Non-Anchor-Based Vehicle Detection for Traffic Surveillance Using Bounding Ellipses

Abstract

Cameras for traffic surveillance are usually pole-mounted and produce images that reflect a birds-eye view. Vehicles in such images, in general, assume an ellipse form. A bounding box for the vehicles usually includes a large empty space when the vehicle orientation is not parallel to the edges of the box. To circumvent this problem, the present study applied bounding ellipses to a non-anchor-based, single-shot detection model (CenterNet). Since this model does not depend on anchor boxes, non-max suppression (NMS) that requires computing the intersection over union (IOU) between predicted bounding boxes is unnecessary for inference. The SpotNet that extends the CenterNet model by adding a segmentation head was also tested with bounding ellipses. Two other anchor-based, single-shot detection models (YOLO4 and SSD) were chosen as references for comparison. The model performance was compared based on a local dataset that was doubly annotated with bounding boxes and ellipses. As a result, the performance of the two models with bounding ellipses exceeded that of the reference models with bounding boxes. When the backbone of the ellipse models was pretrained on an open dataset (UA-DETRAC), the performance was further enhanced. Several data augmentation schemes also improved the performance of the proposed models. As a result, the best mAP score of a CenterNet exceeds 0.95 when augmenting heatmaps with bounding ellipses.

Object Detection in Traffic Videos: A Survey

“…However, its specifically divergent approach and different backbone architectures make it not compatible with the other popular object detectors. Therefore, it has not been used for traffic surveillance and other vision applications as commonly [148], [149]. Figure . 13 presents an overview of the CenterNet architecture.…”

Deep Learning for Clothing Style Recognition Using YOLOv5

“…In YOLOv3~YOLOv5, a certain feature fusion is added that can integrate related information extracted from a group of images without losing data. The feature extraction and fusion methods of YOLOv3~ YOLOv5 are shown in Figure 5 b [ 53 , 54 , 55 ]. The function of FOCUS is mainly to increase the speed, where the image will be sliced and rearranged.…”