depth estimation

segmentation algorithm

small object

pedestrian detection

edge detection

face detection

camouflaged object

object detection

Pattern Recognition

• Segment detection for low computational power devices. • Enhanced Edge Drawing algorithm. • Integrated capability of jumping over small discontinuities. • New methodology to evaluate accuracy and repeatability. • Best AP for efficient segment detectors and best overall repeatability. 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. 1 1 Source code: https://github.com/iago-suarez/ELSED In the experiments we quantify the accuracy traded for such gain.

ELSED: Enhanced line SEgment drawing