Tiny Object Detection in Aerial Images

• Published in: 2020 25th International Conference on Pattern Recognition (ICPR) pp. 3791 - 3798
• Main Authors: Wang, Jinwang, Yang, Wen, Guo, Haowen, Zhang, Ruixiang, Xia, Gui-Song
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.01.2021
• Subjects: aerial image; benchmark; Benchmark testing; convolutional neural network; Detectors; Earth; Location awareness; Neural networks; Object detection; Performance gain; tiny object detection
• DOI: 10.1109/ICPR48806.2021.9413340

Object detection in Earth Vision has achieved great progress in recent years. However, tiny object detection in aerial images remains a very challenging problem since the tiny objects contain a small number of pixels and are easily confused with the background. To advance tiny object detection research in aerial images, we present a new dataset for Tiny Object Detection in Aerial Images (AI-TOD). Specifically, AI-TOD comes with 700,621 object instances for eight categories across 28,036 aerial images. Compared to existing object detection datasets in aerial images, the mean size of objects in AI-TOD is about 12.8 pixels, which is much smaller than others. To build a benchmark for tiny object detection in aerial images, we evaluate the state-of-the-art object detectors on our AI-TOD dataset. Experimental results show that direct application of these approaches on AI-TOD produces suboptimal object detection results, thus new specialized detectors for tiny object detection need to be designed. Therefore, we propose a multiple center points based learning network (M-CenterNet) to improve the localization performance of tiny object detection, and experimental results show the significant performance gain over the competitors.