Maximally Stable Extremal Regions Improved Tracking Algorithm Based on Depth Image

In order to solve the problem that traditional Camshift algorithm can easily fail to track overlapping targets and multiple similar depth targets, a new improved maximally stable extremal regions (MSER) algorithm is presented in this paper. Firstly, the suspected target contour is extracted and similarity analysis is performed. Secondly, the improved MSER algorithm is used to confirm the target contour and update the similarity library. Finally, combined with the physical properties unique to the depth image and based on the Kalman filter, it is possible to predict the tracking target’s moving position. The experimental results show that the real-time performance and recognition rate are improved, and robustness to the situation of target overlap and occlusion is better with the improved MSER algorithm.

[1]  Liu Jin,et al.  An Adaptive Algorithm for Grey Image Edge Detection Based on Grey Correlation Analysis , 2016, 2016 12th International Conference on Computational Intelligence and Security (CIS).

[2]  J. Paul Siebert,et al.  Local feature extraction and matching on range images: 2.5D SIFT , 2009, Comput. Vis. Image Underst..

[3]  Kalpana C. Jondhale,et al.  Shape matching and object recognition using shape contexts , 2010 .

[4]  Amirmasoud Hamedi,et al.  Asphalt Mixture Segregation Detection: Digital Image Processing Approach , 2017 .

[5]  Robert Sitnik,et al.  New method of structure light measurement system calibration based on adaptive and effective evaluation of 3D-phase distribution , 2005, SPIE Optical Metrology.

[6]  Luigi di Stefano,et al.  People Tracking Using a Time-of-Flight Depth Sensor , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[7]  Owen L. Astrachan,et al.  Bubble sort: an archaeological algorithmic analysis , 2003, SIGCSE.

[8]  George K. I. Mann,et al.  Developing a Cubature Multi-state Constraint Kalman Filter for Visual-Inertial Navigation System , 2017, 2017 14th Conference on Computer and Robot Vision (CRV).

[9]  Andrew Blake,et al.  Efficient Human Pose Estimation from Single Depth Images , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Horst Bischof,et al.  Efficient Maximally Stable Extremal Region (MSER) Tracking , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Marek Biskup,et al.  Eigenvalue vs perimeter in a shape theorem for self-interacting random walks , 2016, 1603.03817.

[12]  Dmitry Chetverikov,et al.  Novel methods for image-guided ToF depth upsampling , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[13]  Changming Sun.  A Fast Stereo Matching Method , 1997 .