Efficient Underwater Object Detection Using Deep Neural Networks

The increasing amount of underwater visual data and deep sea research have led to the rise of marine animal identification as a major field for data processing and analysis. The need to protect the ecosystem emphasizes how important this endeavor is, yet it's still difficult because of things like the complexities of underwater backdrops, poor picture and video quality, and the variety of movements that marine life exhibits. This research used deep learning techniques to identify certain marine species and mark their presence with bounding boxes in uploaded images and videos in order to overcome these difficulties. The main goal is to provide workable methods for detecting marine life, so providing crucial backing for further studies in this area. By using the core deep learning frameworks, YOLOv8 and Faster-RCNN, the research was able to improve the efficiency and accuracy of marine life identification by making significant progress in detection time and mean average precision (mAP). This research work not only solves the current problems with finding marine animals but also establishes the groundwork for future research into comprehending and protecting the fragile undersea ecology.