Structurally re-parameterized rotation detector for arbitrary-oriented objects in high-resolution remote sensing images. Issue 1 (2nd January 2022)

• Record Type: Journal Article
• Authors: Tian, Jimiao; Zhang, Jing; Li, Wensheng; Li, Jiafeng; Zhuo, Li
• Is Part Of: International journal of remote sensing. Volume 43:Issue 1(2022)
• Page Start: 241
• Page End: 269
• Publication Date: 2022-01-02
• Subjects: Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2021.2012294
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: Horizontal bounding boxes are inflexible for precisely locating geospatial objects with arbitrary orientations in high-resolution remote sensing images. Recently, rotation detectors with oriented bounding boxes have been found to have a positive effect on the detection of arbitrary-oriented objects. However, this method usually suffers from the requirement of a heavy network structure to learn orientation information. Therefore, a structurally re-parameterized rotation detector (SRep-RDet) for arbitrary-oriented objects in high-resolution remote sensing images is proposed. (1) A structurally re-parameterized backbone network, RepVGG-B1g2, is introduced to the detector based on RetinaNet to decouple the training-time multi-branch and inference-time single-path architecture. (2) The multiscale features of RepVGG-B1g2 are refined by using a lightweight channel attention structure. (3) The multiscale features are fused by structurally re-parameterizing a portion of the convolution layers in the feature pyramid network (FPN). (4) Arbitrary-oriented objects are detected by using a rotation detector with oriented bounding boxes. The experimental results on DOTA and HRSC2016 datasets achieve competitive performance.