A novel robust algorithm for position and orientation detection based on cascaded deep neural network

Abstract Estimating position and orientation of the object by using machine vision is essential in industrial automation. The traditional canny operator and Hough transform edge detection algorithm is widely used, but its accuracy and real-time object recognition in complex backgrounds are very limited. Other algorithms such as SVM and BP network are usually inaccurate for regression issues. In this paper, the method of a cascade of convolution networks is proposed which results in high precision pose estimates. SSD is utilized to obtain the bounding box of the object to narrow down the recognition range. Convolution neural network is utilized to detect the orientation of the object. This method can extract weak features of the sample image. In generally, the proposed method possess a greatly improved accuracy and recognition rate compared with the traditional algorithm.

[1]  Shahrel Azmin Suandi,et al.  Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut , 2017, Digit. Signal Process..

[2]  Xiang-Gen Xia,et al.  Detection, location, and imaging of fast moving targets using multifrequency antenna array SAR , 2000, SPIE Defense + Commercial Sensing.

[3]  Jun Hu,et al.  Quantised recursive filtering for a class of nonlinear systems with multiplicative noises and missing measurements , 2013, Int. J. Control.

[4]  Daniel Gutierrez-Galan,et al.  Embedded neural network for real-time animal behavior classification , 2018, Neurocomputing.

[5]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[6]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[7]  Jun Hu,et al.  A variance-constrained approach to recursive state estimation for time-varying complex networks with missing measurements , 2016, Autom..

[8]  Wang Guo-rong.  A Stereovision Method for Resuming the Position and Pose of Symmetry Revolution Object , 2005 .

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  Fuad E. Alsaadi,et al.  Event-based filtering for time-varying nonlinear systems subject to multiple missing measurements with uncertain missing probabilities , 2017, Inf. Fusion.

[11]  Loren W. Nolte,et al.  Bayes optimum array detection of targets of known location , 1975 .

[12]  Zhiyu Zhou,et al.  Object detection and tracking based on adaptive canny operator and GM(1,1) model , 2007, 2007 IEEE International Conference on Grey Systems and Intelligent Services.

[13]  Madjid Tavana,et al.  An Artificial Neural Network and Bayesian Network model for liquidity risk assessment in banking , 2018, Neurocomputing.

[14]  Yun Jiang,et al.  Improved HT Object Detection Algorithm Based on Canny Edge Operator , 2014, J. Multim..

[15]  Gongjian Wen,et al.  A deep neural network for real-time detection of falling humans in naturally occurring scenes , 2017, Neurocomputing.

[16]  Gang Hua,et al.  A convolutional neural network cascade for face detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Gajendra P. S. Raghava,et al.  ESLpred: SVM-based method for subcellular localization of eukaryotic proteins using dipeptide composition and PSI-BLAST , 2004, Nucleic Acids Res..

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[20]  Ning Xi,et al.  Dual-arm robot assembly system for 3C product based on vision guidance , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[21]  Luc Van Gool,et al.  Hough Forests for Object Detection, Tracking, and Action Recognition , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[23]  Xizhao Wang,et al.  A review on neural networks with random weights , 2018, Neurocomputing.

[24]  Zhan Li,et al.  Valid data based normalized cross-correlation (VDNCC) for topography identification , 2018, Neurocomputing.

[25]  Ying Zhang,et al.  License plate character recognition algorithm based on filled function method training bp neural network , 2008, 2008 Chinese Control and Decision Conference.