Object Tracking and Recognition Based on Reliability Assessment of Learning in Mobile Environments

This paper proposes a novel object tracking and recognition system according to reliability assessment of learning in mobile environments. The proposed method is based on marker-less tracking, and the proposed system is composed of two main modules (detection and tracking). The detection module identifies an object to be matched on the current frame corresponding to the database, and then generates the standard object information that has the best reliability of learning. This module is able to re-detect the object when the object is missing in the frame. The tracking module traces the object of interest based on the extracted object information using feature points, descriptors, sub-window of object, and its histogram. Additionally, this module tries to select the reliable object between tracked object by Camshift and tracked object by Optical flow. Experimental results show that the proposed method is more robust than the traditional methods, and that it is able to recognize and track objects of interest with reliability assessment of learning for use with mobile environments.

[1]  Alexandre R. J. François,et al.  CAMSHIFT Tracker Design Experiments With Intel OpenCV and SAI , 2004 .

[2]  Martin Kampel,et al.  Interest Point Based Tracking , 2010, 2010 20th International Conference on Pattern Recognition.

[3]  Tieniu Tan,et al.  A real-time object detecting and tracking system for outdoor night surveillance , 2008, Pattern Recognit..

[4]  Ming-Hsuan Yang,et al.  Incremental Learning for Robust Visual Tracking , 2008, International Journal of Computer Vision.

[5]  Shai Avidan,et al.  Locally Orderless Tracking , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Ming-Hsuan Yang,et al.  Robust Object Tracking with Online Multiple Instance Learning , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Xuejie Zhang,et al.  Tracking objects through occlusions using improved Kalman filter , 2010, 2010 2nd International Conference on Advanced Computer Control.

[8]  Alfredo Petrosino,et al.  The Matrioska Tracking Algorithm on LTDT2014 Dataset , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Piotr Indyk,et al.  Approximate Nearest Neighbor: Towards Removing the Curse of Dimensionality , 2012, Theory Comput..

[10]  S. Govindarajulu,et al.  A Comparison of SIFT, PCA-SIFT and SURF , 2012 .

[11]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Yong-Ho Moon,et al.  Multiple Object Tracking Using SIFT Features and Location Matching , 2011 .

[13]  Zhiyu Zhou,et al.  Object Tracking Based on Camshift with Multi-feature Fusion , 2014, J. Softw..

[14]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[15]  Kehua Miao,et al.  An improved algorithm for locality-sensitive hashing , 2015, 2015 10th International Conference on Computer Science & Education (ICCSE).

[16]  Ehud Rivlin,et al.  Mean Shift tracking with multiple reference color histograms , 2010, Comput. Vis. Image Underst..

[17]  Matthew A. Brown,et al.  Invariant Features from Interest Point Groups , 2002, BMVC.

[18]  Luo Juan,et al.  A comparison of SIFT, PCA-SIFT and SURF , 2009 .

[19]  Otthein Herzog,et al.  Binarising SIFT-Descriptors to Reduce the Curse of Dimensionality in Histogram-Based Object Recognition , 2009, FGIT-SIP.

[20]  Jing Li,et al.  Robot robust object recognition based on fast SURF feature matching , 2013, 2013 Chinese Automation Congress.

[21]  Zhang Huijuan,et al.  Fast image matching based-on improved SURF algorithm , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).