基于改进CenterNet的工业目标检测方法

2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI) Pub Date : 2021-08-01 DOI:10.1109/ICCEAI52939.2021.00023

Cong Tang, Zhaoming Wu, Shengqian Wang, Chengzhi Deng, Linjie Luo

{"title":"基于改进CenterNet的工业目标检测方法","authors":"Cong Tang, Zhaoming Wu, Shengqian Wang, Chengzhi Deng, Linjie Luo","doi":"10.1109/ICCEAI52939.2021.00023","DOIUrl":null,"url":null,"abstract":"Aiming at the contradiction between accuracy and speed in industrial object detection, this paper proposes an industrial object detection method based on improved CenterNet. The improved method uses ResNet-50 as the Backbone to boost detection speed, and an upsampling layer is added to the feature processing network to improve detection accuracy. The expermient results show that the mAP of the improved method reaches 87.41 %, which is 3.44% higher than the CenterNet-Res101 method, and the detection speed reaches 31 FPS, which is 4 FPS faster than the CenterNet-Res101 method.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Industrial object detection method based on improved CenterNet\",\"authors\":\"Cong Tang, Zhaoming Wu, Shengqian Wang, Chengzhi Deng, Linjie Luo\",\"doi\":\"10.1109/ICCEAI52939.2021.00023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Aiming at the contradiction between accuracy and speed in industrial object detection, this paper proposes an industrial object detection method based on improved CenterNet. The improved method uses ResNet-50 as the Backbone to boost detection speed, and an upsampling layer is added to the feature processing network to improve detection accuracy. The expermient results show that the mAP of the improved method reaches 87.41 %, which is 3.44% higher than the CenterNet-Res101 method, and the detection speed reaches 31 FPS, which is 4 FPS faster than the CenterNet-Res101 method.\",\"PeriodicalId\":331409,\"journal\":{\"name\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCEAI52939.2021.00023\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

针对工业物体检测中精度与速度的矛盾，提出了一种基于改进CenterNet的工业物体检测方法。改进后的方法采用ResNet-50作为主干网络来提高检测速度，并在特征处理网络中增加上采样层来提高检测精度。实验结果表明，改进方法的mAP达到87.41%，比CenterNet-Res101方法提高了3.44%，检测速度达到31 FPS，比CenterNet-Res101方法提高了4 FPS。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Industrial object detection method based on improved CenterNet

Aiming at the contradiction between accuracy and speed in industrial object detection, this paper proposes an industrial object detection method based on improved CenterNet. The improved method uses ResNet-50 as the Backbone to boost detection speed, and an upsampling layer is added to the feature processing network to improve detection accuracy. The expermient results show that the mAP of the improved method reaches 87.41 %, which is 3.44% higher than the CenterNet-Res101 method, and the detection speed reaches 31 FPS, which is 4 FPS faster than the CenterNet-Res101 method.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)

自引率

0.00%

发文量