![]() ![]() The former is to improve the image quality, and the latter is to perform object recognition and localization. ![]() The current computer vision studies on underwater images mainly include underwater image enhancement and underwater object detection. More and more researchers begin to pay attention to the field of underwater vision. Countries around the world are paying more and more attention to the exploitation of ocean resources. With the rapid social development, production resources are increasingly scarce, and the development and utilization of marine resources become important for human society. Habitat mapping camera(Habcam) UIEBD is available from URL: DOI: 10.1109/TIP.2019.2955241.įunding: This research was funded by the National Natural Science Foundation of China (grant number: 61671470) and the Key Research and Development Program of China (grant number: 2016YFC0802900).Ĭompeting interests: The authors have declared that no competing interests exist. RUIE is available from URL: DOI: 10.1109/TCSVT.2019.2963772 HabCam UID is available from Northeast Fisheries Science Center. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: Article data comes from public data sets. Received: Accepted: JPublished: August 25, 2022Ĭopyright: © 2022 Wang et al. PLoS ONE 17(8):Įditor: Xiyu Liu, Shandong Normal University, CHINA Besides, the ablation experiment also verifies the effectiveness of our method.Ĭitation: Wang J, He X, Shao F, Lu G, Hu R, Jiang Q (2022) Semantic segmentation method of underwater images based on encoder-decoder architecture. On the objective data, the proposed method achieves the highest MIOU of 68.3 and OA of 79.4, and it has a low resource consumption. Compared with the state-of-the-art semantic segmentation algorithms, the proposed method has advantages in segmentation integrity, location accuracy, boundary clarity, and detail in subjective perception. The proposed method was evaluated on RUIE, HabCam UID, and UIEBD. Finally, the context information aggregation decoder fuses the features of the shallow network and the deep network to extract rich contextual information, which greatly reduces information loss. Next, the cascaded atrous convolutional spatial pyramid pooling module integrates boundary features of different scales to enrich target details. Then, the densely connected hybrid atrous convolution effectively expands the receptive field and slows down the speed of resolution reduction. ![]() Firstly, the image enhancement based on multi-spatial transformation is performed to improve the quality of the original images, which is not common in other advanced semantic segmentation methods. ![]() To solve these problems, this paper proposes a semantic segmentation method for underwater images. However, the quality of the original underwater images is so low that traditional semantic segmentation methods obtain poor segmentation results, such as blurred target edges, insufficient segmentation accuracy, and poor regional boundary segmentation effects. With the exploration and development of marine resources, deep learning is more and more widely used in underwater image processing. ![]()
0 Comments
Leave a Reply. |