Vision-Based Anti-UAV Detection and Tracking

Unmanned aerial vehicles (UAV) have been widely used in various fields, and their invasion of security and privacy has aroused social concern. Several detection and tracking systems for UAVs have been introduced in recent years, but most of them are based on radio frequency, radar, and other media. We assume that the field of computer vision is mature enough to detect and track invading UAVs. Thus we propose a visible light mode dataset called Dalian University of Technology Anti-UAV dataset, DUT Anti-UAV for short. It contains a detection dataset with a total of 10,000 images and a tracking dataset with 20 videos that include short-term and long-term sequences. All frames and images are manually annotated precisely. We use this dataset to train several existing detection algorithms and evaluate the algorithms’ performance. Several tracking methods are also tested on our tracking dataset. Furthermore, we propose a clear and simple tracking algorithm combined with detection that inherits the detector’s high precision. Extensive experiments show that the tracking performance is improved considerably after fusing detection, thus providing a new attempt at UAV tracking using our dataset. The datasets and results are publicly available at: https://github.com/wangdongdut/DUT-Anti-UAV.

I. Introduction

With the maturity of industrial technology, unmanned aerial vehicles (UAV) have gradually become mainstream. They are widely used in logistics [1], transportation [2], monitoring [3], and other fields because of their small size, low price, and simple operation [4]. Although UAVs provide convenience, they cause a series of problems. Either public safety or personal safety and privacy are easily violated. Therefore, the detection and tracking of illegally or unintentionally invading UAVs are crucial. However, no complete and reliable anti-UAV detection and tracking system is available at present. Most of the existing detection and early warning technologies are based on radar [5], radio frequency (RF) [6], and acoustic sensors [7], which often have limitations, such as high cost and susceptibility to noise. These limitations lead to unreliable results. Therefore, these existing algorithms cannot be used extensively. Their application range is limited to airports and other public places.