Anomaly detection in periodic motion scenes based on multi-scale feature Gaussian weighting analysis

Anomaly monitoring of production line processing equipment based on machine vision is an important method for ensuring its efficient and stable operation. However, problems related to dynamic scenes, accidental and non-transcendental anomalies, image vulnerability to the severe vibrations of machining equipment, and difficulty in accepting the missing detection are significant obstacles to abnormality monitoring in the machining process. A periodic motion scene decomposition method is presented in this paper to solve dynamic scenes, occasional anomalies, severe vibrations, and other issues. Through optimization of the morphological structural elements, the feature points of the 'abnormality' region are obtained, and a Gaussian weighting formula is derived to detect the anomaly and improve the accuracy of detection. This method, which is verified by experiments, effectively overcomes problems related to the machining process and achieves good detection results.

[2]  Xinyue Zhao,et al.  A novel vision-based mold monitoring system in an environment of intense vibration , 2017 .

[3]  Li Pengfei,et al.  Detection of the Fabric Printing Quality Based on the Machine Vision , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[4]  Andrew Otieno,et al.  Machine vision applications in plastics injection molding , 2006 .

[5]  Chul Kim,et al.  A study on the development of computer-aided process planning system for electric product with bending and piercing operations , 2002 .

[6]  Ting-Yun Chi,et al.  An In-Mold Monitoring and Protection System of the Injection Molding Machine Using Offset Correction and Dynamic Safe Range Learning Approach , 2015, 2015 First International Conference on Computational Intelligence Theory, Systems and Applications (CCITSA).

[7]  Huiyu Zhou,et al.  Region-based Mixture of Gaussians modelling for foreground detection in dynamic scenes , 2015, Pattern Recognit..

[8]  Jin-Hyung Kim,et al.  Image alignment method based on CUDA SURF for multi-spectral machine vision application , 2014 .

[9]  Juan V. Lorenzo-Ginori,et al.  A method to determine the size of the structuring element in morphological correction of non-uniform illumination , 2011, 2011 18th IEEE International Conference on Image Processing.

[10]  Xiyang Zhi,et al.  Realization of CUDA-based real-time registration and target localization for high-resolution video images , 2016, Journal of Real-Time Image Processing.

[11]  Massimo Pacella,et al.  Monitoring and diagnosis of multichannel nonlinear profile variations using uncorrelated multilinear principal component analysis , 2013 .

[12]  陈星明 Chen Xing-ming,et al.  Foreground detection based on modified ViBe in dynamic background , 2014 .

[13]  Binoy Pinto,et al.  Speeded Up Robust Features , 2011 .

[14]  Du-Ming Tsai,et al.  Independent component analysis-based defect detection in patterned liquid crystal display surfaces , 2008, Image Vis. Comput..

[15]  Huang Chang-lin.  Inspection of foreign substances in mould using image scattergrams and multi-resolution analysis , 2009 .

[16]  Charles R Farrar,et al.  Damage prognosis: the future of structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[17]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[18]  Nikos Paragios,et al.  Scene modeling and change detection in dynamic scenes: A subspace approach , 2009, Comput. Vis. Image Underst..

[19]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[20]  Vedang Chauhan,et al.  Fault detection and classification in automated assembly machines using machine vision , 2017 .

[21]  Larry S. Davis,et al.  Real-time periodic motion detection, analysis, and applications , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[22]  Sajid Saleem,et al.  A Performance Evaluation of SIFT and SURF for Multispectral Image Matching , 2012, ICIAR.

[23]  S. Leptidis,et al.  Failure analysis of an EDM machined mold-printing die used for the production of truck spare parts , 2016 .

[24]  Ren C. Luo,et al.  On-line self-tuning using embedded pressure sensors in the injection molding process , 2000, 2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation. 21st Century Technologies.

[25]  Luis M. López-González,et al.  Development of indicators for the detection of equipment malfunctions and degradation estimation based on digital signals (alarms and events) from operation SCADA , 2016 .

[26]  Zhisheng Zhang,et al.  Automatic Tonnage Monitoring for Missing Part Detection in Multi-Operation Forging Processes , 2010 .