Author:
Wang Jinghao,Teng Xichao,Li Zhang,Yu Qifeng,Bian Yijie,Wei Jiaqi
Abstract
Arbitrary-oriented vehicle detection via aerial imagery is essential in remote sensing and computer vision, with various applications in traffic management, disaster monitoring, smart cities, etc. In the last decade, we have seen notable progress in object detection in natural imagery; however, such development has been sluggish for airborne imagery, not only due to large-scale variations and various spins/appearances of instances but also due to the scarcity of the high-quality aerial datasets, which could reflect the complexities and challenges of real-world scenarios. To address this and to improve object detection research in remote sensing, we collected high-resolution images using different drone platforms spanning a large geographic area and introduced a multi-view dataset for vehicle detection in complex scenarios using aerial images (VSAI), featuring arbitrary-oriented views in aerial imagery, consisting of different types of complex real-world scenes. The imagery in our dataset was captured with a wide variety of camera angles, flight heights, times, weather conditions, and illuminations. VSAI contained 49,712 vehicle instances annotated with oriented bounding boxes and arbitrary quadrilateral bounding boxes (47,519 small vehicles and 2193 large vehicles); we also annotated the occlusion rate of the objects to further increase the generalization abilities of object detection networks. We conducted experiments to verify several state-of-the-art algorithms in vehicle detection on VSAI to form a baseline. As per our results, the VSAI dataset largely shows the complexity of the real world and poses significant challenges to existing object detection algorithms. The dataset is publicly available.
Funder
National Natural Science Funding of China
Subject
Artificial Intelligence,Computer Science Applications,Aerospace Engineering,Information Systems,Control and Systems Engineering
Reference49 articles.
1. The Pascal Visual Object Classes (VOC) Challenge
2. ImageNet Large Scale Visual Recognition Challenge
3. Microsoft coco: Common objects in context;Lin;Proceedings of the European Conference on Computer Vision,2014
4. Rotation-invariant object detection in remote sensing images based on radial-gradient angle;Lin;IEEE Geosci. Remote Sens. Lett.,2014
5. Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献