Abstract. A multi-view multi-hypothesis approach to segmenting and tracking multiple (possibly occluded) persons on a ground plane is proposed. During tracking, several iterations of segmentation are performed using information from human appearance models and ground plane homography. To more precisely locate the ground location of a person, all center vertical axes of the person across views are mapped to the topview plane and their intersection point on the ground is estimated. To tackle the explosive state space due to multiple targets and views, iterative segmentation-searching is incorporated into a particle filtering framework. By searching for people’s ground point locations from segmentations, a set of a few good particles can be identified, resulting in low computational cost. In addition, even if all the particles are away from the true ground point, some of them move towards the true one through the iterated process as long as they are located nearby. We demonstrate the performance of the approach on several video sequences. 1

Visual surveillance using multiple cameras has attracted increasing interest in recent years. Correspondence between multiple cameras is one of the most important and basic problems which visual surveillance using multiple cameras brings. In this paper, we propose a simple and robust method, based on principal axes of people, to match people across multiple cameras. The correspondence likelihood reflecting the similarity of principal axis pairs is constructed according to the relationship between “ground-points ” detected in each camera view and the intersections of principal axes detected in different camera views and transformed to the same view. Our method has the following desirable properties: (1) Camera calibration is not needed. (2) Accurate motion detection and segmentation are less critical due to the robustness of the principal axis-based feature to noise. (3) Based on the fused data derived from correspondence results, positions of people in each camera view can be accurately located even when the people are partially occluded in all views. The experimental results on several real video sequences from outdoor environments have demonstrated the effectiveness, efficiency and robustness of our method.

In this paper, we aim to achieve scalability and wider scene coverage through the use of multiple cameras in an outdoor visual surveillance system. Only image-based information is used to control the cameras, making the system highly scalable. We show that when a Pan-Tilt-Zoom camera pans and tilts, a given image point moves in circular and linear trajectory respectively. We also create a scene model using a directly top-view image of the scene to eliminate perspective foreshortening. The scene model allows us to handle occlusion occurring as a result of line of sight between cameras and tracked objects and to determine the view of an object that a camera is acquiring images of. In addition, we also use a maximum weight matching algorithm to assign cameras to tasks when the number of cameras are limited. Finally, the system is tested by simulations and a prototype system. 1

This paper presents a novel approach for continuous detection and tracking of moving objects observed by multiple stationary cameras. We address the tracking problem by simultaneously modeling motion and appearance of the moving objects. The objects appearance is represented using color distribution model invariant to 2D rigid and scale transformation. It provides an efficient blobs similarity measure for tracking. The motion models are obtained using a Kalman Filter (KF) process, which predicts the position of the moving object in 2D and 3D. The tracking is performed by the maximization of a joint probability model reflecting objects motion and appearance. The novelty of our approach consists in integrating multiple cues and multiple views in a JPDAF for tracking a large number of moving people with partial and total occlusions. We demonstrate the performances of the proposed method on a soccer game captured by two stationary cameras. 1.#

Tracking over a long period of time is challenging as the appearance, shape and scale of the object in question may vary. We propose a paradigm of tracking by repeatedly segmenting figure from background. Accurate spatial support obtained in segmentation provides rich information about the track and enables reliable tracking of non-rigid objects without drifting. Figure/ground segmentation operates sequentially in each frame by utilizing both static image cues and temporal coherence cues, which include an appearance model of brightness (or color) and a spatial model propagating figure/ground masks through low-level region correspondence. A superpixel-based conditional random field linearly combines cues and loopy belief propagation is used to estimate marginal posteriors of figure vs background. We demonstrate our approach on long sequences of sports video, including figure skating and football. 1.

This paper presents novel approaches for continuous detection and tracking of moving objects observed by multiple, stationary or moving cameras. Stationary video streams are registered using a ground plane homography and the trajectories derived by Tensor Voting formalism are integrated across cameras by a spatio-temporal homography. Tensor Voting based tracking approach provides smooth and continuous trajectories and bounding boxes, ensuring minimum registration error. In the more general case of moving cameras, we present an approach for integrating objects trajectories across cameras by simultaneous processing of video streams. The detection of moving objects from moving camera is performed by defining an adaptive background model that uses an affine-based camera motion approximation. Relative motion between cameras is approximated by a combination of affine and perspective transform while objects dynamics are modeled by a Kalman Filter. Shape and appearance of moving objects are also taken into account using a probabilistic framework. The maximization of the joint probability model allows tracking moving objects across the cameras. We demonstrate the performances of the proposed approaches on several video surveillance sequences. Keywords Video Surveillance, Video Analysis, Multiple Cameras, Heterogeneous Cameras, Tracking, Detection, Tensor Voting, Camera Registration, Kalman Filter, JPDAF. 1.#

Abstract. Systems utilizing multiple sensors are required in many domains. In this paper, we specifically concern our-selves with applications where dynamic objects appear randomly and the system is employed to obtain some user-specified characteristics of such objects. For such systems, we deal with the tasks of determining measures for evaluating their performance and of determining good sensor configurations that would maximize such measures for better system performance. We introduce a constraint in sensor planning that has not been addressed earlier: visibility in the presence of random occluding objects. Two techniques are developed to analyze such visibility constraints: a probabilistic approach to determine “average ” visibility rates and a deterministic approach to address worst-case scenarios. Apart from this constraint, other important constraints to be considered include image resolution, field of view, capture orientation, and algorithmic constraints such as stereo matching and background appearance. Integration of such constraints is performed via the development of a probabilistic framework that allows one to reason about different occlusion events and integrates different multi-view capture and visibility constraints in a natural way. Integration of the thus obtained capture quality measure across the region of interest yields a measure for the effectiveness of a sensor configuration and maximization of such measure yields sensor configurations that are

In this paper, we present a review of existing techniques and systems for tracking multiple occluding objects using one or more cameras. Following a formulation of the occlusion problem, we divide these techniques into two groups: mergesplit (MS) approaches and straight-through (ST) approaches. Then, we consider tracking in ball game applications, with emphasis on soccer. Based on this assessment of the state of the art, we identify what appear to be the most promising approaches for tracking in general and for soccer in particular. 1.

This paper presents a novel approach for tracking multiple objects and a statistical learning approach for detection of human activities in a video sequence. For the tracking, a ## rigid transformation invariant appearance model combining color and edge information of the detected blob is proposed. For the activity detection, each activity label is regarded as a hypothesis. Given some labeled sequences, a group of features are first extracted from motion trajectories of each detected object and the likelihood of each feature under that hypothesis is calculated. A dynamic programming-based training algorithm is applied to get an optimal classifier for each feature. Then it selects the classifiers with the most discriminative power and combines them to form a stronger classifier. This algorithm complies with ######-###### # criterion so that it is guaranteed to achieve a specified detection rate as well as a minimized false alarm rate. Results on #### ## dataset show the effectiveness of the proposed algorithm.

In this paper we introduce a system to track pedestrians using a combined input from RGB and thermal cameras. Two major contributions are presented here. First is the novel model of the scene background where each pixel is represented as a multi-modal distribution with the changing number of modalities for both color and thermal input. We demonstrate how to eliminate the influence of shadows with this type of fusion. Second, based on our background model we introduce a pedestrian tracker designed as a particle filter. We further develop a number of informed reversible transformations to sample the model probability space in order to maximize our model posterior probability. The novelty of our tracking approach also comes from a way we formulate observation likelihoods to account for 3D locations of the bodies with respect to the camera and occlusions by other tracked human bodies as well as static objects. The results of tracking on color and thermal sequences demonstrate that our algorithm is robust to illumination noise and performs well in the outdoor environments.