Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
This addresses the problem of underwater object detection for applications such as marine cleanup and mine detection, though it is incremental as it adapts existing detection proposal methods to a new domain.
The paper tackled generic object detection in forward-looking sonar images, which is complex due to small and unknown objects, by developing a Convolutional Neural Network to score objectness and generate detection proposals, achieving 94% recall with around 60 proposals per image on a marine garbage dataset and demonstrating generalization to unseen objects like chain links and walls.
Forward-looking sonar can capture high resolution images of underwater scenes, but their interpretation is complex. Generic object detection in such images has not been solved, specially in cases of small and unknown objects. In comparison, detection proposal algorithms have produced top performing object detectors in real-world color images. In this work we develop a Convolutional Neural Network that can reliably score objectness of image windows in forward-looking sonar images and by thresholding objectness, we generate detection proposals. In our dataset of marine garbage objects, we obtain 94% recall, generating around 60 proposals per image. The biggest strength of our method is that it can generalize to previously unseen objects. We show this by detecting chain links, walls and a wrench without previous training in such objects. We strongly believe our method can be used for class-independent object detection, with many real-world applications such as chain following and mine detection.