Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
Abstract: Aiming at the problem of poor detection and recognition effect and low accuracy due to complex detection environment, high similarity of instrument panels, multiple category classification and other interference in industrial scenes, an automatic instrument recognition method based on improved faster regional convolutional neural network (Faster RCNN) was proposed. Firstly, the residual network (Resnet) 101 was used to replace the visual geometry group network (VGG) 16 for network structure simplification. Then, the feature pyramid network (FPN) was introduced and further improved into a recursive feature pyramid network for iterative fusion, and the feature map was output. Then, the attention mechanism was introduced to realize the weight of the output channel and reassign it according to the degree of importance to enhance the model-s computation of the target. A softer non-maximum suppression(softer-NMS) algorithm was introduced to determine the accurate target candidate box by reducing the confidence degree. Finally, Mosaic data enhancement technology was used to expand the visual object classes(VOC)2007 data set, and the improved Faster-RCNN model was used to carry out the instrument automatic recognition experiment. The results show that, in the same industrial environment, comparing with the traditional Faster RCNN algorithm model, the accuracy rate of the improved Faster-RCNN model is 93.5%, which is 3.8% higher than that of the original model, and the mAP value is 92.6%, which is 3.7% higher than that of the original model. It can be seen that this method has good robustness and generalization ability in actual production, and can meet the requirements of intelligent detection in the industry.
Key words: instrument identification; faster regional convolutional neural network(Faster RCNN); recursive feature pyramid network; attention mechanism; softer nonmaximum suppression(softer-NMS); Mosaic data enhancement technology
-
- Chinese Core Periodicals
-
- Chinese Sci-tech Core Periodicals
-
- SA, INSPEC Indexed
-
- CSA: T Indexed
-
- UPD:Indexed
-
2010 Zhejiang Information Institute of Mechinery Industry
Technical Support：Hangzhou Bory science and technology
