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

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 2384 - 2399
• Main Authors: Yang, Xue, Yan, Junchi, Liao, Wenlong, Yang, Xiaokang, Tang, Jin, He, Tao
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aerial images; boundary problem; Datasets; Detectors; feature denoising; Feature extraction; Feature maps; Interference; Noise measurement; Noise reduction; Object detection; Object recognition; Periodic variations; Rotation; rotation detection; Task analysis; Traffic signals
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2022.3166956

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> <mml:math><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="yan-ieq1-3166956.gif"/> </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> <mml:math><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="yan-ieq2-3166956.gif"/> </inline-formula> TLD is made public available, which contains 5,786 images with 14,130 traffic light instances across five categories.