Automated multi-camera planar tracking correspondence modeling

Stauffer, Chris; Tieu, Kinh

doi:10.1109/cvpr.2003.1211362

Cited by 90 publications

(67 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work of Javed et al [7] and that of Stauffer and Tieu [5] for example, is directly related to the development of multi-target tracking systems. Similarly, one of the stated goals of Ellis et al [8,9] is to enhance the tracking performance of surveillance systems.…”

Section: Related Workmentioning

confidence: 99%

“…A number of researchers have looked at the problem of self-configuring a multi-sensor network through the exploitation of motion in the environment [3][4][5][6]. These efforts generally assume vision-based sensors and focus on issues regarding the processing of observations collected from distributed sensors.…”

Section: Related Workmentioning

confidence: 99%

“…Also relying on overlapping fields of view between cameras placed at adjacent sensing locations, Stauffer and Tieu [5] described a method for building a tracking correspondence model based solely on observational data. Their work focused on determining which tracking data resulted from observations of the same objects in sensors with overlapping views.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Self-calibration of a vision-based sensor network

Marinakis

Dudek

2009

Image and Vision Computing

View full text Add to dashboard Cite

When a network of vision-based sensors is emplaced in an environment for applications such as surveillance or monitoring the spatial relationships between the sensing units must be inferred or computed for self-calibration purposes. In this paper we describe a technique to solve one aspect of this self-calibration problem: automatically determining the topology and connectivity information of a network of cameras based on a statistical analysis of observed motion in the environment. While the technique can use labels from reliable cameras systems, the algorithm is powerful enough to function using ambiguous tracking data. The method requires no prior knowledge of the relative locations of the cameras and operates under very weak environmental assumptions. Our approach stochastically samples plausible agent trajectories based on a delay model that allows for transitions to and from sources and sinks in the environment. The technique demonstrates considerable robustness both to sensor error and non-trivial patterns of agent motion. The output of the method is a Markov model describing the behavior of agents in the system and the underlying traffic patterns. The concept is demonstrated with simulation data for systems containing up to 10 agents and verified with experiments conducted on a six camera sensor network.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Self-calibration of a vision-based sensor network

Marinakis

Dudek

2009

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Aspects of SLAT are also related to work in computer vision in multiple camera tracking and calibration [5,13,15], which as largely focused on overlapping camera configurations, and structure from motion (SFM) [8,12,14]. Given a sequence of images of a static scene captured by a moving camera, the goal of SFM is to recover the 3D geometry of the scene and the trajectory of the camera motion, typically by using correspondences between feature points.…”

Section: Related Workmentioning

confidence: 99%

Distributed localization of networked cameras

Funiak¹,

Guestrin²,

Paskin³

et al. 2006

2006 5th International Conference on Information Processing in Sensor Networks

View full text Add to dashboard Cite

Camera networks are perhaps the most common type of sensor network and are deployed in a variety of real-world applications including surveillance, intelligent environments and scientific remote monitoring. A key problem in deploying a network of cameras is calibration, i.e., determining the location and orientation of each sensor so that observations in an image can be mapped to locations in the real world. This paper proposes a fully distributed approach for camera network calibration. The cameras collaborate to track an object that moves through the environment and reason probabilistically about which camera poses are consistent with the observed images. This reasoning employs sophisticated techniques for handling the difficult nonlinearities imposed by projective transformations, as well as the dense correlations that arise between distant cameras. Our method requires minimal overlap of the cameras' fields of view and makes very few assumptions about the motion of the object. In contrast to existing approaches, which are centralized, our distributed algorithm scales easily to very large camera networks. We evaluate the system on a real camera network with 25 nodes as well as simulated camera networks of up to 50 cameras and demonstrate that our approach performs well even when communication is lossy.

show abstract

“…The proliferation of large camera networks in recent past has ushered research in multiple camera analysis, and several methods have been proposed to address the problems of calibration, tracking and activity analysis with some degree of reliability [1,2,3,4,5,6,7]. However, despite significant efforts in this area, the majority of literature has been confined to solution of problems like object correspondence and activity correlation between visible objects, while estimation and inference of object behaviors in unobservable regions between disjoint cameras has mainly remained unexplored.…”

Section: Introductionmentioning

confidence: 99%

Statistical Inference of Motion in the Invisible

Idrees

Saleemi

Shah

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. This paper focuses on the unexplored problem of inferring motion of objects that are invisible to all cameras in a multiple camera setup. As opposed to methods for learning relationships between disjoint cameras, we take the next step to actually infer the exact spatiotemporal behavior of objects while they are invisible. Given object trajectories within disjoint cameras' FOVs (field-ofview), we introduce constraints on the behavior of objects as they travel through the unobservable areas that lie in between. These constraints include vehicle following (the trajectories of vehicles adjacent to each other at entry and exit are time-shifted relative to each other), collision avoidance (no two trajectories pass through the same location at the same time) and temporal smoothness (restricts the allowable movements of vehicles based on physical limits). The constraints are embedded in a generalized, global cost function for the entire scene, incorporating influences of all objects, followed by a bounded minimization using an interior point algorithm, to obtain trajectory representations of objects that define their exact dynamics and behavior while invisible. Finally, a statistical representation of motion in the entire scene is estimated to obtain a probabilistic distribution representing individual behaviors, such as turns, constant velocity motion, deceleration to a stop, and acceleration from rest for evaluation and visualization. Experiments are reported on real world videos from multiple disjoint cameras in NGSIM data set, and qualitative as well as quantitative analysis confirms the validity of our approach.

show abstract

Automated multi-camera planar tracking correspondence modeling

Cited by 90 publications

References 2 publications

Self-calibration of a vision-based sensor network

Self-calibration of a vision-based sensor network

Distributed localization of networked cameras

Statistical Inference of Motion in the Invisible

Contact Info

Product

Resources

About