CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images
This work addresses object detection in distorted fisheye images, which is incremental as it builds on existing multi-point representation approaches.
The paper tackles the problem of object detection in fisheye images, where rectangular bounding boxes introduce background noise, by proposing the Concentric Rectangles Regression Strategy (CRRS) to improve multi-point representation, resulting in enhanced training accuracy and stability compared to prior methods.
Modern object detectors take advantage of rectangular bounding boxes as a conventional way to represent objects. When it comes to fisheye images, rectangular boxes involve more background noise rather than semantic information. Although multi-point representation has been proposed, both the regression accuracy and convergence still perform inferior to the widely used rectangular boxes. In order to further exploit the advantages of multi-point representation for distorted images, Concentric Rectangles Regression Strategy(CRRS) is proposed in this work. We adopt smoother mean loss to allocate weights and discuss the effect of hyper-parameter to prediction results. Moreover, an accurate pixel-level method is designed to obtain irregular IoU for estimating detector performance. Compared with the previous work for muti-point representation, the experiments show that CRRS can improve the training performance both in accurate and stability. We also prove that multi-task weighting strategy facilitates regression process in this design.