HDDet: A More Common Heading Direction Detector for Remote Sensing and Arbitrary Viewing Angle Images

Object heading detection (OHD) offers potential for research in the control and traffic analysis sectors. Contemporary methodologies in OHD grapple with a set of distinct limitations: a constrained range of detectable object types, a discernible drop in accuracy for oriented bounding box (OBB) predictions influenced by heading estimations, and the inherent limitations associated with the exclusive perspective of bird's-eye view imagery. This article introduces heading direction detector (HDDet), an advanced method devised for detecting the OBB of objects with heading direction from various viewpoints. It sequentially delineates the circular annotation method (CAM), multidimensional angle encoding (MDAE), and the CosWeight strategy. CAM initially couples OBB data with heading details for accurate target delineation. MDAE follows, optimizing angle encoding to boost the model's training process. The culmination of this approach is CosWeight, which integrates the Rotated-intersection over union (IoU) and heading information into the horizontal box's loss, thereby enhancing the precision of heading predictions. Rigorous testing across diverse datasets, including the SJTU-L dataset where the heading accuracy increased from 64.41% to 94.82% over OHDet, validates HDDet's enhanced capabilities, surpassing existing methodologies in both OBB detection and heading accuracy, and marking a significant advancement over the state-of-the-art OHDet. Additionally, this article presents an engineering vehicle dataset, which is conducive to multiperspective OHD research.