[1] C ALDRICH, C MARAIS, B J SHEAN, et al. Online monitoringand control of froth flotation systems with machine vision: a review. International Journal of Mineral Processing, 96, 1-13(2010).

[4] [4] LI Shengli . Research on wkpiece recongnition loction technology based on binocular stereo vision[D]. Harbin: Harbin Institute of Technology, 2016.

[5] A RUTA, Y LI, X LIU. Real-time traffic sign recognitionfrom video by class-specific discriminative features. Pattern Recognition, 43, 416-430(2010).

[6] J F KHAN, S M A BHUIYAN, R R ADHAMI. Image seg-mentation and shape analysis for road-sign detection. IEEE Transactions on Intelligent Transportation Systems, 12, 83-96(2010).

[7] [7] HUANG Shan. Research on robot arm sting system based on machine vision[D]. Zhenjiang: Jiangsu University of Science Technology, 2016.

[8] N OTSU. A threshold selection method from gray-level histograms. Automatica, 11, 23-27(1975).

[9] G E HINTON, S OSINDERO, Y W THE. A fast learning algorithm for deep belief nets. Neural Computation, 18, 1527-1554(2006).

[10] A KRIZHEVSKY, I SUTSKEVER, G E HINTON. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60, 84-90(2017).

[11] [11] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies f accurate object detection semantic segmentation[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition. New Yk: IEEE, 2014: 580587.

[12] [12] GIRSHICK R. Faster RCNN[C]2015 IEEE International Conference on Computer Vision(ICCV). New Yk: IEEE, 2015: 14401448.

[13] S Q REN, K M HE, R GIRSHICK, et al. Faster RCNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149(2017).

[14] J R R UIJLINGS, DE SANDE K E A VAN, A W M SMEULDERS, et al. Selective search for object recongnition. International Journal of Computer Vision, 104, 54-171(2013).

[15] [15] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learing f image recongnition[C]2016 IEEE Conference on Computer Vision Pattern Recongnition(CVPR). New Yk: IEEE, 2016: 770778.