Pedestrian multi-object tracking based on YOLOv7 and BoT-SORT

Abstract

As a crucial component in the realm of computer vision, multi-object tracking has garnered widespread application in areas such as autonomous driving, smart transportation, and surveillance technology.Based on YOLOv7 and BoT-SORT algorithms, this paper followed TBD (track by detection) framework. First, YOLOv7 served as the detector tasked with identifying the target and specifying its location within the frame. Then, the BoT-SORT algorithm was used to track the target based on the target detection results. The results are then tested on the MOT20 dataset. The experimental data show that on MOT20 data set, the accuracy of multi-object tracking reaches 69.36%, and the accuracy of multi-object tracking reaches 79.11%, which effectively solves the problems of target occlusion and frequent identity switching. The experiment proves that it still has good tracking effect under dim lighting and crowded complex scenes. It can achieve better tracking for the non-rigid target of pedestrians, and has higher accuracy than YOLOv7-DeepSORT and YOLOv7-ByteTrack.

AI-based, automated longitudinal performance monitoring of multiple boxers in large scale videos

“…To assess the performance of proposed tracker, we implemented the stateof-the-art [20][21][22][23] detection and tracking modules on the segmented bout videos. This experiment will help show the robustness of the proposed approach for tracking persons with dynamic movements from an overhead camera angle.…”

“…Notably, this JDE model exhibited the highest Frames Per Second (FPS) rate, surpassing 30, in comparison to other techniques. Another state-of-the-art technique employs a single-stage object detection model, YOLOv7, as its foundational detection model, combined with the Simple Online Real-Time Tracking (SORT) method for tracking [22]. In contrast to Mask RCNN [1] and JDE [2], YOLOv7 exhibits a higher number of detections per frame when applied to overhead views.…”