Clustered Object Detection in Aerial Images

By Fan Yang, Heng Fan, Peng Chu, Erik Blasch, Haibin Ling. IEEE International Conference on Computer Vision, 2019

413 citations recorded by the source corpus.

Detecting objects in aerial images is challenging for at least two reasons: (1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding background; and (2) targets are in general sparsely and non-uniformly distributed, making the detection very inefficient. In this paper, we address both issues inspired by observing that these targets are often clustered. In particular, we propose a Clustered Detection (ClusDet) network that unifies object clustering and detection in an end-to-end framework. The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet). Given an input image, CPNet produces object cluster regions and ScaleNet estimates object scales for these regions. Then, each scale-normalized cluster region is fed into DetecNet for object detection. ClusDet has several advantages over previous solutions: (1) it greatly reduces the number of chips for final object detection and hence achieves high running time efficiency, (2) the cluster-based scale estimation is more accurate than previously used single-object based ones, hence effectively improves the detection for small objects, and (3) the final DetecNet is dedicated for clustered regions and implicitly models the prior context information so as to boost detection accuracy. The proposed method is tested on three popular aerial image datasets including VisDrone, UAVDT and DOTA. In all experiments, ClusDet achieves promising performance in comparison with state-of-the-art detectors.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8d5497bd3a96e686d884d1788ed48cbeea03c4c2

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Guisong Xia
4. Jianke Zhu
5. Xiwen Yao
6. Xiang Bai
7. Wentong Li
8. Dacheng Tao

Citations in the corpus

• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “In contrast with horizontal object detection [8], [20], [21], [22], oriented object detec-”
• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “6) Focus-and-Detect Methods: Small objects in high-resolution images tend to distribute non-uniformly [139], and the general divide-and-detect scheme consumes too much computation on those empty patches, leading the inefficiency during inference.”
• Align Deep Features for Oriented Object Detection (2020, methodology): “COMPARING S2A-NET WITH CLUSDET [33] ON DOTA VALIDATION SET.”
• Oriented RepPoints for Aerial Object Detection (2021, background): “Different from the generic object detection, aerial target localization has its own difficulties, including non-axis aligned objects with arbitrary orientations [3,9,24] and densely packed distribution with complex context [7, 37, 45].”