JacobChen1998/Feature-tracking-with-PCA

Traditional feature tracking techniques such as SIFT, SURF, and Lucas Kanade algorithms define key points in terms of finding poles and cannot specify specific tracking points. The general Deep Learning based tracking algorithms such as Siamese tracker require a lot of resources for neural network training. Here, we implement feature tracking using PCA. Our algorithm can specify tracking points and does not require extensive training.

Python