| Title | Water Surface Object Detection Based on Neural Style Learning Algorithm |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Gong, Peiyong, Zheng, Kai, Jiang, Yi, Liu, Jia |
| Conference Name | 2021 40th Chinese Control Conference (CCC) |
| Keywords | convolutional neural network, convolutional neural networks, Deep Learning, image recognition, image texture, Metrics, Neural networks, Neural style, neural style transfer, object detection, pubcrawl, resilience, Resiliency, Scalability, Surface texture, Water surface object detection |
| Abstract | In order to detect the objects on the water surface, a neural style learning algorithm is proposed in this paper. The algorithm uses the Gram matrix of a pre-trained convolutional neural network to represent the style of the texture in the image, which is originally used for image style transfer. The objects on the water surface can be easily distinguished by the difference in their styles of the image texture. The algorithm is tested on the dataset of the Airbus Ship Detection Challenge on Kaggle. Compared to the other water surface object detection algorithms, the proposed algorithm has a good precision of 0.925 with recall equals to 0.86. |
| DOI | 10.23919/CCC52363.2021.9549756 |
| Citation Key | gong_water_2021 |
Water Surface Object Detection Based on Neural Style Learning Algorithm