Accurate information on urban surface water is important for assessing the role it plays in urban ecosystem services in the context of human survival and climate change. The precise extraction of urban water bodies from images is of great significance for urban planning and socioeconomic development. In this paper, a novel deep-learning architecture is proposed for the extraction of urban water bodies from high-resolution remote sensing (HRRS) imagery. First, an adaptive simple linear iterative clustering algorithm is applied for segmentation of the remote-sensing image into high-quality superpixels. Then, a new convolutional neural network (CNN) architecture is designed that can extract useful high-level features of water bodies from input data in a complex urban background and mark the superpixel as one of two classes: an including water or no-water pixel. Finally, a high-resolution image of water-extracted superpixels is generated. Experimental results show that the proposed method achieved higher accuracy for water extraction from the high-resolution remote-sensing images than traditional approaches, and the average overall accuracy is 99.14%.

In high-resolution image data, multilevel cloud detection is a key task for remote sensing data processing. Generally, it is difficult to obtain high accuracy for multilevel cloud detection when using satellite imagery which only contains visible and near-infrared spectral bands. So, multilevel cloud detection for high-resolution remote sensing imagery is challenging. In this paper, a new multilevel cloud detection technique is proposed based on the multiple convolutional neural networks for high-resolution remote sensing imagery. In order to avoid input the entire image into the network for cloud detection, the adaptive simple linear iterative clustering (A-SCLI) algorithm was applied to the segmentation of the satellite image to obtain good-quality superpixels. After that, a new multiple convolutional neural networks (MCNNs) architecture is designed to extract multiscale features from each superpixel, and the superpixels are marked as thin cloud, thick cloud, cloud shadow, and non-cloud. The results suggest that the proposed method can detect multilevel clouds and obtain a high accuracy for high-resolution remote sensing imagery.

Underwater acoustic sensor networks (UASNs) have become a popular research topic, with research challenges focused on underwater communication techniques. By incorporating long end-to-end latency, high energy consumption and dynamic network topology in UASNs, many intelligent routing protocols have been proposed to solve the problem. However, shortcomings still exist, and comprehensive routing protocols are urgently needed. In this paper, we propose an adaptive Deep Q-Network-based energyand latency-aware routing protocol (DQELR) to prolong network lifetimes in UASNs. In the DQELR, a Deep Q-Network algorithm with both off-policy and on-policy methods is adopted to make globally optimal routing decisions. Based on both the energy and depth states of nodes at different communication stages, nodes with the maximum Q-value can be selected as forwarders adaptively considering both energy and latency. A hybrid of the broadcast and unicast communication mechanisms is also designed to reduce network overhead. In addition, network topology changes can be addressed through an on-policy method that makes a new routing decision when the current route becomes corrupted. With less energy consumption and strict latency limitations, the DQELR can prolong network lifetimes in UASNs. Simulation results show that the DQELR can achieve a superior network lifetime with better latency and energy efficiency performances relative to other general schemes applied in UASNs. INDEX TERMS Underwater acoustic sensor network, routing protocol, deep-Q network.

No abstract

No abstract