Deep Hough Transform for Semantic Line Detection

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 9; pp. 4793 - 4806
• Main Authors: Zhao, Kai, Han, Qi, Zhang, Chang-Bin, Xu, Jun, Cheng, Ming-Ming
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: CNN; Datasets; deep learning; Detectors; Domains; Feature extraction; Feature maps; hough transform; Hough transformation; Image edge detection; Measurement; Object recognition; Quality assessment; Representations; Semantic line detection; Semantics; Source code; Task analysis; Transforms

We focus on a fundamental task of detecting meaningful line structures, a.k.a. , semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inhe...