Important Method for Detecting and Tracking Based on Color
Zainab Oufqir1, Abdellatif El Abderrahmani2, Khalid Satori3
1Zainab OUFQIR, PhD Student, Department of Mathematics and informatic, Dhar-Mahraz, Morocco.
2Abdullatif EL ABDERRAHMANI, Professor, Department of computer science Larache Poly disciplinary School LARACHE, Morocco.
3Khalid SATORI, Professor, Department of Mathematics and informatic, Dhar-Mahraz, Morocco.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 688-692 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7203068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Our work presents a new robust approach that detects an object based on its color in a real 3D scene and in real time, this detected object will be augmented by additional information and its position in the scene will allow us to calculate the camera pose in order to correctly align the virtual object in the real world. The calculation of the camera position is the most studied problem in augmented reality, the solution of this problem is to provide the position of four 3D points in a real-world reference and their 2D position of their projection in the image sequence acquired in real time. For good detection, the color mode conversion of the scene from RGB to HSV allows multiple colors to be extracted and this color space is less sensitive to shadows and variance of brightness. A rectangle is automatically drawn around the detected object and surrounds the minimum surface area of its contour, this rectangle expresses the location of the detected object in the scene and the position of the four corners of this rectangle will allow us to follow the object in the scene so we can estimate the position of the camera. The result shows the quality, simplicity and speed of our approach compared to the methods mentioned in the related work section.
Keywords: Augmented Reality, Color, Object Detection, Real Time
Scope of the Article: Real-Time Information Systems