Towards Light-weight and Real-time Line Segment Detection
This enables real-time line segment detection on mobile devices, addressing a bottleneck for applications in computationally restricted environments, though it is incremental as it builds on existing methods with efficiency improvements.
The paper tackles the problem of deep learning-based line segment detection being too large and slow for real-time use on resource-constrained devices by proposing Mobile LSD (M-LSD), which achieves competitive performance with 2.5% of the model size and a 130.5% increase in inference speed compared to the previous best real-time method, running at up to 56.8 FPS on mobile devices.
Previous deep learning-based line segment detection (LSD) suffers 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 found in previous methods. To maintain competitive performance with a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation, matching and geometric loss. SoL augmentation splits a line segment into multiple subparts, which are used to provide auxiliary line data during the training process. Moreover, the matching and geometric loss allow a model to capture additional geometric cues. 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. Furthermore, our model runs at 56.8 FPS and 48.6 FPS on the latest Android and iPhone mobile devices, respectively. To the best of our knowledge, this is the first real-time deep LSD available on mobile devices. Our code is available.