Tracking multiple people with recovery from partial and total occlusion

Lerdsudwichai, Charay; Abdel-Mottaleb, Mohamed; Ansari, A-Nasser

doi:10.1016/j.patcog.2004.11.022

Cited by 30 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same applies to related approaches studied in Sidenbladh et al (2000) or more recently, e.g., in Ning et al (2004), Pai et al (2004), Yam et al (2004), Lerdsudwichai et al (2005), and Kang and Kim (2005).…”

Section: Tracking Of Non-rigid Bodymentioning

confidence: 87%

A Framework for Model-Based Tracking Experiments in Image Sequences

Dahlkamp

Nagel

Ottlik

et al. 2006

Int J Comput Vision

View full text Add to dashboard Cite

Motris, an integrated system for model-based tracking research, has been designed modularly to study the effects of algorithmic variations on tracking results. Motris attempts to avoid introducing bias into the relative assessment of alternative approaches. Such a bias may be caused by differences of implementation and parameterization if the component approaches are evaluated in separate testing environments. Tracking results are evaluated automatically on a significant test sample in order to quantify the effects of different combinations of alternatives. The Motris system environment thus allows an in-depth comparison between the so-called 'Edge-Element Association' approach documented in Haag and Nagel (1999) and the more recent 'Expectation-Maximization' approach reported by Pece and Worrall (2002).

show abstract

Section: Tracking Of Non-rigid Bodymentioning

confidence: 87%

A Framework for Model-Based Tracking Experiments in Image Sequences

Dahlkamp

Nagel

Ottlik

et al. 2006

Int J Comput Vision

View full text Add to dashboard Cite

show abstract

“…The face is modeled by a density distribution function of human face colors [3]- [5]. The algorithm tries to match the color density distribution (CDD) function of the human face model with the corresponding CDD function of the searched image area.…”

Section: A Face Modelmentioning

confidence: 99%

“…The function b : R 2 → {1...m} is a mapping function associating the pixel at location x i * with index b(x i * ) of the histogram bin in the quantized hue space (corresponding to the color of that pixel). For each binq u , CDD of the region x * is calculated as [3]- [5]:…”

Section: A Face Modelmentioning

confidence: 99%

See 1 more Smart Citation

Dual camera surveillance system for control and alarm generation in security applications

Draganjac

Kovačić

Ujlaki

et al. 2008

2008 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

In this paper we present an integrated system for intelligent video surveillance, control and alarm generation in security applications related to protection of public buildings (e.g. various financial institutions). By using only two networked cameras, video information is collected, dispatched via network and processed on-line with a group of integrated image processing algorithms able to detect humans in motion, track their motion, and check the visibility of their faces while entering the building. In addition, the developed system counts people's traffic and keeps the record of a number of people in the protected area. The integration of given algorithms is made in order to raise the reliability of the threat recognition. The emphasis is on the fast detection of the invisible (masked) face of the approaching person. Based on the outputs of the algorithms, either alarm generation or adequate control actions may take place.

show abstract

“…The defect is it can not endure too free motions. Lerdsudwichai et al [8] use color histogram to build the upper body model to recover the person after occlusion. It is easy to be failure, when the occluded person reappears with her/his face turning away from the camera.…”

Section: Introductionmentioning

confidence: 99%

Tracking and Recognition of Multiple Faces at Distances

Liu

Gao

Chu

et al.

Advances in Biometrics

View full text Add to dashboard Cite

Abstract. Many applications require tracking and recognition of multiple faces at distances, such as in video surveillance. Such a task, dealing with noncooperative objects is more challenging than handling a single face and than tackling a cooperative user. The difficulties include mutual occlusions of multiple faces and arbitrary head poses. In this paper, we present a method for solving the problems and a real-time system implementation. An appearance model updating mechanism is developed via Gaussian Mixture Models to deal with tracking under head rotation and mutual occlusion. Face recognition based on video sequence is then performed to get the identity information. Through fusing the tracking and recognition information, the performance of them are both improved. A real-time system for multi-face tracking and recognition at distances is presented. The system can track multiple faces under head rotations, and deal with total occlusion effectively regardless of the motion trajectory. It is also able to recognize multi-persons simultaneously. Experimental results demonstrate promising performance of the system.

show abstract

Tracking multiple people with recovery from partial and total occlusion

Cited by 30 publications

References 33 publications

A Framework for Model-Based Tracking Experiments in Image Sequences

A Framework for Model-Based Tracking Experiments in Image Sequences

Dual camera surveillance system for control and alarm generation in security applications

Tracking and Recognition of Multiple Faces at Distances

Contact Info

Product

Resources

About