ATLANTIS: A benchmark for semantic segmentation of waterbody images

• Published in: Environmental modelling & software : with environment data news Vol. 149; p. 105333
• Main Authors: Erfani, Seyed Mohammad Hassan, Wu, Zhenyao, Wu, Xinyi, Wang, Song, Goharian, Erfan
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.03.2022; Elsevier Science Ltd
• Subjects: Artificial neural networks; Benchmarks; Computer vision; Datasets; Deep learning models; Flooding; Image annotation; Image processing; Image segmentation; Information management; Information processing; Modulation; Neural networks; Semantic segmentation; Semantics; State-of-the-art reviews; Water management; Water resources; Water resources engineering; Water resources management; Waterbody image dataset; Computer vision; Deep learning models; Waterbody image dataset; Semantic segmentation; Water resources engineering
• ISSN: 1364-8152; 1873-6726
• DOI: 10.1016/j.envsoft.2022.105333

Vision-based semantic segmentation of waterbodies and nearby related objects provides important information for managing water resources and handling flooding emergency. However, the lack of large-scale labeled training and testing datasets for water-related categories prevents researchers from studying water-related issues in the computer vision field. To tackle this problem, we present ATLANTIS, a new benchmark for semantic segmentation of waterbodies and related objects. ATLANTIS consists of 5,195 images of waterbodies, as well as high quality pixel-level manual annotations of 56 classes of objects, including 17 classes of man-made objects, 18 classes of natural objects and 21 general classes. We analyze ATLANTIS in detail and evaluate several state-of-the-art semantic segmentation networks on our benchmark. In addition, a novel deep neural network, AQUANet, is developed for waterbody semantic segmentation by processing the aquatic and non-aquatic regions in two different paths. AQUANet also incorporates low-level feature modulation and cross-path modulation for enhancing feature representation. Experimental results show that the proposed AQUANet outperforms other state-of-the-art semantic segmentation networks on ATLANTIS. We claim that ATLANTIS is the largest waterbody image dataset for semantic segmentation providing a wide range of water and water-related classes and it will benefit researchers of both computer vision and water resources engineering. • •ATLANTIS, a large-scale dataset for semantic segmentation of waterbodies and water-related structures is introduced.• •ATeX (ATLANTIS TeXture), a new benchmark for classification and texture analysis of water in different waterbodies is introduced.• •AQUANet, a novel network, developed for semantic segmentation of waterbodies achieves the best performance on ATLANTIS.