Efficient Object Detection of Marine Debris using Pruned YOLO Model
This work addresses the need for efficient object detection in marine debris cleanup using AUVs, representing an incremental improvement in model optimization.
This research tackled the problem of detecting marine debris for autonomous underwater vehicles by applying channel pruning to a YOLOv4 model, which increased the frame rate from 15.19 FPS to 19.4 FPS with only a 1.2% drop in mean Average Precision from 97.6% to 96.4%.
Marine debris poses significant harm to marine life due to substances like microplastics, polychlorinated biphenyls, and pesticides, which damage habitats and poison organisms. Human-based solutions, such as diving, are increasingly ineffective in addressing this issue. Autonomous underwater vehicles (AUVs) are being developed for efficient sea garbage collection, with the choice of object detection architecture being critical. This research employs the YOLOv4 model for real-time detection of marine debris using the Trash-ICRA 19 dataset, consisting of 7683 images at 480x320 pixels. Various modifications-pretrained models, training from scratch, mosaic augmentation, layer freezing, YOLOv4-tiny, and channel pruning-are compared to enhance architecture efficiency. Channel pruning significantly improves detection speed, increasing the base YOLOv4 frame rate from 15.19 FPS to 19.4 FPS, with only a 1.2% drop in mean Average Precision, from 97.6% to 96.4%.