论文标题
LSDNET：可训练的LSD算法用于实时线段检测
LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection
论文作者
论文摘要
截至今天，基于卷积神经网络-CNN的算法实现了线段检测（LSD）的最佳准确性（LSD）。不幸的是，这些方法利用了深层，重型网络，并且比传统的基于模型的检测器慢。在本文中，我们通过将轻量级CNN纳入经典的LSD检测器中来构建准确但快速的基于CNN的检测器LSDNET。具体来说，我们用轻量级的CNN替换了原始LSD算法的第一步 - 线段段热图和切线场的构造 - 能够计算出更复杂且丰富的特征。 LSD算法的第二部分仅用于次要修改。与标准线框数据集上的几个现代线段探测器相比，所提出的LSDNET提供了214 fps的最高速度（在基于CNN的探测器中），竞争精度为78 FH。尽管最佳报告的精度为33 fps的83 fh，但我们推测观察到的准确性差距是由注释错误引起的，而实际差距明显更低。我们指出了在流行线检测基准的注释中的系统不一致 - 线框和约克城市，仔细地重新注册了一部分图像，并表明（i）现有检测器在不进行重新培训的情况下提高了质量，而无需重新培训，表明新的注释与正确的线条段检测的记录更好； （ii）我们的检测器的精度与其他人之间的差距减少到可忽略的0.2 fh，而我们的方法最快。
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 Fh . Although the best-reported accuracy is 83 Fh 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 Fh , with our method being the fastest.
