The timing of the forward collision warnings (FCWs) selected for the current study was based on the comfort boundary (CB) model developed during a previous project, which describes the moment a driver would brake. Drivers’ acceptance toward these warnings was analyzed. The present study was conducted as part of the European research project PROSPECT (“Proactive Safety for Pedestrians and Cyclists”). Methods: Two warnings were selected: One inside the CB and one outside the CB. The scenario tested was a cyclist crossing scenario with time to arrival (TTA) of 4 s (it takes the cyclist 4 s to reach the intersection). The timing of the warning inside the CB was at a time to collision (TTC) of 2.6 s (asymptotic value of the model at TTA = 4 s) and the warning outside the CB was at TTC = 1.7 s (below the lower 95% value at TTA = 4 s). Thirty-one participants took part in the test track study (between-subjects design where warning time was the independent variable). Participants were informed that they could brake any moment after the warning was issued. After the experiment, participants completed an acceptance survey. Results: Participants reacted faster to the warning outside the CB compared to the warning inside the CB. This confirms that the CB model represents the criticality felt by the driver. Participants also rated the warning inside the CB as more disturbing, and they had a higher acceptance of the system with the warning outside the CB. The above results confirm the possibility of developing wellsaccepted warnings based on driver models. Conclusions: Similar to other studies’ results, drivers prefer warning times that compare with their driving behavior. It is important to consider that the study tested only one scenario. In addition, in this study, participants were aware of the appearance of the cyclist and the warning. A further investigation should be conducted to determine the acceptance of distracted drivers.

<div>An Autonomous vehicle depends on the combination of latest technology or the ADAS safety features such as Adaptive cruise control (ACC), Autonomous Emergency Braking (AEB), Automatic Parking, Blind Spot Monitor, Forward Collision Warning or Avoidance (FCW or FCA), Lane Departure Warning. The current trend follows incorporation of these technologies using the Artificial neural network or Deep neural network, as an imitation of the traditionally used algorithms. Recent research in the field of deep learning and development of competent processors for autonomous or self driving car have shown amplitude of prospect, but there are many complexities for hardware deployment because of limited resources such as memory, computational power, and energy. Deployment of several mentioned ADAS safety feature using multiple sensors and individual processors, increases the integration complexity and also results in the distribution of the system, which is very pivotal for autonomous vehicles.</div><div><br></div><div>This thesis attempts to tackle two important adas safety feature: Forward collision Warning, and Object Detection using the machine learning and Deep Neural Networks and there deployment in the autonomous embedded platform.</div><div><br></div><div><div>This thesis proposes the following: </div><div>1. A machine learning based approach for the forward collision warning system in an autonomous vehicle.<br></div><div>2.3-D object detection using Lidar and Camera which is primarily based on Lidar Point Clouds. </div><div><br></div><div>The proposed forward collision warning model is based on the forward facing automotive radar providing the sensed input values such as acceleration, velocity and separation distance to a classifier algorithm which on the basis of supervised learning model, alerts the driver of possible collision. Decision Tress, Linear Regression, Support Vector Machine, Stochastic Gradient Descent, and a Fully Connected Neural Network is used for the prediction purpose.</div><div><br></div><div>The second proposed methods uses object detection architecture, which combines the 2D object detectors and a contemporary 3D deep learning techniques. For this approach, the 2D object detectors is used first, which proposes a 2D bounding box on the images or video frames. Additionally a 3D object detection technique is used where the point clouds are instance segmented and based on raw point clouds density a 3D bounding box is predicted across the previously segmented objects.</div></div>

<div>Self driving cars becoming more popular nowadays, which transport with it's own intelligence and take appropriate actions at adequate time. Safety is the key factor in driving environment. A simple fail of action can cause many fatalities. Computer Vision has major part in achieving this, it help the autonomous vehicle to perceive the surroundings. Detection is a very popular technique in helping to capture the surrounding for an autonomous car. At the same time tracking also has important role in this by providing dynamic of detected objects. Autonomous cars combine a variety of sensors such as RADAR, LiDAR, sonar, GPS, odometry and inertial measurement units to perceive their surroundings. Driver-assistive technologies like Adaptive Cruise Control, Forward Collision Warning system (FCW) and Collision Mitigation by Breaking (CMbB) ensure safety while driving.</div><div>Perceiving the information from environment include setting up sensors on the car. These sensors will collect the data it sees and this will be further processed for taking actions. The sensor system can be a single sensor or multiple sensor. Different sensors have different strengths and weaknesses which makes the combination of them important for technologies like Autonomous Driving. Each sensor will have a limit of accuracy on it's readings, so multi sensor system can help to overcome this defects. This thesis is an attempt to develop a multi sensor multi object tracking method to perceive the surrounding of the ego vehicle. When the Object detection gives information about the presence of objects in a frame, Object Tracking goes beyond simple observation to more useful action of monitoring objects. The experimental results conducted on KITTI dataset indicate that our proposed state estimation system for Multi Object Tracking works well in various challenging environments.</div>

