Scale-aware feature pyramid architecture for marine object detection

Chen

et al. 2022

Journal of Sensors

The feature information of small-scale targets is seriously missing under the interference of complex underwater terrain and light refraction. Moreover, the unbalanced distribution of underwater target samples can also affect the accuracy of spatial semantic feature extraction. Aiming at the above problems, this paper proposes a dynamic multiscale feature fusion method for underwater target recognition. Firstly, this paper uses multiscale info noise contrastive estimation (MS-InfoNCE) loss to extract the significant features of the target at 4 scales. Secondly, the method learns the spatial semantic features of the target through a dynamic conditional probability matrix. Finally, this paper designs different feature fusion mechanisms for different scale targets, dynamically fusing multiscale significant features and spatial semantic features to recognize underwater weak targets. The experimental results show that the recognition accuracy of the proposed algorithm is 1.38% higher than that of the existing algorithm when recognizing underwater distorted targets.

Section: Resultsmentioning

confidence: 99%

Dynamic Multiscale Feature Fusion Method for Underwater Target Recognition

Chen

et al. 2022

Journal of Sensors

“…is section evaluates the recognition performance of the proposed algorithm in conventional underwater images and compares it with FFBNet [23], SiamFPN [24], SA-FPN [25], and Faster R-CNN [26]. e recognition results are shown in Figure 4, and the recognition accuracy and recognition speed are shown in Table 1.…”

Section: Conventional Underwater Image Recognition Resultsmentioning

confidence: 99%

“…is section evaluates the performance of the proposed algorithm to recognize underwater blurred images and compares it with FFBNet [23], SiamFPN [24], SA-FPN [25], Computational Intelligence and Neuroscience and Faster R-CNN [26]. e recognition results are shown in Figure 5.…”

Section: Underwater Blurred Image Recognition Resultsmentioning

confidence: 99%

Underwater Distortion Target Recognition Network (UDTRNet) via Enhanced Image Features

Computational Intelligence and Neuroscience

Chen

Chai

2021

It is difficult for the autonomous underwater vehicle (AUV) to recognize targets similar to the environment in lacking data labels. Moreover, the complex underwater environment and the refraction of light cause the AUV to be unable to extract the complete significant features of the target. In response to the above problems, this paper proposes an underwater distortion target recognition network (UDTRNet) that can enhance image features. Firstly, this paper extracts the significant features of the image by minimizing the info noise contrastive estimation (InfoNCE) loss. Secondly, this paper constructs the dynamic correlation matrix to capture the spatial semantic relationship of the target and uses the matrix to extract spatial semantic features. Finally, this paper fuses the significant features and spatial semantic features of the target and trains the target recognition model through cross-entropy loss. The experimental results show that the mean average precision (mAP) of the algorithm in this paper increases by 1.52% in recognizing underwater blurred images.

“…The evaluation indicators of the algorithm are mAP and time. First, we compare the methods proposed in this paper with advanced methods, such as SA-FPN [24], YOLOv4 [25], ViTDet [26], and UPDETR [27]. In each subsection, we analyze the experimental results, and the conclusions of the experiments provide a clear picture of the efficiency of the algorithm in this paper.…”

Section: Underwater Image Missing Feature Generation Modulementioning

confidence: 99%

Underwater Incomplete Target Recognition Network via Generating Feature Module

Shen

Jia

International Journal of Distributed Sensor Networks

2023

A complex and changeable underwater archaeological environment leads to the lack of target features in the collected images, affecting the accuracy of target detection. Meanwhile, the difficulty in obtaining underwater archaeological images leads to less training data, resulting in poor generalization performance of the recognition algorithm. For these practical issues, we propose an underwater incomplete target recognition network via generating feature module (UITRNet). Specifically, for targets that lack features, features are generated by dual discriminators and generators to improve target detection accuracy. Then, multilayer features are fused to extract regions of interest. Finally, supervised contrastive learning is introduced into few-shot learning to improve the intraclass similarity and interclass distance of the target and enhance the generalization of the algorithm. The UIFI dataset is produced to verify the effectiveness of the algorithm in this paper. The experimental results show that the mean average precision (mAP) of our algorithm was improved by 0.86% and 1.29% under insufficient light and semiburied interference, respectively. The mAP for ship identification reached the highest level under all four sets of experiments.