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

TL;DR

SCRDet++ introduces instance-level feature denoising and rotation loss smoothing to improve detection of small, cluttered, and rotated objects, achieving superior results on diverse datasets.

Contribution

It proposes novel denoising and rotation loss techniques specifically designed for small, cluttered, and rotated object detection, with extensive experimental validation.

Findings

Enhanced detection accuracy on multiple datasets.

Effective handling of rotation variations with new loss function.

Public release of a traffic light detection dataset.

Abstract

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$^2$TLD by this paper. The results show the effectiveness of our approach. The released dataset S2TLD is made public available, which contains 5,786 images with 14,130 traffic light instances across five categories.