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

TL;DR

This paper introduces ULSD, a unified end-to-end Bezier curve regression method for detecting line segments across pinhole, fisheye, and spherical images without preprocessing, outperforming existing methods in accuracy and speed.

Contribution

The paper presents a novel Bezier curve-based model for unified line segment detection across various camera distortions, eliminating the need for image undistortion preprocessing.

Findings

Outperforms state-of-the-art methods in accuracy.

Achieves real-time detection at 40.6 fps.

Effective across multiple camera types and distortions.

Abstract

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.