Densely-Populated Traffic Detection using YOLOv5 and Non-Maximum Suppression Ensembling

TL;DR

This paper introduces a novel ensemble of YOLOv5 models to improve vehicle detection in densely crowded urban traffic images, achieving high accuracy and real-time inference suitable for traffic management.

Contribution

The paper presents a new ensembling approach of four YOLOv5 models to enhance detection of small, crowded vehicles in real-time urban traffic scenarios.

Findings

Achieved mAP@0.5 of 0.458 on Dhaka AI dataset.

Inference time of 0.75 seconds per image.

Outperformed existing state-of-the-art models in dense traffic detection.

Abstract

Vehicular object detection is the heart of any intelligent traffic system. It is essential for urban traffic management. R-CNN, Fast R-CNN, Faster R-CNN and YOLO were some of the earlier state-of-the-art models. Region based CNN methods have the problem of higher inference time which makes it unrealistic to use the model in real-time. YOLO on the other hand struggles to detect small objects that appear in groups. In this paper, we propose a method that can locate and classify vehicular objects from a given densely crowded image using YOLOv5. The shortcoming of YOLO was solved my ensembling 4 different models. Our proposed model performs well on images taken from both top view and side view of the street in both day and night. The performance of our proposed model was measured on Dhaka AI dataset which contains densely crowded vehicular images. Our experiment shows that our model achieved mAP@0.5 of 0.458 with inference time of 0.75 sec which outperforms other state-of-the-art models on performance. Hence, the model can be implemented in the street for real-time traffic detection which can be used for traffic control and data collection.