Perceiving Traffic from Aerial Images

TL;DR

This paper introduces Butterfly Detector, a novel object detection method tailored for aerial images from UAVs, addressing scale variation and occlusion issues, and demonstrating superior real-time performance on UAV datasets.

Contribution

The paper proposes Butterfly Detector, a new detection approach using butterfly fields and voting mechanisms to improve accuracy in aerial imagery.

Findings

Outperforms previous state-of-the-art methods on UAV datasets

Maintains real-time processing capabilities

Effectively handles scale variation and occlusion in aerial images

Abstract

Drones or UAVs, equipped with different sensors, have been deployed in many places especially for urban traffic monitoring or last-mile delivery. It provides the ability to control the different aspects of traffic given real-time obeservations, an important pillar for the future of transportation and smart cities. With the increasing use of such machines, many previous state-of-the-art object detectors, who have achieved high performance on front facing cameras, are being used on UAV datasets. When applied to high-resolution aerial images captured from such datasets, they fail to generalize to the wide range of objects' scales. In order to address this limitation, we propose an object detection method called Butterfly Detector that is tailored to detect objects in aerial images. We extend the concept of fields and introduce butterfly fields, a type of composite field that describes the spatial information of output features as well as the scale of the detected object. To overcome occlusion and viewing angle variations that can hinder the localization process, we employ a voting mechanism between related butterfly vectors pointing to the object center. We evaluate our Butterfly Detector on two publicly available UAV datasets (UAVDT and VisDrone2019) and show that it outperforms previous state-of-the-art methods while remaining real-time.