Line as object: datasets and framework for semantic line segment detection
share
In this work, we propose a learning-based approach to the task of detecting semantic line segments from outdoor scenes. Semantic line segments are salient edges enclosed by two endpoints on an image with apparent semantic information, e.g., the boundary between a building roof and the sky (See Fig. 1). Semantic line segments can be efficiently parameterized and fill the gap between dense feature points and sparse objects to act as an effective landmarks in applications such as large-scale High Definition Mapping (HDM). With no existing benchmarks, we have built two new datasets carefully labeled by humans that contain over 6,000 images of semantic line segments. Semantic line segments have different appearance and layout patterns that are challenging for existing object detectors. We have proposed a Semantic Line Segment Detector (SLSD) together with an unified representation and a modified evaluation metric to better detect semantic line segments. SLSD trained on our proposed datasets is shown to perform effectively and efficiently. We have conducted excessive experiments to demonstrate semantic line segment detection task as a valid and challenging research topic.
READ FULL TEXT