ELSED: Enhanced Line SEgment Drawing

TL;DR

ELSED is a new, extremely fast line segment detector that efficiently connects gradient-aligned pixels, suitable for real-time applications and low-end hardware, while maintaining high accuracy and repeatability.

Contribution

The paper introduces ELSED, the fastest line segment detector with a novel local segment growing algorithm and new metrics for evaluation.

Findings

ELSED achieves the highest repeatability among tested detectors.

ELSED is the most efficient line segment detector in the literature.

ELSED can be parametrized for detecting short or long segments.

Abstract

Detecting local features, such as corners, segments or blobs, is the first step in the pipeline of many Computer Vision applications. Its speed is crucial for real-time applications. In this paper we present ELSED, the fastest line segment detector in the literature. The key for its efficiency is a local segment growing algorithm that connects gradient-aligned pixels in presence of small discontinuities. The proposed algorithm not only runs in devices with very low end hardware, but may also be parametrized to foster the detection of short or longer segments, depending on the task at hand. We also introduce new metrics to evaluate the accuracy and repeatability of segment detectors. In our experiments with different public benchmarks we prove that our method accounts the highest repeatability and it is the most efficient in the literature. In the experiments we quantify the accuracy traded for such gain.