Multiple object detection of workpieces based on fusion of deep learning and image processing

Tools

Lei, Yi and Yao, Xifan and Chen, Wocheng and Zhang, Junming and Mehnen, Jorn and Yang, Erfu (2020) Multiple object detection of workpieces based on fusion of deep learning and image processing. In: IEEE World Congress on Computational Intelligence 2020, 2020-07-19 - 2020-07-24. (https://doi.org/10.1109/IJCNN48605.2020.9207566)

[thumbnail of Lei-etal-WCCI-2020-Multiple-object-detection-of-workpieces-based-on-fusion]
Preview
 Text. Filename: Lei_etal_WCCI_2020_Multiple_object_detection_of_workpieces_based_on_fusion.pdf
Accepted Author Manuscript
Download (568kB)| Preview

Abstract

A workpiece detection method based on fusion of deep learning and image processing is proposed. Firstly, the workpiece bounding boxes are located in the workpiece images by YOLOv3, whose parameters are compressed by an improved convolutional neural network residual structure pruning strategy. Then, the workpiece images are cropped based on the bounding boxes with cropping biases. Finally, the contours and suitable gripping points of the workpieces are obtained through image processing. The experimental results show that mean Average Precision (mAP) is 98.60% for YOLOv3, and 99.38% for that one by pruning 50.89% of its parameters, and the inference time is shortened by 31.13%. Image processing effectively corrects the bounding boxes obtained by deep learning, and obtains workpiece contour and gripping point information.

ORCID iDs

Lei, Yi, Yao, Xifan, Chen, Wocheng, Zhang, Junming, Mehnen, Jorn ORCID logoORCID: https://orcid.org/0000-0001-6625-436X and Yang, Erfu ORCID logoORCID: https://orcid.org/0000-0003-1813-5950;
  • Item type:Conference or Workshop Item(Paper)
    ID code:72167
    Dates:
    Date
    Event
    28 September 2020
    Published
    19 April 2020
    Accepted
    Notes:© Copyright 2020 IEEE - All rights reserved. Y. Lei, X. Yao, W. Chen, J. Zhang, J. Mehnen and E. Yang, "Multiple Object Detection of Workpieces Based on Fusion of Deep Learning and Image Processing," 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020, pp. 1-7, doi: 10.1109/IJCNN48605.2020.9207566.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Design, Manufacture and Engineering Management
    Depositing user: Pure Administrator
    Date deposited:27 Apr 2020 13:25
    Last modified:16 Dec 2024 03:11
    URI:https://strathprints.strath.ac.uk/id/eprint/72167
CORE (COnnecting REpositories)