Sem-LSD: A Learning-based Semantic Line Segment Detector
This addresses the need for robust, compact scene representations in large-scale applications like SLAM and loop closure detection, but it is incremental as it builds on existing line detection methods with semantic enhancements.
The paper tackles the problem of detecting semantic line segments (Sem-LS), a new line-shaped image representation with high-level semantics, by proposing a learning-based detector (Sem-LSD) and labeling benchmarks on KITTI and KAIST URBAN datasets, showing efficacy and efficiency in experiments including city-scale loop closure detection.
In this paper, we introduces a new type of line-shaped image representation, named semantic line segment (Sem-LS) and focus on solving its detection problem. Sem-LS contains high-level semantics and is a compact scene representation where only visually salient line segments with stable semantics are preserved. Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations. The compactness of Sem-LS facilitates its use in large-scale applications, such as city-scale SLAM (simultaneously localization and mapping) and LCD (loop closure detection). Sem-LS detection is a challenging task due to its significantly different appearance from existing learning-based image representations such as wireframes and objects. For further investigation, we first label Sem-LS on two well-known datasets, KITTI and KAIST URBAN, as new benchmarks. Then, we propose a learning-based Sem-LS detector (Sem-LSD) and devise new module as well as metrics to address unique challenges in Sem-LS detection. Experimental results have shown both the efficacy and efficiency of Sem-LSD. Finally, the effectiveness of the proposed Sem-LS is supported by two experiments on detector repeatability and a city-scale LCD problem. Labeled datasets and code will be released shortly.