Coarse-grained soil particle tracking and crushing matching method based on computer vision

CN119313925AInactive Publication Date: 2025-01-14ZHEJIANG UNIV OF TECH
-1 Cites 4 Cited by

Patent Information

Application Number
CN202411850101.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-16
Publication Date
2025-01-14
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure CN119313925A_ABST
    Figure CN119313925A_ABST
Patent Text Reader

Abstract

The invention relates to a coarse-grained soil particle tracking and crushing matching method based on computer vision, and the method comprises the following steps: S1, carrying out the recognition of coarse-grained soil particles in an image or a video through a trained YOLO11 model; s2, carrying out multi-target tracking on the identification result of the coarse-grained soil particles in the step S1 by using BoT-SORT; s3, tracking fine-grained soil particles outside the YOLO11 identification area by using a PIV (particle image velocimetry) algorithm; and S4, performing feature point extraction on the tracking result obtained in the S2 by using an SIFT algorithm, and matching the feature points by using an FLANN to obtain a soil particle crushing matching result. According to the method, uneven grading particle tracking and crushing matching can be achieved, after first training is carried out, coarse-grained soil particles of the same type and different forms can be tracked, and extremely high robustness and generalization ability are achieved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Coarse-grained soil broken particle tracking method based on improved YOLOv8

    CN118470062A

  • Coarse-grained soil broken particle tracking method based on YOLOv8 network model

    CN118537366A

  • Adaptive high-precision compression method and system based on convolutional neural network model

    US20220351043A1

  • Quickly extraction of morphology characterization parameters of recycled concrete sand particles based on deep learning technology

    US20230394806A1

Cited By

  • Particle tracking method and device, electronic equipment and storage medium

    CN121095279A

  • A particle tracking method, device, electronic equipment and storage medium

    CN121095279B

  • Wheeled robot trafficability determination algorithm under road surface defect condition

    CN121190989A

  • Method for monitoring roller deviation of inclined zipper equipment in cement industry

    CN121708051A