Density Map Guided Object Detection in Aerial Images

Changlin Li, Taojiannan Yang, Sijie Zhu, Chen Chen, Shanyue Guan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 190-191

Object detection in high-resolution aerial images is a challenging problem because of 1) the large variation in object size, and 2) non-uniform distribution of objects. A common solution is to divide the large aerial image into small (uniform) chips and then apply object detection on each small crop. In this paper, we investigate the effective image cropping strategy to address these challenges. Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that density map presents how objects distribute in terms of pixel intensity. As pixel intensity varies, it is able to tell whether a region has objects or not, which in turn provide guidance to crop image statistically. DMNet has three key components: a density map generation module, an image cropping module and an object detector. DMNet generates density map and learns scale of categories by utilizing pixel intensity as the guidance to form an implicit boundary as tentative cropping region, which is affected by objects in the region. Compared with ClusDet [??], DMNet puts more emphasis on spatial relation between objects. Extensive experiments show that the proposed method achieves state-of-the-art performance on two popular aerial image datasets, i.e. VisionDrone [??] and UAVDT [??].