Augmented reality (AR) has the potential to fundamentally change the way we interact with information. Direct perception of computer generated graphics atop physical reality can afford hands-free access to contextual information on the fly. However, as users must interact with both digital and physical information simultaneously, yesterday's approaches to interface design may not be sufficient to support the new way of interaction. Furthermore, the impacts of this novel technology on user experience and performance are not yet fully understood. Driving is one of many promising tasks that can benefit from AR, where conformal graphics strategically placed in the real-world can accurately guide drivers' attention to critical environmental elements. The ultimate purpose of this study is to reduce pedestrian accidents through design of driver interfaces that take advantage of AR head-up displays (HUD). For this purpose, this work aimed to (1) identify information requirements for pedestrian collision warning, (2) design AR driver interfaces, and (3) quantify effects of AR interfaces on driver performance and experience. Considering the dynamic nature of human-environment interaction in AR-supported driving, we took an ecological approach for interface design and evaluation, appreciating not only the user but also the environment. The requirement analysis examined environmental constraints imposed on the drivers' behavior, interface design translated those behavior-shaping constraints into perceptual forms of interface elements, and usability evaluations utilized naturalistic driving scenarios and tasks for better ecological validity. A novel AR driver interface for pedestrian collision warning, the virtual shadow, was proposed taking advantage of optical see-through HUDs. A series of usability evaluations in both a driving simulator and on an actual roadway showed that virtual shadow interface outperformed current pedestrian collision warning interfaces in guiding driver attention, increasing situation awareness, and improving task performance. Thus, this work has demonstrated the opportunity of incorporating an ecological approach into user interface design and evaluation for AR driving applications. This research provides both basic and practical contributions in human factors and AR by (1) providing empirical evidence furthering knowledge about driver experience and performance in AR, and, (2) extending traditional usability engineering methods for automotive AR interface design and evaluation. / Ph. D.

The purpose of the present study was to examine effects of driver, vehicle, and environment characteristics on Collision Warning System (CWS) design. One hypothesis was made that the capability of collision avoidance would not be same among a driver, vehicle, and environment group with different characteristics. Accident analysis and quantitative analysis was used to examine this hypothesis in terms of ‘risk’ and ‘safety margin’ respectively. Rear-end collision had a stronger focus in the present study. As a result of accident analysis, heavy truck showed a higher susceptibility of the fatal rear-end accidents than car and light truck. Also, dry road surface compared to wet or snow, dark condition compared to daylight condition, straight road compared to curved road, level road compared to grade, crest or sag, roadway having more than 5 travel lanes compared to roadway having 2, 3 or 4 travel lanes showed a higher susceptibility of the fatal rear-end accidents. Relative rear-end accidents involvement proportion compared to the other types of collision was used as a measure of susceptibility. As a result of quantitative analysis, a significant difference in terms of Required Minimum Warning Distance (RMWD) was made among a different vehicle type and braking system group. However, relatively small difference was made among a different age, gender group in terms of RMWD. Based on the result, breaking performance of vehicle should be regarded as an input variable in the design of CWS, specifically warning timing criteria, was concluded.

<p>The purpose of the present study was to examine effects of driver, vehicle, and environment characteristics on Collision Warning System (CWS) design. One hypothesis was made that the capability of collision avoidance would not be same among a driver, vehicle, and environment group with different characteristics. Accident analysis and quantitative analysis was used to examine this hypothesis in terms of ‘risk’ and ‘safety margin’ respectively. Rear-end collision had a stronger focus in the present study. </p><p>As a result of accident analysis, heavy truck showed a higher susceptibility of the fatal rear-end accidents than car and light truck. Also, dry road surface compared to wet or snow, dark condition compared to daylight condition, straight road compared to curved road, level road compared to grade, crest or sag, roadway having more than 5 travel lanes compared to roadway having 2, 3 or 4 travel lanes showed a higher susceptibility of the fatal rear-end accidents. Relative rear-end accidents involvement proportion compared to the other types of collision was used as a measure of susceptibility. </p><p>As a result of quantitative analysis, a significant difference in terms of Required Minimum Warning Distance (RMWD) was made among a different vehicle type and braking system group. However, relatively small difference was made among a different age, gender group in terms of RMWD. Based on the result, breaking performance of vehicle should be regarded as an input variable in the design of CWS, specifically warning timing criteria, was concluded.</p>