TP-LSD: Tri-Points Based Line Segment Detector
This addresses the problem of efficient line detection for computer vision applications, offering a faster and more compact model compared to previous two-step methods.
The paper tackles line segment detection in images by proposing TP-LSD, a deep convolutional model that uses a tri-points representation for one-step detection, achieving competitive accuracy and real-time speed up to 78 FPS on Wireframe and YorkUrban datasets.
This paper proposes a novel deep convolutional model, Tri-Points Based Line Segment Detector (TP-LSD), to detect line segments in an image at real-time speed. The previous related methods typically use the two-step strategy, relying on either heuristic post-process or extra classifier. To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment. TP-LSD has two branches: tri-points extraction branch and line segmentation branch. The former predicts the heat map of root-points and the two displacement maps of endpoints. The latter segments the pixels on straight lines out from background. Moreover, the line segmentation map is reused in the first branch as structural prior. We propose an additional novel evaluation metric and evaluate our method on Wireframe and YorkUrban datasets, demonstrating not only the competitive accuracy compared to the most recent methods, but also the real-time run speed up to 78 FPS with the $320\times 320$ input.