Many computer vision applications need motion detection and analysis. In this research, a newly developed feature descriptor is used to find sparse motion vectors. Based on the resulting sparse motion field the camera motion is detected and analyze. Statistical analysis is performed, based on polar representation of motion vectors. Direction of motion is classified, based on the statistical analysis results. The motion field further is used for depth analysis. This proposed method is evaluated with two video sequences under image deformation: illumination change, blurring and camera movement (i.e. viewpoint change). These video sequences are captured from a moving camera (moving/driving car) with moving objects. 

 Graduate Students:

  Alok Desai

1. D. Zhang, A. Desai, and D.J. Lee, “Using Synthetic Basis Feature Descriptor for Motion Estimation,” International Journal of Advanced Robotic Systems, accepted on 09/03/18. (SCIE)
2. A. Desai, D.J. Lee, and S.H. Mody, “Automatic Motion Classification for Advanced Driver Assistance Systems,” Lecture Notes in Computer Science (LNCS), International Symposium on Visual Computing (ISVC), Part II, LNCS 9475, p. 819-829, Las Vegas, NV, U.S.A., December 14-16, 2015.