Abstract
Image sonar is a widely used wireless communication technology for detecting underwater objects, but the detection process often leads to increased difficulty in object identification due to the lack of equipment resolution. In view of the remarkable results achieved by artificial intelligence techniques in the field of underwater wireless communication research, we propose an object detection method based on convolutional neural network (CNN) and shadow information capture to improve the object recognition and localization effect of underwater sonar images by making full use of the shadow information of the object. We design a Shadow Capture Module (SCM) that can capture the shadow information in the feature map and utilize them. SCM is compatible with CNN models that have a small increase in parameters and a certain degree of portability, and it can effectively alleviate the recognition difficulties caused by the lack of device resolution through referencing shadow features. Through extensive experiments on the underwater sonar data set provided by Pengcheng Lab, the proposed method can effectively improve the feature representation of the CNN model and enhance the difference between class and class features. Under the main evaluation standard of PASCAL VOC 2012, the proposed method improved from an average accuracy (mAP) of 69.61% to 75.73% at an IOU threshold of 0.7, which exceeds many existing conventional deep learning models, while the lightweight design of our proposed module is more helpful for the implementation of artificial intelligence technology in the field of underwater wireless communication.
Highlights
Image sonar is a widely used wireless communication technology for detecting underwater objects, but the detection process often leads to increased difficulty in object identification due to the lack of equipment resolution
In view of the remarkable results achieved by artificial intelligence techniques in the field of underwater wireless communication research, we propose an object detection method based on convolutional neural network (CNN) and shadow information capture to improve the object recognition and localization effect of underwater sonar images by making full use of the shadow information of the object
shadow capture module (SCM) is compatible with CNN models that have a small increase in parameters and a certain degree of portability, and it can effectively alleviate the recognition difficulties caused by the lack of device resolution through referencing shadow features. rough extensive experiments on the underwater sonar data set provided by Pengcheng Lab, the proposed method can effectively improve the feature representation of the CNN model and enhance the difference between class and class features
Summary
C×H×W Figure 2: Shadow Capture Module e structure of shadow capture module. 2.3. Is module takes the shared convolutional feature map output from Hourglass network and the feature map output from the shadow semantic feature capture module containing the high response value of the shadow as input and fuses the two. After the shared convolutional feature map is input into the module, it waits for the shadow semantic feature capture module to output the feature map containing the high response value of the shadow and uses concatenate operation for both and obtains the final feature map C through a fusion function H(·):. After the high-concern areas of shadow features are stripped from the spatial dimension, the values of each pixel in the final feature map should be constituted as follows (taking 1 × 1 convolution as an example): Fji Wj ∗ Xji,. With the learning of the reverse gradient propagation method, the convolution can learn the situation that is most suitable for the fusion of the feature pixels of each channel
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
