Extrinsic Calibration of Multiple Azure Kinect Cameras

Azure Kinect has been released for over a year now and there are a lot of applications and researches utilizing this RGBD sensor to do amazing things. The benefits of using multiple sensors are well-explained by Microsoft here. Basically, live 3D reconstructions of a much larger scene, Tele-presence (which also is a seminar course at Continue reading Extrinsic Calibration of Multiple Azure Kinect Cameras

Install Azure Kinect SDK on Ubuntu 16.04

Note: The current SDK version when I started this post is 1.3.0. Currently, the only supported Linux distribution for is Ubuntu 18.04 and due to reasons like some existing projects are built on Ubuntu 16.04 etc.,  it would be nice to have support on these older projects. This post documented what I did to make Continue reading Install Azure Kinect SDK on Ubuntu 16.04

Experiments with HoloLens (1st Gen) Research Mode

As it is explained by Microsoft, “Research Mode is a capability of HoloLens that provides application access to the key sensors on the device.” It becomes interesting that what if we can directly get point clouds from its depth sensor? So I did several experiments with it. Visualization Basically, Microsoft let developers get access to Continue reading Experiments with HoloLens (1st Gen) Research Mode

Implementing the Perceptron algorithm from scratch with Python

Introduction Perceptron is a fundamental algorithm for binary classification in Machine Learning. The perceptron is a mistake-driven online learning algorithm. It is often said that the perceptron is modeled after neurons in the brain. It has m input values (which correspond with the features of the examples in the training set) and one output value. Continue reading Implementing the Perceptron algorithm from scratch with Python

UR5 Robot Arm Manipulation

Project Goal The objective of this project is to use the UR5 robot to perform the classic pick-and-place operation automatically. I will implement a program that allows me to first “teach” the UR5 the position of the start and target locations and then automatically completes the pick-and-place operation using a gripper and several different types Continue reading UR5 Robot Arm Manipulation

3D Reconstructions From Multiple Images Using SFM

  Introduction 3D reconstruction is a process of capturing the 3D geometrical structures of objects shown in 2D images, which is to determine the 3D locations of the points on the object profiles. 3D reconstruction is the core technology of various fields, including computer animation, computer-aided geometric design, medical imaging, virtual reality(VR) and augmented reality(AR), Continue reading 3D Reconstructions From Multiple Images Using SFM

Pytorch Implementation​: Siamese Network

Project Goal This project uses the Labeled Faces in the Wild (LFW) dataset, and the goal is to train variants of deep architectures to learn when a pair of images of faces is the same person or not. It is a Pytorch implementation of Siamese network with 19 layers. Method Consider a Convolutional Neural Network Continue reading Pytorch Implementation​: Siamese Network