LSD: A Fast Line Segment Detector with a False Detection Control

By Rafael Grompone von Gioi, Jérémie Jakubowicz, Jean-Michel Morel, G. Randall. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

1,965 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/89a4618d9af12b98af656f9d620256e7cfcd4a1c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Luc Van Gool
4. Ming-Hsuan Yang
5. Dacheng Tao
6. Ming-Ming Cheng
7. Jiayi Ma
8. Xiwen Yao

In Media Technology

1. Junwei Han
2. Gong Cheng
3. Xiwen Yao
4. Lei Guo
5. Jiayi Ma
6. Shuhui Bu
7. Xiaojie Guo
8. Zhenfeng Shao

Citations in the corpus

• Scene Parsing by Integrating Function, Geometry and Appearance Models (2013, methodology): “In order to fill this gap, we make use of the discriminative approaches: a line segment detector [20], a foreground detector [12] and a surface orientation detector [17] to produce a line map Al(I), a foreground map Af(I) and a surface orientation map Ao(I) respectively.”
• EDLines: A real-time line segment detector with a false detection control (2011, methodology): “These small segments are then eliminated during the validation step, and therefore, only a few detections are made (Grompone von Gioi et al., 2010).”
• CubeSLAM: Monocular 3-D Object SLAM (2018, background): “Therefore, we also detect long line segments [36] (shown as the green lines in Fig.”
• Superpixels and Polygons Using Simple Non-iterative Clustering (2017, methodology): “The authors of CON- POLY detect preliminary line segments using Line Segment Detector [34].”
• A coarse-to-fine model for airport detection from remote sensing images using target-oriented visual saliency and CRF (2015, methodology): “(3) Validate each line segment based on the Helmholtz principle [31], according to which the observed geometric structure of line-support region should be perceptually meaningful.”
• PL-SVO: Semi-direct Monocular Visual Odometry by combining points and line segments (2016, methodology): “The cost function when employing both type of features is: where r p stands for the projection errors in the case of point features, and r l is the projection error of line segments: This is solved iteratively with Gauss-Newton, for which we need to include (6) in a robustified framework, for which…”
• PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features (2018, methodology): “As to the line features, line segments in new frame are detected by the LSD detector [39] and matched with those in the previous frame by the appearance-based descriptor LBD [40].”
• A review of multimodal image matching: Methods and applications (2021, background): “Another strategy in [424] involves performing optical and SAR image registration based on iterative line extraction inspired by [425], followed by line intersection matching under a coarse-to-fine registration scheme.”
• PL-SLAM: A Stereo SLAM System Through the Combination of Points and Line Segments (2017, methodology): “Finally, by the time of the first submission of this paper, a work with the same name (PL-SLAM, [36]) was published extending the monocular algorithm ORB-SLAM to the case of including line segment features computed through the line segment detector (LSD) detector [37].”