A Survey of Applications and Human Motion Recognition with Microsoft Kinect

  title={A Survey of Applications and Human Motion Recognition with Microsoft Kinect},
  author={Roanna Lun and Wenbing Zhao},
  journal={Int. J. Pattern Recognit. Artif. Intell.},
Microsoft Kinect, a low-cost motion sensing device, enables users to interact with computers or game consoles naturally through gestures and spoken commands without any other peripheral equipment. As such, it has commanded intense interests in research and development on the Kinect technology. In this paper, we present, a comprehensive survey on Kinect applications, and the latest research and development on motion recognition using data captured by the Kinect sensor. On the applications front… 

Human motion tracking & evaluation using Kinect V2 sensor

An approach to handle the problem of human body motion skeletal tracking with application in medical rehabilitation and sports training by using capabilities of the latest version of the Microsoft Kinect sensor is presented.

Hybrid Solution for Motion Capture with Kinect v2 to Different Biotypes Recognition

This work aims to create a tool which uses Kinect as a hybrid optical MOCAP system in which color markers will be positioned on the joints of interest to add extra information through colored passive markers to the standard Kinect skeleton tracking.

A concise tutorial on human motion tracking and recognition with Microsoft Kinect

  • Wenbing Zhao
  • Computer Science
    Science China Information Sciences
  • 2016
This paper provides a concise tutorial on the Microsoft Kinect technology and the state of art research on human motion tracking and recognition with Microsoft Kinect. A pre-requisite for human

Comparison of RGB and HSV Color Spaces for motion Capture and Analysis of Individuals With limb Discrepancy

This work aims to test a hybrid tool using Kinect v2 to analyze movements of individuals with dysmetria using two colorspaces - RGB and HSV to indicate the viability of using them as a tool for capturing movement of people with different biotypes.

Motion Control Gaming with Kinect

The Kinect motion-sensing device, created by Microsoft, allows users to play games by interacting with both the device and the interface without any kind of handheld controller. The motion control

Kinect-based hand gesture recognition using trajectory information, hand motion dynamics and neural networks

This study develops a new trajectory-based method for hand gesture recognition using Kinect that combines radial basis function (RBF) neural networks with dynamical estimators to find the re-occurrences of spatio-temporal patterns through pattern matching.

From Kinect skeleton data to hand gesture recognition with radar

The authors classify ten hand gestures with a set of handcrafted features using simulated mD signatures generated from Kinect skeleton data using the micro-Doppler effect to show its potential for detecting aperiodic human movements.


The Kinect v2 sensor with its great features, like face and body tracking, body gesture, and others, extends the use of virtual reality in different kinds of applications and is used to design and build a realtime VR sports training system.

Research on a Visual Sensing and Tracking System for Distance Education

Experimental results indicate that this new intelligent sensing and tracking system is capable of tracking one individual’s real-time movements with relatively high accuracy and has great potential of functioning as a basic platform where many other human-computer natural interactions can be extended.



Study on the use of Microsoft Kinect for robotics applications

The results from testing the Kinect sensor on an autonomous ground vehicle was given and it was found that this sensor is capable of taking on such a task.

Comparing gesture recognition accuracy using color and depth information

This paper proposes a method that accommodates such challenging conditions by detecting the hands using scene depth information from the Kinect using Dynamic Time Warping (DTW) and can be generalized to recognize a wider range of gestures.

Robust Part-Based Hand Gesture Recognition Using Kinect Sensor

A novel distance metric, Finger-Earth Mover's Distance (FEMD), is proposed, which only matches the finger parts while not the whole hand, it can better distinguish the hand gestures of slight differences.

Depth camera based hand gesture recognition and its applications in Human-Computer-Interaction

This paper compares the performance in terms of speed and accuracy between FEMD and traditional corresponding-based shape matching algorithm, Shape Context and demonstrates that this robust hand gesture recognition system can be a key enabler for numerous hand gesture based HCI systems.

American sign language recognition with the kinect

While the Kinect computer vision system requires more tuning for seated use, the results suggest that the Kinect may be a viable option for sign verification.

Human gesture recognition using Kinect camera

Experimental results have shown that the backpropagation neural network method outperforms other classification methods and can achieve recognition with 100% accuracy, which confirms the high potential of using the Kinect camera in human body recognition applications.

Real-time dynamic gesture recognition system based on depth perception for robot navigation

A novel start/end point detection method for segmenting the 3D hand gesture from the hand motion trajectory is proposed and Hidden Markov Models are implemented to model and classify the hand gesture sequences and the recognized gestures are converted to control commands for the interaction with the robot.

Microsoft Kinect Sensor and Its Effect

While the Kinect sensor incorporates several advanced sensing hardware, this article focuses on the vision aspect of the sensor and its impact beyond the gaming industry.

Hand gesture recognition using color and depth images enhanced with hand angular pose data

  • Pedro TrindadeJ. LoboJ. Barreto
  • Computer Science
    2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
  • 2012
This work proposes to add a tiny pose sensor to the human palm, with a minute accelerometer and magnetometer that combined provide 3D angular pose, to reduce the search space and have a robust and computationally light recognition method.

Simultaneous categorical and spatio-temporal 3D gestures using Kinect

A novel gesture recognition technique for skeletal input data that simultaneously allows for categorical and spatio-temporal gestures and can learn gestures that are most appropriate for the user from examples is proposed.