Face detection and tracking with an active camera

Petrov, Plamen; Boumbarov, Ognian; Muratovski, Krasimir

doi:10.1109/is.2008.4670528

Cited by 14 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean shift procedure (Meer 2003) was adopted in Everts, Sebe, and Jones (2007) for successfully tracking objects from PTZ cameras. Other researchers give examples of face rather than object tracking with active cameras (Comaniciu and Ramesh 2000;Petrov, Boumbarov, and Muratovski 2008).…”

Section: Related Workmentioning

confidence: 99%

A practical approach for active camera coordination based on a fusion-driven multi-agent system

Bustamante

2013

International Journal of Systems Science

View full text Add to dashboard Cite

Abstract:In this paper, we propose a multi-agent system architecture to manage spatially distributed active (or pan-tilt-zoom) cameras. Traditional video surveillance algorithms are of no use for active cameras, and we have to look at different approaches. Such multi-sensor surveillance systems have to be designed to solve two related problems: data fusion and coordinated sensor-task management. Generally, architectures proposed for the coordinated operation of multiple cameras are based on the centralisation of management decisions at the fusion centre. However, the existence of intelligent sensors capable of decision making brings with it the possibility of conceiving alternative decentralised architectures. This problem is approached by means of a MAS, integrating data fusion as an integral part of the architecture for distributed coordination purposes. This paper presents the MAS architecture and system agents.

show abstract

Section: Related Workmentioning

confidence: 99%

A practical approach for active camera coordination based on a fusion-driven multi-agent system

Bustamante

2013

International Journal of Systems Science

View full text Add to dashboard Cite

show abstract

“…Traditional monocular tracking methods mainly explore the temporal correlation in one video to detect moving areas [1][2][3][4]. With the development of the 3D signal processing technologies, multiview video object tracking is gaining increasing interest.…”

Section: Introductionmentioning

confidence: 99%

“…In this kind of system, the camera control algorithm for the tracking process needs to estimate the angular speed/acceleration of the moving object, and the background alignment in different video frames is required for motion detection. In the PTU camera tracking algorithm proposed by Petrov et al [4], a linear feedback controller is applied based on the Theory of Lyapunov Stability. The control parameters are updated by object position estimated using the MeanShift [1] algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…To enable tracking in an unmanned environment, we use a PTU device (Directed Perception D47) to perform camera control. The master camera is able to rotate and its projection center stays unchanged [4]. A slave camera is placed on the flank, and moves along with the master camera, as shown in Figure 1(a).…”

Section: Introductionmentioning

confidence: 99%

“…The estimated disparity values from the stereoscopic image pair are used to adjust the size of the tracking region. The object center is detected using the MeanShift algorithm, and it is provided for PTU control [4] on the master camera.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Binocular video object tracking with fast disparity estimation

Liu

et al. 2013

2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance

View full text Add to dashboard Cite

This paper presents a binocular PTU (pan-tilt unit) camera video object tracking scheme using the MeanShift algorithm and the runtime disparity estimation. The proposed method is to accommodate the requirement of 3D content generation and accurate tracking in more advanced video surveillance applications. The disparity estimation process for each stereoscopic pair is formulated as an energy minimization problem. The iterative solution procedure is implemented in a course-to-fine manner. The estimated disparity is used to scale the tracking window by the MeanShift algorithm, i.e. the size of the tracking area is adjustable according to its inner disparity, and thus the moving object can be better located by the camera. The program maintains the semi-real-time performance and acceptable accuracy as evaluated on a set of standard test data. In our experiment, two PointGrey cameras are controlled through a PTU device. The disparity estimation process on the recorded tracking video (640x480) achieves 6fps on an ordinary PC (2.66GHz CPU, 4GB RAM).

show abstract

Energy Efficient Target Tracking Mechanism using Rotational Camera Sensor in WMSN

Gupta

Sen

2012

Procedia Technology

View full text Add to dashboard Cite

Face detection and tracking with an active camera

Cited by 14 publications

References 9 publications

A practical approach for active camera coordination based on a fusion-driven multi-agent system

A practical approach for active camera coordination based on a fusion-driven multi-agent system

Binocular video object tracking with fast disparity estimation

Energy Efficient Target Tracking Mechanism using Rotational Camera Sensor in WMSN

Contact Info

Product

Resources

About