The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking

TL;DR

This paper introduces a comprehensive UAV benchmark dataset with diverse, complex scenarios and annotations for object detection and tracking, revealing current methods' limitations in real UAV scenes.

Contribution

The paper presents the first large-scale, unconstrained UAV benchmark dataset with detailed annotations and a thorough evaluation of state-of-the-art algorithms in challenging real-world scenarios.

Findings

State-of-the-art methods perform worse on UAV data due to high density and small objects.

The dataset includes 80,000 annotated frames with 14 attributes.

Challenges like camera motion and occlusion significantly impact detection and tracking performance.

Abstract

With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80,000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively.