ELSD: Efficient Line Segment Detector and Descriptor

• URL: http://arxiv.org/abs/2104.14205v1
• Date: Thu, 29 Apr 2021 08:53:03 GMT
• Title: ELSD: Efficient Line Segment Detector and Descriptor
• Authors: Haotian Zhang, Yicheng Luo, Fangbo Qin, Yijia He, Xiao Liu
• Abstract summary: We present the novel Efficient Line Segment Detector and Descriptor (ELSD) to simultaneously detect line segments and extract their descriptors in an image. ELSD provides the essential line features to the higher-level tasks like SLAM and image matching in real time. In the experiments, the proposed ELSD achieves the state-of-the-art performance on the Wireframe dataset and YorkUrban dataset.
• Score: 9.64386089593887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present the novel Efficient Line Segment Detector and Descriptor (ELSD) to simultaneously detect line segments and extract their descriptors in an image. Unlike the traditional pipelines that conduct detection and description separately, ELSD utilizes a shared feature extractor for both detection and description, to provide the essential line features to the higher-level tasks like SLAM and image matching in real time. First, we design the one-stage compact model, and propose to use the mid-point, angle and length as the minimal representation of line segment, which also guarantees the center-symmetry. The non-centerness suppression is proposed to filter out the fragmented line segments caused by lines' intersections. The fine offset prediction is designed to refine the mid-point localization. Second, the line descriptor branch is integrated with the detector branch, and the two branches are jointly trained in an end-to-end manner. In the experiments, the proposed ELSD achieves the state-of-the-art performance on the Wireframe dataset and YorkUrban dataset, in both accuracy and efficiency. The line description ability of ELSD also outperforms the previous works on the line matching task.

Related papers

• Level-line Guided Edge Drawing for Robust Line Segment Detection [38.21854942764346]
  This paper proposes a level-line guided edge drawing for robust line segment detection (GEDRLSD) The level-line information provides potential directions for edge tracking, which could be served as a guideline for accurate edge drawing. Numerical experiments show the superiority of the proposed GEDRLSD algorithm compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-10T04:03:59Z)
• DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients [105.25109274550607]
  Line segments are increasingly used in vision tasks. Traditional line detectors based on the image gradient are extremely fast and accurate, but lack robustness in noisy images and challenging conditions. We propose to combine traditional and learned approaches to get the best of both worlds: an accurate and robust line detector.
  arXiv  Detail & Related papers  (2022-12-15T12:36:49Z)
• Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning [112.54086514317021]
  This article presents HolisticDally-Attracted Wireframe Parsing 2 method for geometric analysis using line segments and junctions. The proposed HAWP consists of three components empowered by end-to-form 4D labels.
  arXiv  Detail & Related papers  (2022-10-24T06:39:32Z)
• Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion [62.269219152425556]
  segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field. We propose a Differentiable Binarization (DB) module that integrates the binarization process into a segmentation network. An efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
  arXiv  Detail & Related papers  (2022-02-21T15:30:14Z)
• LOF: Structure-Aware Line Tracking based on Optical Flow [8.856222186351445]
  We propose a structure-aware Line tracking algorithm based entirely on Optical Flow (LOF) The proposed LOF outperforms the state-of-the-art performance in line tracking accuracy, robustness, and efficiency.
  arXiv  Detail & Related papers  (2021-09-17T11:09:11Z)
• SOLD2: Self-supervised Occlusion-aware Line Description and Detection [95.8719432775724]
  We introduce the first joint detection and description of line segments in a single deep network. Our method does not require any annotated line labels and can therefore generalize to any dataset. We evaluate our approach against previous line detection and description methods on several multi-view datasets.
  arXiv  Detail & Related papers  (2021-04-07T19:27:17Z)
• Line Segment Detection Using Transformers without Edges [22.834316796018705]
  Our method, named LinE segment TRansformers (LETR), tackles the three main problems in this domain. We show state-of-the-art results on Wireframe and YorkUrban benchmarks.
  arXiv  Detail & Related papers  (2021-01-06T08:00:18Z)
• ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras [17.943949895764938]
  Line segment detection is essential for high-level tasks in computer vision and robotics. Currently, most stateof-the-art (SOTA) methods are dedicated to detecting straight line segments in undistorted pinhole images. We propose to target at the unified line segment detection (ULSD) for both distorted and undistorted images.
  arXiv  Detail & Related papers  (2020-11-06T03:30:17Z)
• Deep Hough Transform for Semantic Line Detection [70.28969017874587]
  We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic lines, in natural scenes. Previous methods neglect the inherent characteristics of lines, leading to sub-optimal performance. We propose a one-shot end-to-end learning framework for line detection.
  arXiv  Detail & Related papers  (2020-03-10T13:08:42Z)
• Holistically-Attracted Wireframe Parsing [123.58263152571952]
  This paper presents a fast and parsimonious parsing method to detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification.
  arXiv  Detail & Related papers  (2020-03-03T17:43:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.