Robust Underwater Object Detection with Autonomous Underwater Vehicle

Abstract

Underwater Object Detection had been one of the most challenging research fields of Computer Vision and Image Processing. Before Computer Vision techniques were used for underwater imaging, all the tasks associated with object detection had to be done manually by marine scientists making the task one of the most tedious and error prone. For this case, Underwater Autonomous Vehicles (UAV) has been developed to capture real time videos for specific object detection. Using different hardware improvements and using many varied forms of algorithms, classification of objects, mainly living objects had been carried with different AUVs and high-resolution cameras. Conventional object detection methods of Computer Vision fail to provide accurate detection results due to some challenges faced underwater. For such reasons, object detection underwater needs to be robust, real time and fast also being accurate, for which deep learning approaches are introduced. In this paper, all the works here all the trending underwater object detection techniques are discussed in details and a comprehensive comparative study is carried out.