Multi-Scale Feature Aggregation Network for Water Area Segmentation

Abstract

Water area segmentation is an important branch of remote sensing image segmentation, but in reality, most water area images have complex and diverse backgrounds. Traditional detection methods cannot accurately identify small tributaries due to incomplete mining and insufficient utilization of semantic information, and the edge information of segmentation is rough. To solve the above problems, we propose a multi-scale feature aggregation network. In order to improve the ability of the network to process boundary information, we design a deep feature extraction module using a multi-scale pyramid to extract features, combined with the designed attention mechanism and strip convolution, extraction of multi-scale deep semantic information and enhancement of spatial and location information. Then, the multi-branch aggregation module is used to interact with different scale features to enhance the positioning information of the pixels. Finally, the two high-performance branches designed in the Feature Fusion Upsample module are used to deeply extract the semantic information of the image, and the deep information is fused with the shallow information generated by the multi-branch module to improve the ability of the network. Global and local features are used to determine the location distribution of each image category. The experimental results show that the accuracy of the segmentation method in this paper is better than that in the previous detection methods, and has important practical significance for the actual water area segmentation.

Multiple Attention Mechanism Graph Convolution HAR Model Based on Coordination Theory

“…Due to the limitation of human body topology, it is difficult for the graph volume model to learn the relationship between various end nodes, which is often an important part of the action. In addition, the deep graph convolution model easily leads to the phenomenon of excessive smoothing of features [ 25 , 26 , 27 ], so it is not suitable to use the deep model [ 28 , 29 , 30 ]. Inspired by the dual attention network (DA-net) [ 31 , 32 ], an attention module is proposed.…”

Safety Equipment Wearing Detection Algorithm for Electric Power Workers Based on RepGFPN-YOLOv5

“…The reconstructed neck network contains 5 Concat parallel operations and 5 CSPStage feature fusion modules. Among them, the Concat_1, Concat_2, Con-cat_3, Concat_4, and Concat_5 connection network layers are (10,11), (6,14,15), (4,18), (17,21), and (13,24,25), respectively. Among them, the fusion module CSPStage2 with enhanced feature expression ability outputs feature maps through Concat_3 and Concat_4 respectively, and CSPStage1 is connected to the deep feature map through Concat_5.…”

An Overview on Visual SLAM: From Tradition to Semantic

“…Modern semantic VSLAM systems cannot do without the help of deep learning, and feature attributes and association relations obtained through learning can be used in different tasks [138]. As an important branch of machine learning, deep learning has achieved remarkable results in image recognition [139], semantic understanding [140], image matching [141], 3D reconstruction [142], and other tasks. The application of deep learning in computer vision can greatly ease the problems encountered by traditional methods [143].…”