Weak Edge Identification Nets for Ocean Front Detection

TL;DR

This paper introduces WEIN, a deep learning-based method for detecting weak ocean front edges more accurately than traditional algorithms, by using multi-stage fusion and specialized loss functions.

Contribution

The paper proposes a novel weak edge identification network (WEIN) that effectively detects ocean fronts by leveraging multi-stage fusion and correlation loss.

Findings

WEIN outperforms traditional edge detection methods in accuracy.

The multi-stage fusion approach enhances weak edge detection.

Correlation loss improves the quality of ocean front images.

Abstract

The ocean front has an important impact in many areas, it is meaningful to obtain accurate ocean front positioning, therefore, ocean front detection is a very important task. However, the traditional edge detection algorithm does not detect the weak edge information of the ocean front very well. In response to this problem, we collected relevant ocean front gradient images and found relevant experts to calibrate the ocean front data to obtain groundtruth, and proposed a weak edge identification nets(WEIN) for ocean front detection. Whether it is qualitative or quantitative, our methods perform best. The method uses a welltrained deep learning model to accurately extract the ocean front from the ocean front gradient image. The detection network is divided into multiple stages, and the final output is a multi-stage output image fusion. The method uses the stochastic gradient descent and the correlation loss function to obtain a good ocean front image output.