PLSD: A Perceptually Accurate Line Segment Detection Approach

Abstract

Most existing line segment detection methods suffer from the over-segmentation phenomenon. An improved line segment detection method is presented in this work, which can generate more and longer line segments, yet still accurately reflect the structural details of the image. Line segment grouping, line segment validation and a multiscale framework are adopted to reach this end. Specifically, smart grouping rules are introduced to locate potential homologous line segments (derived from the same boundaries). Novel merging criteria based on Helmholtz principle is then used to evaluate the meaningfulness between separate line segments and their merged ones. The improved multiscale framework facilitates line segments merging in detection and post-detection processes, yielding more high-quality line segments. Finally, the proposed method is compared with four leading methods on the famous public dataset, YorkUrban-LineSegment. Experimental results demonstrate that the method has good continuity and outperforms the leading methods in F-measure.

LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection

“…It happens when a long line segment is intercepted by another object. Although for some applications it could be desirable to avoid such a splitting and there are approaches to achieve that [12], [13], we believe, that for general-purpose detector splitting is the desired detector's behaviour.…”

“…However, they may miss the segments that are salient for human, but for some reason don't match the exact explicit implemented definition. They are also prone to over-segmentation (splitting a single segment into parts) and sometimes demand nontrivial problem-specific postprocessing [12], [13].…”

A Review of Intelligent Assembly Technology of Small Electronic Equipment

“…Gioi [ 48 ] proposed a linear-time line segment detector (LSD), which was faster and less complex than Hough transform. Yu et al [ 49 ] proposed a perceptually accurate line segment detection approach (PLSD), which used line segment grouping, line segment verification, and a multi-scale framework, to improve the line segment detection method and generate higher quality line segments. White et al [ 50 ] obtained welds based on least squares and gravity center fitting and extracted welding points to realize weld positioning.…”

Latency-driven Model Placement for Efficient Edge Intelligence Service

“…As a step forward, Cho et al [20] not only utilized gradient but also other information such as brightness and gradient intensity to further improve the performance. Some other variants like PLSD [15] developed line merging strategies but sometimes tend to over-segment. An obvious limitation of the handcrafted approaches is that the detection is based on low-level information like image gradient and brightness, leading to the unawareness of higher-level semantic information.…”

“…They are computationally cheap but not adaptive or learnable, which might result in inconsistent detection in varying environments. Some recent methods like [15] outperform LSD but they still have a limited perceptual ability and lack adaptivity.…”