SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

By Xue Yang, Junchi Yan, Xiaokang Yang, Jin Tang, Wenlong Liao, Tao He. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

354 citations recorded by the source corpus.

Small and cluttered objects are common in real-world which are challenging for detection. The difficulty is further pronounced when the objects are rotated, as traditional detectors often routinely locate the objects in horizontal bounding box such that the region of interest is contaminated with background or nearby interleaved objects. In this paper, we first innovatively introduce the idea of denoising to object detection. Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects. To handle the rotation variation, we also add a novel IoU constant factor to the smooth L1 loss to address the long standing boundary problem, which to our analysis, is mainly caused by the periodicity of angular (PoA) and exchangeability of edges (EoE). By combing these two features, our proposed detector is termed as SCRDet++. Extensive experiments are performed on large aerial images public datasets DOTA, DIOR, UCAS-AOD as well as natural image dataset COCO, scene text dataset ICDAR2015, small traffic light dataset BSTLD and our released S <inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="yan-ieq1-3166956.gif"/></alternatives></inline-formula> TLD by this paper. The results show the effectiveness of our approach. The released dataset S <inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="yan-ieq2-3166956.gif"/></alternatives></inline-formula> TLD is made public available, which contains 5,786 images with 14,130 traffic light instances across five categories.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e8431bb0bdb628a2b139c4bd2f7c67afb0b5fa9e

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. Wentao Wang
2. Jianke Zhu
3. Wentong Li
4. Junchi Yan
5. Xue Yang
6. Yue Zhou
7. Liping Hou
8. Qi Ming

Citations in the corpus

• MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, neutral): “Depending on the angle range, it can be divided into OpenCV definition ( 𝐷 𝑜𝑐 ,𝜃 ∈ [− 𝜋 / 2 , 0 ) ) [32, 36, 38], long edge 90° definition ( 𝐷 𝑙𝑒 90 ,𝜃 ∈ [− 𝜋 / 2 , 𝜋 / 2 ) ) [3, 6], and long edge 135° ) ) [5]. https://github.com/dingjiansw101/AerialDetection 4…”
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, methodology): “Many rotation detectors (including those for aerial image [46, 15, 47, 2, 6, 51, 45, 30, 48, 49, 50], scene text [56, 23, 14, 26, 19, 18] and face [34, 13, 33]) are derived based on the vanilla detection algorithms [10, 32, 31, 5, 20, 21].”
• Oriented RepPoints for Aerial Object Detection (2021, background): “SCRDet++ [44] enhances the non-axis aligned features and bring the higher object response to train the network.”