Improved YOLOX for pedestrian detection in crowded scenes

In recent years, object detection in computer vision has developed rapidly. However, crowded pedestrian detection in object detection remains a challenging problem, especially in one-stage detectors where improved solutions are rare. In this paper, we propose a novel crowded pedestrian detection method called YOLO-CPD which works better than other one-stage models in crowded environments. Our method primarily enhances the ability of the one-stage detector to detect multiple overlapping objects in a single area. The core of our approach is to use boxes difference to adjust the IoU value of the Non-Maximum Suppression (NMS) and to improve the Intersection over Union regression loss (IoU Loss), with an Optimised Score Module (OPSC). Compared to the baseline, YOLO-CPD can improve the Average Precision (AP) by a 5.04% increase, Recall by a 2.17% increase and the log-average Miss Rate (MR-2) by a 5.12% reduction on the CrowdHuman dataset. In addition, YOLO-CPD also achieved good results in the WiderPerson dataset, demonstrating the strong generalisation capability of our proposed method.

Automated summary

In recent years, significant progress has been made in object detection in computer vision. However, crowded pedestrian detection in one-stage detectors remains challenging, with few improved solutions available. This paper introduces YOLO-CPD, a novel method for crowded pedestrian detection that outperforms other one-stage models in crowded environments. YOLO-CPD enhances the one-stage detector's ability to detect multiple overlapping objects in a single area through an optimized score module and adjustment of the IoU value in non-maximum suppression. Experimental results demonstrate the superior performance of YOLO-CPD on the CrowdHuman and WiderPerson datasets.