Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection
This work addresses marine debris detection for environmental and health monitoring, but it is incremental as it builds on existing EfficientDet methods.
The paper tackled the problem of improving real-time and low-light object detection for marine debris using autonomous underwater vehicles, achieving efficiency gains of 1.5% to 2.6% AP on EfficientDets without increasing GPU latency and evaluating low-light enhancement strategies.
Marine debris is a problem both for the health of marine environments and for the human health since tiny pieces of plastic called "microplastics" resulting from the debris decomposition over the time are entering the food chain at any levels. For marine debris detection and removal, autonomous underwater vehicles (AUVs) are a potential solution. In this letter, we focus on the efficiency of AUV vision for real-time and low-light object detection. First, we improved the efficiency of a class of state-of-the-art object detectors, namely EfficientDets, by 1.5% AP on D0, 2.6% AP on D1, 1.2% AP on D2 and 1.3% AP on D3 without increasing the GPU latency. Subsequently, we created and made publicly available a dataset for the detection of in-water plastic bags and bottles and trained our improved EfficientDets on this and another dataset for marine debris detection. Finally, we investigated how the detector performance is affected by low-light conditions and compared two low-light underwater image enhancement strategies both in terms of accuracy and latency. Source code and dataset are publicly available.