Using Lucas-Kanade Algorithms to Measure Human Movement
As an important part of clinical studies, Motion estimation knowledge is widely used to gather useful movement information for medical professionals to find out the best treatment for chronic pain. The purpose of this project is to develop a program to analyze patients’ movements and therefore to improve the treatment of patients. Initially, the basic Luca-Kanade algorithm was implemented. And this program was primarily improved upon by setting a threshold to decrease the noise, and then by selecting feature points to process. Additionally, the resizing method was adopted to further improve the whole system. The solution successfully meets the project aims as the system performs much better than the original one with higher accuracy and speed, while the motion trail can be represented clearly by multiple optical flow fields and the useful information can be detected from the video through all the improved implementations.
KeywordsMotion estimation Lucas-Kanade Edge detector Optical flow field
- Alex, D.S., Wahi, A.: BSFD Background subtraction frame difference algorithm for moving object detection and extraction. J. Theor. Appl. Inf. Technol. 60(3), 623–628 (2014)Google Scholar
- Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital image processing using MATLAB. Dorling Kindersley Pvt, India (2006)Google Scholar
- Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI, pp. 674–679 (1981)Google Scholar
- Singla, N.: Motion detection based on frame difference method. Int. J. Inf. Comput. Technol. 4(0974–2239), 1559–1565 (2014)Google Scholar