您当前的位置:
首页 >
文章列表页 >
Dense control valve parts dataset for industrial object detection
Information Sciences | 更新时间:2024-05-08
    • Dense control valve parts dataset for industrial object detection

    • Significant progress has been made in a study targeting practical industrial scenarios. The research team has released a dense control valve parts dataset called PD4CV (Part Detection for Control Valve) 2023, providing new resources for automatic object detection in industrial production. This dataset originates from the control valve production workshop and contains 9 types of parts, 510 images of workbenches, and 15015 part samples. It has characteristics such as dense placement, occlusion, large size differences, and similar appearances, which pose many challenges for automatic object detection. Through comparative experiments, the research team found that general scenario datasets and specific industrial scenario datasets are difficult to cope with the specificity of the PD4CV2023 dataset. However, a comprehensive comparison of a series of object detection algorithms on this dataset has validated its effectiveness, demonstrating the superiority of the PD4CV2023 dataset in general object detection, multi-scale object detection, small-scale, and imbalanced data object detection. This research achievement provides a new direction for industrial object detection research and is expected to promote the automation and intelligence process in industrial production. At the same time, this dataset also provides valuable experimental resources for researchers in related fields, laying a solid foundation for solving object detection problems in industrial automation.
    • Optics and Precision Engineering   Vol. 32, Issue 8, Pages: 1241-1251(2024)
    • DOI:10.37188/OPE.20243208.1241    

      CLC: TP391.41;TG95
    • Received:22 September 2023

      Revised:14 November 2023

      Published:25 April 2024

    移动端阅览

  • WANG Linyi,BAI Jing,LI Yanmei,et al.Dense control valve parts dataset for industrial object detection[J].Optics and Precision Engineering,2024,32(08):1241-1251. DOI: 10.37188/OPE.20243208.1241.

  •  
  •  

0

Views

468

下载量

0

CSCD

Alert me when the article has been cited
提交
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

Computed tomography image segmentation of cell pole piece via strip attention mechanism
YOLOv8 model-based additive manufacturing micro porosity defect detection and its dimension measurement
3DRes-ViT knee osteoarthritis classification model based on multimodal fusion
Degradation remote sensing image quality enhancement based on frequency-domain-spatial-domain hybrid attention
Lightweight video super-resolution based on hybrid spatio-temporal convolution

Related Author

LIU Zefang
LONG Chao
LIU Xueshuan
HAN Yan
TAN Chuandong
TAN Hui
DUAN Liming
CAI Yindi

Related Institution

ICT Research Center, Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education, Chongqing University
College of Optoelectronic Engineering, Chongqing University
Project Management Center, Equipment Department of Rocket Force
College of Mechanical Engineering, Dalian University of Technology
College of Computer Science and Engineering, Changchun University of Technology
0