3D Vehicle Trajectory Extraction Using DCNN in an Overlapping Multi-Camera Crossroad Scene

Abstract

The 3D vehicle trajectory in complex traffic conditions such as crossroads and heavy traffic is practically very useful in autonomous driving. In order to accurately extract the 3D vehicle trajectory from a perspective camera in a crossroad where the vehicle has an angular range of 360 degrees, problems such as the narrow visual angle in single-camera scene, vehicle occlusion under conditions of low camera perspective, and lack of vehicle physical information must be solved. In this paper, we propose a method for estimating the 3D bounding boxes of vehicles and extracting trajectories using a deep convolutional neural network (DCNN) in an overlapping multi-camera crossroad scene. First, traffic data were collected using overlapping multi-cameras to obtain a wide range of trajectories around the crossroad. Then, 3D bounding boxes of vehicles were estimated and tracked in each single-camera scene through DCNN models (YOLOv4, multi-branch CNN) combined with camera calibration. Using the abovementioned information, the 3D vehicle trajectory could be extracted on the ground plane of the crossroad by calculating results obtained from the overlapping multi-camera with a homography matrix. Finally, in experiments, the errors of extracted trajectories were corrected through a simple linear interpolation and regression, and the accuracy of the proposed method was verified by calculating the difference with ground-truth data. Compared with other previously reported methods, our approach is shown to be more accurate and more practical.

Multi-camera Vehicle Tracking and Recognition with Multimodal Contrastive Domain Sharing GAN and Topological Embeddings

“…A multi-camera system comprises strategically positioned cameras aimed at capturing and monitoring specific areas or scenes from various angles [1]. This setup is widely utilized to enhance surveillance, analysis, and perception across diverse applications such as security, traffic monitoring, sports analysis, and computer vision research [2]. By providing multiple viewpoints, multi-camera systems offer comprehensive scene coverage, eliminating blind spots and enabling tasks like object tracking and scene reconstruction [3].…”

“…distribution of noise samples, ) (Z G denotes the output of generator when given noise ) (Z . Then to find the domain discrepancy loss using maximum mean discrepancy it is expressed in equation(2).…”