Material identification of construction machinery based on multisource sensor information fusion
Abstract In order to improve the recognition accuracy of construction machinery and equipment and materials in low contrast scenes, a construction machinery material recognition algorithm based on multisource sensor information fusion is proposed. In the paper, the millimeter wave radar is fused wit...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-10-01
|
Series: | Engineering Reports |
Subjects: | |
Online Access: | https://doi.org/10.1002/eng2.12512 |
_version_ | 1811230276950425600 |
---|---|
author | Dengsheng Cai Zhigang Lu Xiangsuo Fan Jiale Yao Bing Li |
author_facet | Dengsheng Cai Zhigang Lu Xiangsuo Fan Jiale Yao Bing Li |
author_sort | Dengsheng Cai |
collection | DOAJ |
description | Abstract In order to improve the recognition accuracy of construction machinery and equipment and materials in low contrast scenes, a construction machinery material recognition algorithm based on multisource sensor information fusion is proposed. In the paper, the millimeter wave radar is fused with the camera considering its strong penetration ability in rainy and foggy days and dim environments. Firstly, the spatial coordinates of radar and camera are unified by establishing a spatial fusion model of millimeter wave and camera; then the target acquired by millimeter wave is projected onto the image and the detection frame intersection and ratio model is used to generate the region of interest of the camera; finally, the improved YOLOv2 algorithm is used to identify the region of interest, and in the improved idea, the low‐level information is first connected with the high‐level information in multilayer depth. At the same time, a multiscale feature pyramid network structure is used to achieve recognition of objects of different scales. This model effectively reduces interference from other feature categories while improving the recognition efficiency of the system. The algorithm can effectively improve the recognition accuracy of mechanical materials in low‐contrast scenes, as demonstrated by the validation of different scenes. |
first_indexed | 2024-04-12T10:26:52Z |
format | Article |
id | doaj.art-4c678ffd9a454562aa9fc95f38c331f4 |
institution | Directory Open Access Journal |
issn | 2577-8196 |
language | English |
last_indexed | 2024-04-12T10:26:52Z |
publishDate | 2022-10-01 |
publisher | Wiley |
record_format | Article |
series | Engineering Reports |
spelling | doaj.art-4c678ffd9a454562aa9fc95f38c331f42022-12-22T03:36:57ZengWileyEngineering Reports2577-81962022-10-01410n/an/a10.1002/eng2.12512Material identification of construction machinery based on multisource sensor information fusionDengsheng Cai0Zhigang Lu1Xiangsuo Fan2Jiale Yao3Bing Li4School of Electrical Engineering Yanshan University Qinhuangdao Hebei ChinaSchool of Electrical Engineering Yanshan University Qinhuangdao Hebei ChinaIntelligent Technology Research Institute of Global Research and Development Center Guangxi LiuGong Machinery Company Limited Liuzhou Guangxi ChinaGuangxi Collaborative Innovation Centre for Earthmoving Machinery Guangxi University of Science and Technology Liuzhou Guangxi ChinaGuangxi Collaborative Innovation Centre for Earthmoving Machinery Guangxi University of Science and Technology Liuzhou Guangxi ChinaAbstract In order to improve the recognition accuracy of construction machinery and equipment and materials in low contrast scenes, a construction machinery material recognition algorithm based on multisource sensor information fusion is proposed. In the paper, the millimeter wave radar is fused with the camera considering its strong penetration ability in rainy and foggy days and dim environments. Firstly, the spatial coordinates of radar and camera are unified by establishing a spatial fusion model of millimeter wave and camera; then the target acquired by millimeter wave is projected onto the image and the detection frame intersection and ratio model is used to generate the region of interest of the camera; finally, the improved YOLOv2 algorithm is used to identify the region of interest, and in the improved idea, the low‐level information is first connected with the high‐level information in multilayer depth. At the same time, a multiscale feature pyramid network structure is used to achieve recognition of objects of different scales. This model effectively reduces interference from other feature categories while improving the recognition efficiency of the system. The algorithm can effectively improve the recognition accuracy of mechanical materials in low‐contrast scenes, as demonstrated by the validation of different scenes.https://doi.org/10.1002/eng2.12512multisource information fusionradarrecognitionvisionYOLOv2 algorithm |
spellingShingle | Dengsheng Cai Zhigang Lu Xiangsuo Fan Jiale Yao Bing Li Material identification of construction machinery based on multisource sensor information fusion Engineering Reports multisource information fusion radar recognition vision YOLOv2 algorithm |
title | Material identification of construction machinery based on multisource sensor information fusion |
title_full | Material identification of construction machinery based on multisource sensor information fusion |
title_fullStr | Material identification of construction machinery based on multisource sensor information fusion |
title_full_unstemmed | Material identification of construction machinery based on multisource sensor information fusion |
title_short | Material identification of construction machinery based on multisource sensor information fusion |
title_sort | material identification of construction machinery based on multisource sensor information fusion |
topic | multisource information fusion radar recognition vision YOLOv2 algorithm |
url | https://doi.org/10.1002/eng2.12512 |
work_keys_str_mv | AT dengshengcai materialidentificationofconstructionmachinerybasedonmultisourcesensorinformationfusion AT zhiganglu materialidentificationofconstructionmachinerybasedonmultisourcesensorinformationfusion AT xiangsuofan materialidentificationofconstructionmachinerybasedonmultisourcesensorinformationfusion AT jialeyao materialidentificationofconstructionmachinerybasedonmultisourcesensorinformationfusion AT bingli materialidentificationofconstructionmachinerybasedonmultisourcesensorinformationfusion |