I did some work.

Others: Motion Planning: TrajOpt, RRT and Variants, RealTime RRT*; Image Segmentation with GMM, Image De- noising using MRF;

Video Action recognition using Deep Learning

  • Implemented a Bi-Directional LSTM Model on VGG16 Net using Keras to classify actions in scenes.
  • Achieved a Mean Average Precision of 15.7 mAP compared to the State of the Art of 21.4 mAP.