Welcome to my page.
I design and implement computer vision systems. My interests are in applying machine learning to computer vision, 3D mapping/tracking and robotic perception.
I work at Trifo Inc. where we develop robotics for home.
Drop me an email at: krishnasamy <dot> prasanna <at> gmail <dot> com
At Apple, I implemented event detection algorithms on images. I also performed a lot of analyses on the time series' and implemented 3D algorithms on pointclouds.
At Arraiy. I worked on making visual content creation easier for artists using the latest in computer vision and deep learning. I worked on solutions for matting foregrounds using deep learning and geometry. Arraiy was acquired by Matterport.
I worked for Magicleap Inc. as a computer vision engineer which was a whole lot of fun. There I worked on hand recognition, deep learning for gestures, depth cameras, object tracking, multiple camera pose and calibration. These were features that enabled mixed-reality experiences.
Prior to that, I was at Amazon Lab126 on their emerging technologies team. Here I worked on object tracking, machine learning for gesture recognition, and 3D plane finding.
OpenCV 2014 – 2017
Google Summer of Code Mentor
Mentored summer interns for software contributions into OpenCV (http://opencv.org/)
2014 - Dense Optical Flow Estimation - Deep Flow
2015 - Charuco AR markers (http://docs.opencv.org/master/d9/d6d/tutorial_table_of_content_aruco.html#gsc.tab=0)
2017 - End-to-End deep textboxes converted from caffe to OpenCV DNN (https://docs.opencv.org/trunk/d1/d66/classcv_1_1text_1_1TextDetectorCNN.html)