Johnson Deepika Roselind, Vaidhyanathan Rhymend Uthariaraj
School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, Tamilnadu, India.
Ramanujan Computing Centre, Anna University, Chennai, Tamilnadu, India.
Math Biosci Eng. 2023 Jul 19;20(8):15219-15243. doi: 10.3934/mbe.2023681.
Object detection is a fundamental aspect of computer vision, with numerous generic object detectors proposed by various researchers. The proposed work presents a novel single-stage rotation detector that can detect oriented and multi-scale objects accurately from diverse scenarios. This detector addresses the challenges faced by current rotation detectors, such as the detection of arbitrary orientations, objects that are densely arranged, and the issue of loss discontinuity. First, the detector also adopts a progressive regression form (coarse-to-fine-grained approach) that uses both horizontal anchors (speed and higher recall) and rotating anchors (oriented objects) in cluttered backgrounds. Second, the proposed detector includes a feature refinement module that helps minimize the problems related to feature angulation and reduces the number of bounding boxes generated. Finally, to address the issue of loss discontinuity, the proposed detector utilizes a newly formulated adjustable loss function that can be extended to both single-stage and two-stage detectors. The proposed detector shows outstanding performance on benchmark datasets and significantly outperforms other state-of-the-art methods in terms of speed and accuracy.
目标检测是计算机视觉的一个基本方面，众多研究人员提出了许多通用目标检测器。本文提出的工作展示了一种新颖的单阶段旋转检测器，它能够从各种场景中准确检测有方向和多尺度的目标。该检测器解决了当前旋转检测器面临的挑战，如任意方向的检测、密集排列的目标以及损失不连续性问题。首先，该检测器还采用了渐进回归形式（从粗粒度到细粒度的方法），在杂乱背景中同时使用水平锚框（速度快且召回率高）和旋转锚框（有方向的目标）。其次，所提出的检测器包括一个特征细化模块，有助于最小化与特征角度相关的问题，并减少生成的边界框数量。最后，为了解决损失不连续性问题，所提出的检测器使用了一种新制定的可调损失函数，该函数可扩展到单阶段和两阶段检测器。所提出的检测器在基准数据集上表现出色，在速度和准确性方面显著优于其他现有最先进方法。
