Nicolas Saunier

A feature-based tracking algorithm for vehicles in intersections

Intelligent Transportation Systems need methods to automatically monitor the road traffic, and especially track vehicles. Most research has concentrated on highways. Traffic in intersections is more variable, with multiple entrance and exit regions. This paper describes an extension to intersections of the feature-tracking algorithm described in [1]. Vehicle features are rarely tracked from their entrance in the field of view to their exit. Our algorithm can accommodate the problem caused by the disruption of feature tracks. It is evaluated on video sequences recorded on four different intersections.

Automated Analysis of Pedestrian-Vehicle Conflicts Using Video Data

Pedestrians are vulnerable road users, and despite their limited representation in traffic events, pedestrian-involved injuries and fatalities are overrepresented in traffic collisions. However, little is known about pedestrian exposure to the risk of collision, especially when compared with the amount of knowledge available for motorized traffic. More data and analysis are therefore required to understand the processes that involve pedestrians in collisions. Collision statistics alone are inadequate for the study of pedestrian–vehicle collisions because of data quantity and quality issues. Surrogate safety measures, as provided by the collection and study of traffic conflicts, were developed as a proactive complementary approach to offer more in-depth safety analysis. However, high costs and reliability issues have inhibited the extensive application of traffic conflict analysis. An automated video analysis system is presented that can (a) detect and track road users in a traffic scene and classify them as pedestrians or motorized road users, (b) identify important events that may lead to collisions, and (c) calculate several severity conflict indicators. The system seeks to classify important events and conflicts automatically but can also be used to summarize large amounts of data that can be further reviewed by safety experts. The functionality of the system is demonstrated on a video data set collected over 2 days at an intersection in downtown Vancouver, British Columbia, Canada. Four conflict indicators are automatically computed for all pedestrian–vehicle events and provide detailed insight into the conflict process. Simple detection rules on the indicators are tested to classify traffic events. This study is unique in its attempt to extract conflict indicators from video sequences in a fully automated way.

Large-Scale Automated Analysis of Vehicle Interactions and Collisions

Road collisions are a worldwide pandemic that can be addressed through the improvement of existing tools for safety analysis. A refined probabilistic framework is presented for the analysis of road-user interactions. In particular, the identification of potential collision points is used to estimate collision probabilities, and their spatial distribution can be visualized. A probabilistic time to collision is introduced, and interactions are grouped into four categories: head-on, rear-end, side, and parallel. The framework is applied to a large data set of video recordings collected in Kentucky that contains more than 300 severe interactions and collisions. The results demonstrate the usefulness of the approach for studying road-user behavior and mechanisms that may lead to collisions.

Automated Analysis of Pedestrian-Vehicle Conflicts Context for Before-and-After Studies

This paper presents a novel application of automated video analysis for a before-and-after (BA) safety evaluation of a scramble phase treatment. Data availability has been a common challenge to pedestrian studies, especially for proactive safety analysis. The traditional reliance on collision data has many shortcomings because of the quality and quantity of collision records. Qualitative and quantitative issues with road collision data are more pronounced in pedestrian safety studies. In addition, little information on the mechanism of action implicated can be drawn from collision reports. Traffic conflict techniques have been advocated as supplements or alternatives to collision-based safety analysis. Automated conflict analysis has been advocated as a new safety analysis paradigm that empowers the drawbacks of survey-based and observer-based traffic conflict analysis. One of the areas of focus of pedestrian safety that could greatly benefit from vision-based road user tracking is BA evaluation of safety treatments. This paper demonstrates the feasibility of conducting a BA analysis with video data collected from a commercial-grade camera in Chinatown, Oakland, California. Video sequences for a period of 2 h before and 2 h after scramble were automatically analyzed. The BA results of the automated analysis exhibit a declining pattern of conflict frequency, a reduction in the spatial density of conflicts, and a shift in the spatial distribution of conflicts farther from crosswalks.

Automated Analysis of Road Safety with Video Data

Traffic safety analysis has often been undertaken with historical collision data. However, well-recognized availability and quality problems are associated with collision data. In addition, the use of collision records for safety analysis is reactive: a significant number of collisions has to be recorded before action is taken. Therefore, the observation of traffic conflicts has been advocated as a complementary approach in the analysis of traffic safety. However, incomplete conceptualization and the cost of training observers and collecting conflict data have been factors inhibiting extensive application of the traffic conflict technique. The goal of this research is to develop a method for automated analysis of road safety with video sensors to address the problem of dependency on the deteriorating collision data. The method automates the extraction of traffic conflicts from video sensor data. This method should address the main shortcomings of the traffic conflict technique. A comprehensive system is described for traffic conflict detection in video data. The system is composed of a feature-based vehicle tracking algorithm adapted for intersections and a traffic conflict detection method based on the clustering of vehicle trajectories. The clustering uses a K-means approach with hidden Markov models and a simple heuristic to find the number of clusters automatically. Traffic conflicts can then be detected by identifying and adapting pairs of models of conflicting trajectories. The technique is demonstrated on real-world video sequences of traffic conflicts.

