Avi Singh writes about computer vision, deep learning, and robotics, with hands-on tutorials and research-driven insights. His work covers visual odometry, activity recognition, neural networks, and practical implementations using OpenCV, CUDA, and MATLAB.
10 articles from this blog
A developer revives their blog to improve thinking through public writing, planning posts on research, career, and technical topics.
Explores Visual Question Answering (VQA) as an alternative Turing Test, detailing neural network approaches using Python and Keras.
A technical guide to implementing Monocular Visual Odometry using OpenCV and C++, covering feature detection, motion estimation, and algorithm details.
A technical walkthrough of implementing a human activity recognition system using Kinect's skeletal joint data and machine learning.
A guide to choosing temporal models like HMMs, MEMMs, and CRFs for sequence classification in a human activity recognition project using Kinect data.
A beginner-friendly tutorial on implementing Visual Odometry for robotics, focusing on a stereo vision approach based on a classic research paper.
Explores algorithms for segmenting individual teeth from dental images, comparing Active Contours and Watershed transforms.
Explores using ASIFT algorithm to stitch close-range intra-oral dental images for a complete jaw view, overcoming perspective challenges.
A student's curated reading list for learning Visual Odometry, including tutorials and key papers on algorithms like the 5-point and 8-point methods.
An explanation of the RANSAC algorithm for outlier rejection, used in computer vision and data modeling.
