A Method on Dynamic Kinematics in Detecting Objects and Humans for the Visually Impaired and Disabled People

Authors

  • Dr. I. Lakshmi  Assistant Professor Department of Computer Science, Stella Maris College Chennai, Tamil Nadu, India

Keywords:

Artificial Intelligence; Kinect; Xtion PRO; RANSAC; RGB-D

Abstract

The human eye is the organ of vision. This essential organ of eyesight plays a predominant role not only in life but also the human body. People who have no vision feel very difficult to detect the objects. In addition to it, there are voice messages which are attached to any device and are provided to the blind people for more convenience such that they can hear the messages in real time. There are many other technologies available where a system can detect an obstacle. KINECT is a motion sensing device which helps the end users to interact conveniently with the computer or any console by using gestures and speech. XTION PRO is another device which calculates the depth information of real time objects and humans. There are many technologies which have been implemented especially for the blind. This paper briefs about how KINECT and XTION PRO is useful for the blind in detecting objects and humans. The two main approaches are detecting objects and human beings. Depth information have been applied for detecting objects and humans. The work is focused mainly to minimize the errors, to improve accuracy and also examines how Artificial Intelligence can be helpful for the blind.

References

  1. Titus Jia Jie Tang, Wen Lik Dennis Lui and Wai Ho Li,"Plane-based detection of staircases using inverse depth", Proceedings of Australasian Conference on Robotics and Automation,3-5 Dec 2012.
  2. Soichiro Murakami, Manabu Shimakawa, Kimiyasu Kiyota, Takashi Katoc", Study on Stairs Detection using RGB-Depth Images", SCIS&ISIS, December 3-6, 2014,pp.1186-1191
  3. Hsieh-Chang Huang, Ching-Tang Hsieh and Cheng-Hsiang Yeh,"An Indoor Obstacle Detection System Using Depth Information and Region Growth", Sensors 2015, 15, pp. 27116-27141
  4. Atif Khan, Febin Moideen, Juan Lopez, Wai L. Khoo, and Zhigang Zhu, "KinDectect: Kinect Detecting Objects", ICCHP 2012,pp.588–595
  5. Xtion PRO, https://www.asus.com/3D-Sensor/Xtion_PRO/
  6. Using path planning functionality, http://www.coppeliarobotics.com/helpFiles/en/pathPlanningOperation.htm
  7. Open NI framework, https://www.heise.de/make/meldung/3D-Sensor-Framework-OpenNI-lebt-weiter-2176392.html
  8. RGB-D Object Dataset, https://rgbd-dataset.cs.washington.edu/
  9. Opencv, http://funvision.blogspot.in/2016/03/opencv-31-people-detection-at-13-fps-by.html
  10. SAPI Functions, https://msdn.microsoft.com/en-us/library/aa911241.aspx
  11. People Detection Documentation, http://wiki.ros.org/cob_people_detection https://www.cdc.gov/ncbddd/disabilityandhealth/disability-barriers.html

Downloads

Published

2018-02-28

Issue

Section

Research Articles

How to Cite

[1]
Dr. I. Lakshmi, " A Method on Dynamic Kinematics in Detecting Objects and Humans for the Visually Impaired and Disabled People, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 1, pp.471-476, January-February-2018.