Description
Dataset for "Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection." This is the "In-Water Plastic Bags and Bottles" (WPBB) dataset for marine debris detection.
All shards have 300 samples, hence the total number of samples in this dataset is 900; 500 with plastic bags and 400 with plastic bottles. Annotations are in PASCAL VOC 2012 format.
This dataset is linked to the paper: https://arxiv.org/pdf/2203.07155.pdf and it is funded by the UKRI-NERC project [grant number NE/V008080/1]:
Paper abstract:
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% APonD3without 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.
All shards have 300 samples, hence the total number of samples in this dataset is 900; 500 with plastic bags and 400 with plastic bottles. Annotations are in PASCAL VOC 2012 format.
This dataset is linked to the paper: https://arxiv.org/pdf/2203.07155.pdf and it is funded by the UKRI-NERC project [grant number NE/V008080/1]:
Paper abstract:
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% APonD3without 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.
| Date made available | Mar 2022 |
|---|---|
| Publisher | Queen's University Belfast |
| Date of data production | Mar 2022 |