Multi camera person tracking applying a graph-cuts based foreground segmentation in a homography framework

Arsic, D.; Lyutskanov, Atanas; Rigoll, Gerhard; Kwolek, Bogdan

doi:10.1109/pets-winter.2009.5399723

Cited by 12 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They define local loitering; someone loitering in the scene for an extended period of time, and global loitering; which keeps in mind that the candidate can temporarily leave the camera view and then return to it if they are loitering around the area. Arsic et al [1] use multiple cameras surveilling the same scene at different angles to track and detect loiterers and abandoned luggage.…”

Section: Related Workmentioning

confidence: 99%

An Entropy Model for Loiterer Retrieval across Multiple Surveillance Cameras

Sandifort

Liu

Nishimura

et al. 2018

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Loitering is a suspicious behavior that often leads to criminal actions, such as pickpocketing and illegal entry. Tracking methods can determine suspicious behavior based on trajectory, but require continuous appearance and are difficult to scale up to multi-camera systems. Using the duration of appearance of features works on multiple cameras, but does not consider major aspects of loitering behavior, such as repeated appearance and trajectory of candidates. We introduce an entropy model that maps the location of a person's features on a heatmap. It can be used as an abstraction of trajectory tracking across multiple surveillance cameras. We evaluate our method over several datasets and compare it to other loitering detection methods. The results show that our approach has similar results to state of the art, but can provide additional interesting candidates.

show abstract

Section: Related Workmentioning

confidence: 99%

An Entropy Model for Loiterer Retrieval across Multiple Surveillance Cameras

Sandifort

Liu

Nishimura

et al. 2018

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…Figure 13 shows the robust nature of the Visual Cortex model, respectively for F1 score (14) and Precision (13), using the mutual information of the three LGN pathways, in comparison to their independent performances. order that comparisons may be drawn: (Arsic et al, 2009) employ a multi-layer homography, which is capable of creating a three dimensional representation of the scene. Homography frameworks rely on the fusion of previously segmented foreground regions visible from multiple views.…”

Section: Muhavimentioning

confidence: 99%

“…Homography frameworks rely on the fusion of previously segmented foreground regions visible from multiple views. In the case of (Arsic et al, 2009) system, these foreground segmentations are produced by finding the median of pixel values and composing a reference image for simple background subtraction. Brightness invariance is achieved by normalised cross covariance when compared with the reference image and contrast invariance is achieved using normalised cross-correlation.…”

Section: Muhavimentioning

confidence: 99%

Biologically-inspired robust motion segmentation using mutual information

Ellis

Ferryman

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This paper presents a neuroscience inspired information theoretic approach to motion segmentation. Robust motion segmentation represents a fundamental first stage in many surveillance tasks. As an alternative to widely adopted individual segmentation approaches, which are challenged in different ways by imagery exhibiting a wide range of environmental variation and irrelevant motion, this paper presents a new biologically-inspired approach which computes the multivariate mutual information between multiple complementary motion segmentation outputs. Performance evaluation across a range of datasets and against competing segmentation methods demonstrates robust performance.

show abstract

“…The silhouettes were delineated on the basis of the background subtraction [1]. The second term reflects the degree of overlap between the projected edges of the model and image gradients.…”

Section: Tracking Frameworkmentioning

confidence: 99%

Multiple views based human motion tracking in surveillance videos

Kwolek

2011

2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

Self Cite

View full text Add to dashboard Cite

Most work on activity recognition focuses on 2D image properties, holistic spatiotemporal representations, or space-time shapes in image domain rather than with 3D pose in a body-centric or world frame. Such techniques rely on advanced pattern recognition algorithms and interpreting complex behavioral patterns. In this work we posit that it is possible to achieve 3D pose tracking using videos recorded in multi-camera surveillance systems. We show experimental results that were obtained on PETS 2009 datasets. The estimation of the 3D articulated motion is achieved using a modified particle swarm optimization.

show abstract

Multi camera person tracking applying a graph-cuts based foreground segmentation in a homography framework

Cited by 12 publications

References 13 publications

An Entropy Model for Loiterer Retrieval across Multiple Surveillance Cameras

An Entropy Model for Loiterer Retrieval across Multiple Surveillance Cameras

Biologically-inspired robust motion segmentation using mutual information

Multiple views based human motion tracking in surveillance videos

Contact Info

Product

Resources

About