文献类型：期刊文献

英文题名：A Deep Neural Network Based on Circular Representation for Target Detection

作者：Lin, Cong[1];Chen, Zhoujian[1];Huang, Yiquan[1];Jiang, Haoyu[1];Du, Wencai[2];Chen, Qiong[3]

机构：[1]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524025, Peoples R China;[2]Univ St Joseph, Inst Data Engn & Sci, Macau, Peoples R China;[3]Tsinghua Univ, Inst Global Change Studies, Dept Earth Syst Sci, Key Lab Earth Syst Modeling,Minist Educ, Beijing 100084, Peoples R China

年份：2022

卷号：2022

外文期刊名：JOURNAL OF SENSORS

收录：SCI-EXPANDED(收录号：WOS:000827912800002)、、EI(收录号：20222012107419)、Scopus(收录号：2-s2.0-85129977384)、WOS

基金：Cong Lin and Zhoujian Chen are the co-first authors and contributed equally to this work. Qiong Chen and Wencai Du are the cocorrespondence authors. This work was supported by the National Natural Science Foundation of China under Grant 62072121 and Natural Science Foundation of Guangdong Province 2021A1515011847.

语种：英文

外文关键词：Convolutional neural networks - Deep neural networks - Object detection - Object recognition

外文摘要：Convolutional neural network (CNN) model based on deep learning has excellent performance for target detection. However, the detection effect is poor when the object is circular or tubular because most of the existing object detection methods are based on the traditional rectangular box to detect and recognize objects. To solve the problem, we propose the circular representation structure and RepVGG module on the basis of CenterNet and expand the network prediction structure, thus proposing a high-precision and high-efficiency lightweight circular object detection method RebarDet Specifically, circular tubular type objects will be optimized by replacing the traditional rectangular box with a circular box. Second, we improve the resolution of the network feature map and the upper limit of the number of objects detected in a single detect to achieve the expansion of the network prediction structure, optimized for the dense phenomenon that often occurs in circular tubular objects. Finally, the multibranch topology of RepVGG is introduced to sum the feature information extracted by different convolution modules, which improves the ability of the convolution module to extract information. We conducted extensive experiments on rebar datasets and used AB-Score as a new evaluation method to evaluate RebarDet. The experimental results show that RebarDet can achieve a detection accuracy of up to 0.8114 and a model inference speed of 6.9 fps while maintaining a moderate amount of parameters, which is superior to other mainstream object detection models and verifies the effectiveness of our proposed method. At the same time, RebarDet's high precision detection of round tubular objects facilitates enterprise intelligent manufacturing processes.