Distributed calibration of Camera Sensor Networks

Elhamifar, Ehsan; Vidal, René

doi:10.1109/icdsc.2009.5289397

Cited by 7 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, estimation problems with hundreds of cameras and a large variety of moving objects are not considered in those elementary articles. Other algorithms for topology estimation rely on assumptions like the presence of shared Field of Views (FOVs) that enable various algorithms for neighborhood detection [5], [6], [7], [8]. Unfortunately, those overlapping camera views cannot be guaranteed in large scenarios and from a macroscopic point of view, it is not beneficial spending computing resources to find them.…”

Section: Related Work In Topology Estimationmentioning

confidence: 99%

Efficient communication for large-scale robust image processing with smart camera devices

Golembewski

Schaefer

Gerlach

2012

2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

Large-scale data acquisition and distributed processing of video material requires smart camera devices to collaborate over arbitrary transport networks with no further centralized coordinating instances. Especially in the context of surveillance and security in public transportation networks, the knowledge of spatio-temporal traffic flows can support applications like anomaly detection, smart navigation, or prosecution. Therefore, the problem of autonomously estimating a logical camera topology with respect to scalability, agility and robustness must be solved by efficient communication about distributed detected events. Simple broadcasting or flooding of information does not scale well with the number of nodes and leads to strong requirements on bandwidth and processing power. Thus, a generic system model, describing the process of generating eventbased distributed knowledge without making use of flooding, broadcast or multicast, is introduced and evaluated. The results of a conducted simulation study reveal the potential of saving a significant amount of messages on the one hand, and being able to handle poor performance of object recognition algorithms on the other hand.

show abstract

Section: Related Work In Topology Estimationmentioning

confidence: 99%

Efficient communication for large-scale robust image processing with smart camera devices

Golembewski

Schaefer

Gerlach

2012

2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

show abstract

“…Calibrating the camera network -First, a large body of work suppose that cameras have overlapping Field-OfViews (FOV) [10], [28] whereas our work focuses on camera networks with non-overlapping FOVs. Moreover, existing works suppose that either a single person [4] or limited number of humans move around at different time intervals.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised camera localization in crowded spaces

Alahi

Wilson

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-Existing camera networks in public spaces such as train terminals or malls can help social robots to navigate crowded scenes. However, the localization of the cameras is required, i.e., the positions and poses of all cameras in a unique reference. In this work, we estimate the relative location of any pair of cameras by solely using noisy trajectories observed from each camera. We propose a fully unsupervised learning technique using unlabelled pedestrians motion patterns captured in crowded scenes.We first estimate the pairwise camera parameters by optimally matching single-view pedestrian tracks using social awareness. Then, we show the impact of jointly estimating the network parameters. This is done by formulating a nonlinear least square optimization problem, leveraging a continuous approximation of the matching function. We evaluate our approach in real-world environments such as train terminals, where several hundreds of individuals need to be tracked across dozens of cameras every second.

show abstract

“…Moreover, unlike [4,10], we do not require that the internal or external parameters of any camera be known and do not require any external calibration object. Also, unlike [12], our method does not consider every pan-tilt configuration of any camera in the network.…”

Section: Related Workmentioning

confidence: 99%

“…The methods in [3,10,7,4] are for distributed calibration of static camera networks while we propose a technique for distributed calibration of pan-tilt camera network. Moreover, unlike [4,10], we do not require that the internal or external parameters of any camera be known and do not require any external calibration object.…”

Section: Related Workmentioning

confidence: 99%

“…In [7], 3D features and geographic hash tables are used while in [5] object motion is used for calibration. Very recently, authors in [4], have proposed a distributed algorithm for calibration of a camera sensor network, where they assume that one of the cameras is calibrated and use epipolar geometry based algorithms at each node to obtain its calibration parameters. They show that a globally consistent solution can be reached in a distributed manner by solving a set of linear equations.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Distributed calibration of pan-tilt camera network using multi-layered belief propagation

Choudhary

Sharma

Chaudhury

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops

View full text Add to dashboard Cite

In this paper, we present a technique for distributed selfcalibration of pan-tilt camera network using multi-layered belief propagation. Our goal is to obtain globally consistent estimates of the camera parameters for each camera with respect to a global world coordinate system. The network configuration changes with time as the cameras can pan and tilt. We also give a distributed algorithm for automatically finding which cameras have overlapping views at a certain point in time. We argue that using belief propagation it is sufficient to have correspondences between three cameras at a time for calibrating a larger set of (static) cameras with overlapping views. Our method gives an accurate and globally consistent estimate of the camera parameters of each camera in the network.

show abstract

Distributed calibration of Camera Sensor Networks

Cited by 7 publications

References 24 publications

Efficient communication for large-scale robust image processing with smart camera devices

Efficient communication for large-scale robust image processing with smart camera devices

Unsupervised camera localization in crowded spaces

Distributed calibration of pan-tilt camera network using multi-layered belief propagation

Contact Info

Product

Resources

About