Tiny Object Detection in Aerial Images

By Jinwang Wang, Wen Yang, Haowen Guo, Ruixiang Zhang, Guisong Xia. International Conference on Pattern Recognition, 2021

354 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b9db792a456f76517783a965ac3a127c985adcb5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Junwei Han
2. Gong Cheng
3. Chang Xu
4. Ke Yan
5. Hao Zhang
6. Shuaijie Zhang
7. Cong Xu
8. Wen Yang

In Computer Vision and Pattern Recognition

1. Gong Cheng
2. Junwei Han
3. Xiwen Yao
4. Wen Yang
5. Ke Yan
6. Xiang Yuan
7. Qinghua Zeng
8. Chang Xu

Citations in the corpus

• Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box (2023, methodology): “…the generalization ability of the proposed method, we conducted comparative experiments using the YOLOv5s detector on the AI-TOD dataset [21], using SIoU [5] In comparative experiment 1, by setting the ratio value between 0.7 and 0.8 to be less than 1, an auxiliary border smaller than…”
• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “In addition, the images in AI-TOD are cropped from existing datasets and the image resolution is fixed to 800 × 800 .”
• A Normalized Gaussian Wasserstein Distance for Tiny Object Detection (2021, positive): “While tiny objects (less than 16× 16 pixels in the AI-TOD dataset [29]) often exhibit with extremely limited appearance information, which increases difficulty in learning discriminative features, leading to enormous failure cases when detecting tiny objects [25, 29, 35].”