Automatic Detection and Classification of Road, Car, and Pedestrian Using Binocular Cameras in Traffic Scenes with a Common Framework

Abstract

In order to solve the problems of traffic object detection, fuzzification, and simplification in real traffic environment, an automatic detection and classification algorithm for roads, vehicles, and pedestrians with multiple traffic objects under the same framework is proposed. We construct the final V view through a considerate U-V view method, which determines the location of the horizon and the initial contour of the road. Road detection results are obtained through error label reclassification, omitting point reassignment, and so an. We propose a peripheral envelope algorithm to determine sources of vehicles and pedestrians on the road. The initial segmentation results are determined by the regional growth of the source point through the minimum neighbor similarity algorithm. Vehicle detection results on the road are confirmed by combining disparity and color energy minimum algorithms with the object window aspect ratio threshold method. A method of multifeature fusion is presented to obtain the pedestrian target area, and the pedestrian detection results on the road are accurately segmented by combining the disparity neighbor similarity and the minimum energy algorithm. The algorithm is tested in three datasets of Enpeda, KITTI, and Daimler; then, the corresponding results prove the efficiency and accuracy of the proposed approach. Meanwhile, the real-time analysis of the algorithm is performed, and the average time efficiency is 13 pfs, which can realize the real-time performance of the detection process.

Real time pedestrian and objects detection using enhanced YOLO integrated with learning complexity-aware cascades

“…YOLOv2 [20], an enhanced version, incorporates anchor boxes, and K-means clustering, enhancing training models. Efficient proposes a compound scaling strategy for elevated object detection performance, while RetinaNet introduces a focal loss function to mitigate class imbalance issues [21].…”

3D-Net: Monocular 3D Object Recognition for Traffic Monitoring

“…Zhang, Xiao, Coifman, and Mills (2020) proposed a centroid-based tracking method and a refining module to track vehicles and improve speed estimations. Song, Yao, Ju, Jiang, and Du (2020) proposed a framework to detect roads, pedestrians, and vehicles using binocular cameras. In another multi-modal research, thermal sensor data is fused with the RGB camera sensor, leading to a noise-resistant technique for traffic monitoring (Alldieck, Bahnsen, & Moeslund, 2016).…”

Efficient Obstacle Detection and Tracking Using RGB-D Sensor Data in Dynamic Environments for Robotic Applications

“…Adrian et al [8] showed multiple representations of the disparity image and uvθ-disparity to achieve obstacle detection. Song et al [9] presented obstacle detection using a considerate uv-disparity that uses a refined v-disparity for accurate road segmentation. These approaches are equally applicable in a system that helps visually impaired persons [10] because of the similarities in the motion characteristics between humans and AGVs.…”