We help the deaf and the dumb to communicate with normal people using hand gesture to speech conversion. In this code we use depth maps from the kinect camera and techniques like convex hull + contour mapping to recognise 5 hand signs

Object detection from images/point cloud using ROS

A virtual fitting room using Kinect v2 with gesture controlled GUI. The project aims to map any cloth images downloaded from the internet on a person standing in front of the Kinect Sensor

improve performance of skeleton data from kinect v2 body tracking sdk using unscented kalman filter

A Python API for interfacing with the Kinect2.

Use of naoqi APIs to teleoperate Pepper robot in real-time using Openpose estimated skeleton data + kinect v2 depth info

Multispectral Processing is an implementation in ROS Melodic for Multi-modal Data Processing and Implementation for Vineyard Analysis.

contains snippets/tools for processing pointclouds from depth camera

A project which makes use of Microsoft Kinect, to build 3D map. Simultaneously, detect the switch board in the surrounding.

Work for detecting group interactions with social cues with depth cameras.

A Python wrapper for the kinect built on pylibfreenect2.

Multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences

Captura de imágenes y nubes de puntos con el dispositivo kinect2 (kinect one) usando la librería freenect2

Human Robot Interaction

An Image Segmenting based power adjusting system for a Ring shooter system designed for RoboCon 2023

Data science project which inspects possible useful properties of motion-captured skateboarder performing so called "Ollie". Data is gathered using Kinect v2 body+floor frames.

Term project for course 24-354 Gadgetry: Sensors, Actuators, and Processors at Carnegine Mellon University

Dataset for patch-based person classification (person vs. non-person objects) and posture classification (standing vs. sitting vs. squatting). The data was recorded using a Kinect2 sensor and consists of labeled depth image patches of 27 persons in various postures and of various non-person objects. In total, the dataset consists of more than 23…

This is a project where in an autonomous robot is built which makes use of the 3D mapping technique to map the entire environment and finally is able to navigate autonomously toward the detected switch board. This project was developed with the basic idea of making the robot to be able to navigate toward the switch board whenever it needs to be …