AI-Based Drone Object Tracking System: Design and Implementation 


Vol. 42,  No. 12, pp. 2391-2401, Dec.  2017
10.7840/kics.2017.42.12.2391


PDF Full-Text
  Abstract

We present an object tracking system utilizing artificial intelligence on Unmanned Aerial Vehicles (drones). Such a tracking mission requires that (i) the target be correctly detected from the visual data obtained from the camera and (ii) the drone be controlled accordingly to keep track of the target. In light of these requirements, we make use of a neural network-based AI algorithm for object detection and a reinforcement learning-based algorithm for robust and energy-efficient drone control in the tracking of objects following irregular, arbitrary paths. In addition, the need to deliver user commands to the drones and to obtain tracking results from them has led to our development of a GCS (Ground Control Station) and the networking between the drones and the GCS. We believe that all the aforementioned tasks call for the design and implementation of a comprehensive platform, providing basic functionalities including networking, AI job processing, drone control with reinforcement learning, and expandability to different brands and types of drones. This paper thus (i) defines the specific requirements of such a platform, (ii) introduces an AI-based object tracking platform built on the said specifics, and (iii) verifies the platform functionalities with field experiments and simulations.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

D. Kim, W. J. Kang, Y. Koo, J. Bang, K. Son, D. Hostallero, S. Yoon, H. Yeo, J. Ha, N. Seo, D. Han, Y. Yi, "AI-Based Drone Object Tracking System: Design and Implementation," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 12, pp. 2391-2401, 2017. DOI: 10.7840/kics.2017.42.12.2391.

[ACM Style]

Daewoo Kim, Wan Ju Kang, Yoon-pyo Koo, Jihwan Bang, Kyung-hwan Son, David Hostallero, Se-eun Yoon, Hyun-ho Yeo, Jae-hyeong Ha, Nansol Seo, Dongsu Han, and Yung Yi. 2017. AI-Based Drone Object Tracking System: Design and Implementation. The Journal of Korean Institute of Communications and Information Sciences, 42, 12, (2017), 2391-2401. DOI: 10.7840/kics.2017.42.12.2391.

[KICS Style]

Daewoo Kim, Wan Ju Kang, Yoon-pyo Koo, Jihwan Bang, Kyung-hwan Son, David Hostallero, Se-eun Yoon, Hyun-ho Yeo, Jae-hyeong Ha, Nansol Seo, Dongsu Han, Yung Yi, "AI-Based Drone Object Tracking System: Design and Implementation," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 12, pp. 2391-2401, 12. 2017. (https://doi.org/10.7840/kics.2017.42.12.2391)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880