A Robust Real-Time Embedded Vision System on an Unmanned Rotorcraft for Ground Target Following

Lin, Feng; Dong, Xiangxu; Chen, Ben M.; Lum, Kai‐Yew; Lee, T. H.

doi:10.1109/tie.2011.2161248

Cited by 103 publications

(31 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 9 shows the proposed tracking agent mode of functioning. • Once the target is initialized, in the model-based image tracking, a Kalman filtering technique tries to predict the position and velocity of the target in the subsequent frames and then perform data association based on an updated likelihood function [19].…”

Section: Target Initialization Agentmentioning

confidence: 99%

A Multi-Task Distributed Vision System Embedded on a Hex-Rotorcraft UAV

Nadir¹,

Boukhdir²,

Moutaouakkil³

et al. 2016

ijacsa

View full text Add to dashboard Cite

Abstract-In this paper, are presented the general architecture and implementation of a multi-task distributed vision system designed and embedded onboard a Hex-Rotorcraft UAV. The system uses multiple cheap heterogeneous cameras in order to perform various tasks such as: ground target pedestrian detection, tracking, creating panoramic images, video stabilization and streaming multiple data/video feeds over a wireless secure channel. In what follows, are discussed this multiagent architecture designed to provide our UAV with an embedded intelligent vision system using autonomous agents entrusted with managing the previously listed functionalities. In addition to the cheap set of USB and module cameras, the presented vision system is composed of a Local Data Processing Module connected to each camera and a Central Module used to control the overall system, process the regrouped data and streams it to the ground station. The overall vision system has been tested in real flights and is still under improvements.

show abstract

Section: Target Initialization Agentmentioning

confidence: 99%

A Multi-Task Distributed Vision System Embedded on a Hex-Rotorcraft UAV

Nadir¹,

Boukhdir²,

Moutaouakkil³

et al. 2016

ijacsa

View full text Add to dashboard Cite

show abstract

“…When retrieved, the users in the system with the help of its own constitution by selecting an image to be retrieved or describe the color ratio, object shape, texture, or select the example of figure. Retrieval system using the same method to treat 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016) retrieved image feature analysis, retrieval feature type, feature indexing and retrieval library, indexed and retrieval those features characteristics sufficient formula with similar images retrieved [7,8]. General search result was thumbnails, image URL or form URL of the page containing the image information appears.…”

Section: The Key Target Detection Technology Based On Invariant Featurementioning

confidence: 99%

Design and Implementation of Small Target Detection System based on Invariant Feature

Bai¹,

Tian²,

Sun³

2016

Proceedings of the 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016)

View full text Add to dashboard Cite

Abstract. In our study, computer graphics are discussed and they are collected by the image sensor with an analog electrical signal. During acquisition of image, 3D space is relative to the camera system of different viewpoints with the same goals, it will cause the target respect to the change in orientation of imaging system and attitude, which will change the target in the imaging system. Images showed the same target image. Change the viewpoint to target in 3D space, which relative to the movement of the imaging system, such as change of the target rotation, translation and scale. We need to find or construct some sort of goal in order to make the motion or the target image features do not change. Such features and feature amounts are called invariance, and invariants. It is invariance only reflect the same characteristics or the same type of target, or that the nature with differences between different modes in the visual information. Because they are in 3D space with the target location, attitude and independent according to people who are easy to find the right target.

show abstract

“…[7] Lin [8] Watanabe [9] Choi [10] [11] Cheng [5] Zhao [12] [13] [14] [15] [14] [16] [17] [ 18] meanshift [19] [20] [6][7] [8] Proceedings of the 33rd Chinese Control Conference July 28-30, 2014, Nanjing, China …”

Section: [1] [2]mentioning

confidence: 99%

Design and implementation of a visual tracking system for small-scale unmanned helicopters

Wang

et al. 2014

Proceedings of the 33rd Chinese Control Conference

View full text Add to dashboard Cite

A visual tracking system for unmanned helicopters is introduced in this paper. The target is identified based on the identification methods of statistical analyses of color pieces and tracked based on the color histogram meanshift method. A visual tracking controller is designed for the ground target tracking. This controller contains a nonlinear controller and a linear controller. Experimental results show that the visual tracking system is stable and reliable even when the target is performing a certain extent maneuver. 1 [1] [2] [3] [4] [5] Mejias [6] Garcia-Pardo * 61203071 61374034. [7] Lin [8] Watanabe [9] Choi [10] [11] Cheng [5] Zhao [12] [13] [14] [15] [14] [16] [17] [18] meanshift [19][20] [6][7][8]

show abstract

A Robust Real-Time Embedded Vision System on an Unmanned Rotorcraft for Ground Target Following

Cited by 103 publications

References 34 publications

A Multi-Task Distributed Vision System Embedded on a Hex-Rotorcraft UAV

A Multi-Task Distributed Vision System Embedded on a Hex-Rotorcraft UAV

Design and Implementation of Small Target Detection System based on Invariant Feature

Design and implementation of a visual tracking system for small-scale unmanned helicopters

Contact Info

Product

Resources

About