LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection

IEEE ACCESS(2022)

引用 5|浏览12
暂无评分
摘要
As of today, the best accuracy in line segment detection (LSD) is achieved by algorithms based on convolutional neural networks - CNNs. Unfortunately, these methods utilize deep, heavy networks and are slower than traditional model-based detectors. In this paper we build an accurate yet fast CNN-based detector, LSDNet, by incorporating a lightweight CNN into a classical LSD detector. Specifically, we replace the first step of the original LSD algorithm - construction of line segments heatmap and tangent field from raw image gradients - with a lightweight CNN, which is able to calculate more complex and rich features. The second part of the LSD algorithm is used with only minor modifications. Compared with several modern line segment detectors on standard Wireframe dataset, the proposed LSDNet provides the highest speed (among CNN-based detectors) of 214 FPS with a competitive accuracy of 78 F-H. Although the best-reported accuracy is 83 F-H at 33 FPS, we speculate that the observed accuracy gap is caused by errors in annotations and the actual gap is significantly lower. We point out systematic inconsistencies in the annotations of popular line detection benchmarks - Wireframe and York Urban, carefully reannotate a subset of images and show that (i) existing detectors have improved quality on updated annotations without retraining, suggesting that new annotations correlate better with the notion of correct line segment detection; (ii) the gap between accuracies of our detector and others diminishes to negligible 0.2 F-H, with our method being the fastest.
更多
查看译文
关键词
Convolutional neural networks, edge detection, line segment detection, U-net, LSD
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要