Previous deep learning-based line segment detection (LSD) suffer from the immense model size and high computational cost for line prediction. This constrains them from real-time inference on computationally restricted environments. In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD). We design an extremely efficient LSD architecture by minimizing the backbone network and removing the typical multi-module process for line prediction in previous methods. To maintain competitive performance with such a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation and geometric learning scheme. SoL augmentation splits a line segment into multiple subparts, which are used to provide auxiliary line data during the training process. Moreover, the geometric learning scheme allows a model to capture additional geometry cues from matching loss, junction and line segmentation, length and degree regression. Compared with TP-LSD-Lite, previously the best real-time LSD method, our model (M-LSD-tiny) achieves competitive performance with 2.5% of model size and an increase of 130.5% in inference speed on GPU when evaluated with Wireframe and YorkUrban datasets. Furthermore, our model runs at 56.8 FPS and 48.6 FPS on Android and iPhone mobile devices, respectively. To the best of our knowledge, this is the first real-time deep LSD method available on mobile devices.

翻译：先前的深层次基于学习的线段检测(LSD)受到巨大的模型规模和高计算成本的线段预测(LSD)的影响。这制约了他们从计算限制环境中的实时推断。在本文件中,我们提议为资源受限制的环境(名为M-LSD(M-LSD))建立一个实时和轻量线段检测器。我们设计了一个极高效的LSD架构,办法是尽量减少主干网,并去除以往方法中典型的线段预测多模块程序。为了保持这种轻量网络的竞争性性能,我们提出了新的培训计划:线段(SoL)增强和几何学学习计划。SoL增强将线段分成多个小段,用于在培训过程中提供辅助性线段数据。此外,几何学学习计划允许一种模型从匹配损失、连接和线段分解、长度和程度回归中获取更多的几何线线线线线线。 与TP-LSD-Lite(以前的最佳实时LSD)方法相比,我们的模型(M-LSD-tin-SD-SD)和几何学习计划部分实现最佳竞争性性性性性性性性性工作,在模型中分别以2.5/FPSBSDFSL.5的模型和速度中,在可理解中,在可理解中,在SL-xxxxxxxxxxxxxxxx中,其速度中,在Slxxxx节中,用最佳和速度为2.5-30。