ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

11/06/2020 ∙ by Hao Li, et al. ∙ 2 ∙ share

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, thus distortions on fisheye or spherical images may largely degenerate their performance. Targeting at the unified line segment detection (ULSD) for both distorted and undistorted images, we propose to represent line segments with the Bezier curve model. Then the line segment detection is tackled by the Bezier curve regression with an end-to-end network, which is model-free and without any undistortion preprocessing. Experimental results on the pinhole, fisheye, and spherical image datasets validate the superiority of the proposed ULSD to the SOTA methods both in accuracy and efficiency (40.6fps for pinhole images). The source code is available at https://github.com/lh9171338/Unified-LineSegment-Detection.

READ FULL TEXT

PPGNet: Learning Point-Pair Graph for Line Segment Detection

In this paper, we present a novel framework to detect line segments in m...
05/09/2019 ∙ by Ziheng Zhang, et al. ∙ 0 ∙ share

read it
TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images

Line segment detection is an essential task in computer vision and image...
02/27/2020 ∙ by Ming Gong, et al. ∙ 4 ∙ share

read it
Learning to Parse Wireframes in Images of Man-Made Environments

In this paper, we propose a learning-based approach to the task of autom...
07/15/2020 ∙ by Kun Huang, et al. ∙ 14 ∙ share

read it
From line segments to more organized Gestalts

In this paper, we reconsider the early computer vision bottom-up program...
03/18/2016 ∙ by Boshra Rajaei, et al. ∙ 0 ∙ share

read it
Line detection via a lightweight CNN with a Hough Layer

Line detection is an important computer vision task traditionally solved...
08/20/2020 ∙ by Lev Teplyakov, et al. ∙ 6 ∙ share

read it
DeepSphere: a graph-based spherical CNN

Designing a convolution for a spherical neural network requires a delica...
12/30/2020 ∙ by Michaël Defferrard, et al. ∙ 0 ∙ share

read it
Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

Many computer vision challenges require continuous outputs, but tend to ...
04/10/2019 ∙ by Shuai Liao, et al. ∙ 26 ∙ share

read it

ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

Authors

PPGNet: Learning Point-Pair Graph for Line Segment Detection

TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images

Learning to Parse Wireframes in Images of Man-Made Environments

From line segments to more organized Gestalts

Line detection via a lightweight CNN with a Hough Layer

DeepSphere: a graph-based spherical CNN

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

Code Repositories

Unified-Line-Segment-Detection

ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

Authors

PPGNet: Learning Point-Pair Graph for Line Segment Detection

TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images

Learning to Parse Wireframes in Images of Man-Made Environments

From line segments to more organized Gestalts

Line detection via a lightweight CNN with a Hough Layer

DeepSphere: a graph-based spherical CNN

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

Code Repositories

Unified-Line-Segment-Detection

This week in AI