How to Register and Align Features in a Video with MATLAB

 Computer Vision Toolbox is used to perform image registration to stabilize a video captured during a surgical procedure using an endoscopic near-infrared fluorescence imaging system. To do so, tracked points are used to compute a transformation to warp the current frame such that features remain aligned with the initial frame. 

With each video frame aligned to the same reference frame, the mean intensity of a grid of regions can then be quickly computed using distinct block processing of the warped intensity frame. In this way, computer vision is helping surgeons automate data collection to research if changes in the fluorescence intensity time histories can be used to discriminate normal tissue from cancerous tissue.

Related Resources: 

- Computer Vision Onramp: https://bit.ly/3HpoDkp

- Image Registration: https://bit.ly/43N8f7d

- Fluorescence Tracker App: https://bit.ly/3ve1Seh

- “How To” Video Series for Biomedical and Pharmaceutical Applications: https://bit.ly/43O2pT4