In this paper, we have addressed the problem of real-time detection and tracking of dynamic objects using quadrotors. We have developed a novel object detection algorithm by analyzing and matching the color and spacial features of the target from monocular image sequences. The proposed object detection algorithm can track the objects with high Frame Per Second (FPS) which is suitable for low-end onboard computers that are used in quad-rotors. In addition, we also estimate the position of the target object in real world so that the drone can track the object accurately. A rigorous experimental analysis is provided to show the efficacy of the proposed approach in indoor as well as outdoor environments.
Gaussian Mixture Model (GMM) Based Dynamic Object Detection and Tracking
2019-06-01
1900901 byte
Conference paper
Electronic Resource
English
Video Object Segmentation Based on Gaussian Mixture Model
British Library Online Contents | 2006
|Driver face tracking using Gaussian mixture model(GMM)
Tema Archive | 2003
|Gaussian Mixture PHD Filter for Space Object Tracking (AAS 13-242)
British Library Conference Proceedings | 2013
|