Object Detection Using Clustering Algorithm Adaptive Searching Regions in Aerial Images

Abstract

Aerial images are increasingly used for critical tasks, such as traffic monitoring, pedestrian tracking, and infrastructure inspection. However, aerial images have the following main challenges: 1) small objects with non-uniform distribution; 2) the large difference in object size. In this paper, we propose a new network architecture, Cluster Region Estimation Network (CRENet), to solve these challenges. CRENet uses a clustering algorithm to search cluster regions containing dense objects, which makes the detector focus on these regions to reduce background interference and improve detection efficiency. However, not every cluster region can bring precision gain, so each cluster region difficulty score is calculated to mine the difficult region and eliminate the simple cluster region, which can speed up the detection. Then, a Gaussian scaling function(GSF) is used to scale the difficult cluster region to reduce the difference of object size. Our experiments show that CRENet achieves better performance than previous approaches on the VisDrone dataset. Our best model achieved 4.3 $\%$ % improvement on the VisDrone dataset.