论文标题
ULSD：跨针孔，鱼眼和球形摄像头的统一线段检测
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
论文作者
论文摘要
线段检测对于计算机视觉和机器人技术中的高级任务至关重要。当前，大多数状态（SOTA）方法专门用于检测未置换的针孔图像中的直线段，因此鱼眼或球形图像上的畸变可能在很大程度上退化其性能。针对统一线段检测（ULSD）的扭曲图像和未发生的图像，我们建议用Bezier曲线模型表示线段。然后，线段检测通过端到端网络的Bezier曲线回归解决，该网络是无模型的，而没有任何不可变化的预处理。针孔，鱼眼和球形图像数据集的实验结果验证了拟议的ULSD对SOTA方法的优越性，均以精确性和效率（针孔图像40.6fps）。源代码可在https://github.com/lh9171338/unified-linesegrest-detection上获得。
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.
