Crowded Traffic Scenes Research Articles

An Interaction-Aware Lane Change Behavior Planner for Automated Vehicles on Highways Based on Polygon Clipping

This letter presents automated driving using polygon clipping (A-D-PolyC), a novel framework for lane change behavior planning of automated vehicles on highways. It assumes that a mission planning layer generates lane change requests. In crowded traffic scenes, various variants for the lane change execution arise. The developed algorithm identifies the maneuver variants deterministically and in bounded runtime using polygon clipping in spatiotemporal domain. The variants are represented using a graph that captures the scene topology. Afterward, it efficiently samples optimal lateral and longitudinal trajectories with regard to vehicle dynamics. The satisfaction of hard constraints is checked. Finally, a scene prediction is conducted for a subset of the sampled trajectories. In comparison with most state of the art approaches, the framework accounts for traffic interaction and collects meaningful features. A novel measure based on generalized kinetic energies for the impact of a maneuver execution on the whole traffic scene is introduced. A-D-PolyC is a hierarchical, holistic, modular, and parallelizable concept that can be coupled with different scene prediction engines and lower-level local trajectory planners. The performance of A-D-PolyC is statistically evaluated using randomized simulation runs and compared to a state of the art approach.

Complex Video Scene Analysis Using Kernelized-Collaborative Behavior Pattern Learning Based on Hierarchical Representative Object Behaviors

This paper considers an unsupervised learning algorithm that can automatically discover key behavior patterns to characterize a complex video scene. For behavior features (bFs) extracted at multiple spatial-temporal scales, an optimization problem is formulated to cluster bFs in their scales while establishing a collaborative nonlinear relationship in the form of a kernel regression function among clustered bFs across different spatial scales. The relationship allows features extracted in one scale to be considered as contextual information in the analysis of another scale. This optimization problem is solved using linear programming to reduce computational complexity. The proposed algorithm is evaluated on four crowded traffic scenes and two sports video data sets. Experimental results show that the proposed algorithm achieves a better performance compared with the current state-of-the-art algorithms in terms of video segmentation accuracy.

A vehicle classification system based on hierarchical multi-SVMs in crowded traffic scenes

Automatic vehicle classification is very important for video surveillance, especially for intelligent transportation system. Currently, some approaches have been proposed. However, almost all of these methods cannot play well in the practical crowded traffic scenes with heavy occlusions, shadows, and different views, etc. To solve this difficult problem, we propose a new vehicle classification method based on hierarchical multi-SVMs. First, we extract the foreground objects from the surveillance videos. Then, we use the proposed hierarchical multi-SVMs method for vehicle classification. Moreover, we present a voting based correction scheme by tracking the classified vehicles for the final precision. Based on the proposed approach, we have built a practical system for robust vehicle classification in complicated traffic scenes. Extensive experimental results show that our solution can achieve convincing results.

Large-scale surveillance system: detection and tracking of suspicious motion patterns in crowded traffic scenes

The worldwide increasing sentiment of insecurity gave birth to a new era, shaking thereby the intelligent video-surveillance systems design and deployment. The large-scale use of these means has prompted the creation of new needs in terms of analysis and interpretation. For this purpose, behavior recognition and scene understanding related applications have become more captivating to a significant number of computer vision researchers, particularly when crowded scenes are concerned. So far, motion analysis and tracking remain challenging due to significant visual ambiguities, which encourage looking into further keys.By this work, we present a new framework to recognize various motion patterns, extract abnormal behaviors and track them over a multi-camera traffic surveillance system. We apply a density-based technique to cluster motion vectors produced by optical flow, and compare them with motion pattern models defined earlier. Non-identified clusters are treated as suspicious and simultaneously tracked over an overlapping camera network for as long as possible. To aiming the network configuration, we designed an active camera scheduling strategy where camera assignment was realized via an improved Weighted Round-Robin algorithm.To validate our approach, experiment results are presented and discussed.

Automated classification based on video data at intersections with heavy pedestrian and bicycle traffic: Methodology and application

Pedestrians and cyclists are amongst the most vulnerable road users. Pedestrian and cyclist collisions involving motor-vehicles result in high injury and fatality rates for these two modes. Data for pedestrian and cyclist activity at intersections such as volumes, speeds, and space–time trajectories are essential in the field of transportation in general, and road safety in particular. However, automated data collection for these two road user types remains a challenge. Due to the constant change of orientation and appearance of pedestrians and cyclists, detecting and tracking them using video sensors is a difficult task. This is perhaps one of the main reasons why automated data collection methods are more advanced for motorized traffic. This paper presents a method based on Histogram of Oriented Gradients to extract features of an image box containing the tracked object and Support Vector Machine to classify moving objects in crowded traffic scenes. Moving objects are classified into three categories: pedestrians, cyclists, and motor vehicles. The proposed methodology is composed of three steps: (i) detecting and tracking each moving object in video data, (ii) classifying each object according to its appearance in each frame, and (iii) computing the probability of belonging to each class based on both object appearance and speed. For the last step, Bayes’ rule is used to fuse appearance and speed in order to predict the object class. Using video datasets collected in different intersections, the methodology was built and tested. The developed methodology achieved an overall classification accuracy of greater than 88%. However, the classification accuracy varies across modes and is highest for vehicles and lower for pedestrians and cyclists. The applicability of the proposed methodology is illustrated using a simple case study to analyze cyclist–vehicle conflicts at intersections with and without bicycle facilities.

Using a Light DBSCAN Algorithm for Visual Surveillance of Crowded Traffic Scenes

ABSTRACTBehaviour analysis in visual surveillance has become a very active issue for the computer vision research community, particularly when crowded scenes are concerned. In this perspective, motion analysis and tracking is challenging due to significant visual ambiguities which incite to look into more alternative solutions. In this work, we introduce a new framework for recognizing various motion patterns, extracting abnormal behaviours, and tracking them over crowded traffic scenes. The proposed approach exploits a novel density-based clustering method and highlights three traffic density levels. It performs in two modes: an “offline” mode for motion patterns learning and modelling, and an “online” mode for distinguishing irregular motions and tracking them separately. We developed a light density-based clustering technique to “online” cluster motion vectors, produced by optical flow, and compare them with motion pattern models previously defined. Non-identified clusters are treated as suspicious and tracked over the scene. To evaluate and validate our work, experiment results are discussed and compared with the most recent approaches.

Rapid scene perception with tragic consequences: observers miss perceiving vulnerable road users, especially in crowded traffic scenes.

How does scene complexity influence the detection of expected and appropriate objects within the scene? Traffic research has indicated that vulnerable road users (VRUs: pedestrians, bicyclists, and motorcyclists) are sometimes not perceived, despite being expected. Models of scene perception emphasize competition for limited neural resources in early perception, predicting that an object can be missed during quick glances because other objects win the competition to be individuated and consciously perceived. We used pictures of traffic scenes and manipulated complexity by inserting or removing vehicles near a to-be-detected VRU (crowding). The observers' sole task was to detect a VRU in the laterally presented pictures. Strong bias effects occurred, especially when the VRU was crowded by other nearby vehicles: Observers failed to detect the VRU (high miss rates), while making relatively few false alarm errors. Miss rates were as high as 65% for pedestrians. The results indicated that scene context can interfere with the perception of expected objects when scene complexity is high. Because urbanization has greatly increased scene complexity, these results have important implications for public safety.