Underwater object detection algorithm based on feature enhancement and progressive dynamic aggregation strategy. (July 2023)

• Record Type: Journal Article
• Authors: Hua, Xia; Cui, Xiaopeng; Xu, Xinghua; Qiu, Shaohua; Liang, Yingjie; Bao, Xianqiang; Li, Zhong
• Is Part Of: Pattern recognition. Volume 139(2023)
• Publication Date: 2023-07
• Subjects: Underwater image -- Dynamic feature fusion -- Small object detection -- Rapid spatial pyramid pooling -- Feature enhancement; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109511
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Firstly, a new feature enhancement gating module is designed to extract the key information contained in features from different dimensions more comprehensively; Then, a feature dynamic fusion module is designed to aggregate the features of adjacent layers, which can establish the relationship between the object scale of the input image and feature fusion, and dynamically learn the fusion weight according to the object scale; Finally, this paper proposes a fast spatial pyramid mixed pooling module (FMSPP) composed of mixed pooling layers of the same size to replaces the spatial pyramid pooling (SPP) in the original yolov5s model, so that the network can obtain stronger texture and contour feature description ability. Abstract: To solve the problems that the conventional object detector is hard to extract features and miss detection of small objects when detecting underwater objects due to the noise of underwater environment and the scale change of objects, this paper designs a novel feature enhancement & progressive dynamic aggregation strategy, and proposes a new underwater object detector based on YOLOv5s. Firstly, a feature enhancement gating module is designed to selectively suppress or enhance multi-level features and reduce the interference of underwater complex environment noise on feature fusion. Then, the adjacent feature fusion mechanism and dynamic fusion module are designed to dynamically learn fusion weights and perform multi-level feature fusion progressively, so as to suppress the conflict information in multi-scale feature fusion and prevent small objects from being submerged by the conflict information. At last, a spatial pyramid pool structure (FMSPP) based on the same size quickly mixed pool layer is proposed, which can make the network obtain stronger description ability of texture and contour features, reduce the parameters, and further improve the generalization ability and classification accuracy. The ablation experiments and multi-method comparison experiments on URPC and DUT-USEG data sets prove the effectiveness of the proposed strategy. Compared with the current mainstream detectors, our detector achieves obvious advantages in detection performance and efficiency.