Probabilistic Framework for Automated Analysis of Exposure to Road Collisions

The advent of powerful sensing technologies, especially video sensors and computer vision techniques, has allowed for the collection of large quantities of detailed traffic data. These technologies allow further advancement toward completely automated systems for road safety analysis. This paper presents a comprehensive probabilistic framework for automated road safety analysis. Building on traffic conflict techniques and the concept of the safety hierarchy, it provides computational definitions of the probability of collision for road users involved in an interaction. It proposes new definitions for aggregated measures over time. This framework allows the interpretation of traffic from a safety perspective, by studying all interactions and their relationship to safety. New and more relevant exposure measures can be derived from this work, and traffic conflicts can be detected. A complete vision-based system is implemented to demonstrate the approach, providing experimental results on real-world video data.

Change Detection in Feature Space Using Local Binary Similarity Patterns

In general, the problem of change detection is studied in color space. Most proposed methods aim at dynamically finding the best color thresholds to detect moving objects against a background model. Background models are often complex to handle noise affecting pixels. Because the pixels are considered individually, some changes cannot be detected because it involves groups of pixels and some individual pixels may have the same appearance as the background. To solve this problem, we propose to formulate the problem of background subtraction in feature space. Instead of comparing the color of pixels in the current image with colors in a background model, features in the current image are compared with features in the background model. The use of a feature at each pixel position allows accounting for change affecting groups of pixels, and at the same time adds robustness to local perturbations. With the advent of binary feature descriptors such as BRISK or FREAK, it is now possible to use features in various applications at low computational cost. We thus propose to perform background subtraction with a small binary descriptor that we named Local Binary Similarity Patterns (LBSP). We show that this descriptor outperforms color, and that a simple background subtractor using LBSP outperforms many sophisticated state of the art methods in baseline scenarios.

Clustering Vehicle Trajectories with Hidden Markov Models Application to Automated Traffic Safety Analysis

The importance of reducing the social and economic costs associated with traffic collisions can not be over-stated. The first goal of this research is to develop a method for automated road safety analysis using video sensors in order to address the problem of a dependency on the deteriorating collision data. The method will automate the extraction of traffic conflicts (near misses) from video sensor data. To our knowledge, there is limited research primarily applied to traffic conflicts. In this paper a method based on the clustering of vehicle trajectories is presented. The clustering uses a k-means approach with hidden Markov models and a simple heuristic to find the number of clusters automatically. Traffic conflicts can then be detected by identifying and adapting pairs of models of conflicting trajectories. The technique is demonstrated on real world video sequences of traffic conflicts.

Methodologies for Aggregating Indicators of Traffic Conflict

Various indicators of objective conflict have been proposed in the literature to measure the severity of traffic events. Objective conflict indicators measure various spatial and temporal aspects of proximity on the premise that proximity is a surrogate for severity. These aspects of severity may be partially overlapping and in some cases independent. Two sets of conflict indicators were used in a study conducted to demonstrate that integration of the severity cues provided by each conflict indicator could be performed to reflect better the true, yet unobservable, severity of traffic events. The first set of conflict indicators required the presence of a collision course common to the interacting road users. The second set measured severity in mere temporal proximity between road users. The study proposes a methodology with which to aggregate the event-level measurements of conflict indicators into a safety index. First, individual conflict indicator measurements are mapped into severity intervals [0, 1]. Second, these severity indices are aggregated to a safety index that includes both individual severities and exposure. The methodology is applied on individual measurements of pedestrian–vehicle conflicts.

Urban Tracker: Multiple object tracking in urban mixed traffic

In this paper, we study the problem of detecting and tracking multiple objects of various types in outdoor urban traffic scenes. This problem is especially challenging due to the large variation of road user appearances. To handle that variation, our system uses background subtraction to detect moving objects. In order to build the object tracks, an object model is built and updated through time inside a state machine using feature points and spatial information. When an occlusion occurs between multiple objects, the positions of feature points at previous observations are used to estimate the positions and sizes of the individual occluded objects. Our Urban Tracker algorithm is validated on four outdoor urban videos involving mixed traffic that includes pedestrians, cars, large vehicles, etc. Our method compares favorably to a current state of the art feature-based tracker for urban traffic scenes on pedestrians and mixed traffic.