L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate system. IEEE Trans. on PAMI, 22(8), Aug. 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Consistent Labeling of Tracked Objects in Multiple Cameras with .. - Khan, Shah (2003) (1 citation) (Correct)
....map to the same location. Of course, as is the case with spatial alignment, this can only be done when disparity between cameras is small. In our case, where the preferred camera arrangement is the one with large disparity, such a scheme is unlikely to work. A di#erent approach is described in [11] that uses trajectory information for alignment. The motion trajectories in di#erent cameras are randomly matched against one another and plane homographies computed for each match. The correct homography is the one that is statistically most frequent. Finer alignment is achieved through global ....
....of the existing ones, then it is given the same label, otherwise it is given a new label. Thus, we may view the this approach as an alternate way to compute the correspondences and homography between cameras. This method is simple compared to other approaches of computing homography, for example [11]. In fact, it is interesting to note that the search problem in [11] looks for the statistically most common homography from random matches between tracks. Here, assuming time alignment is available as in most real time systems) the search is done for statistically best lines, and thus over a ....
[Article contains additional citation context not shown here]
L. Lee, R. Romano, and G. Stein. "Monitoring activities from multiple video streams: Establishing a common coordinate frame". IEEE Trans. on PAMI, 22(8):758--767, Aug 2000.
Bayesian Modality Fusion for Tracking Multiple People with a.. - Chang, Gong (2001) (5 citations) (Correct)
....views. To this end, Collins et al. 4] use the trajectory and normalised colour histogram of an object. Chang et al. 5] esti mate the subjects apparent height and apparent colour across cameras. This matching can also be done by geometric method, such as epipo lar geometry [6] homography [9] and landmarks [5] However, these feature based matching methods can be unreliable due to the ambiguous positions of the extracted features resulting in inconsistencies. A framework is required to combine multiple visual modalities, or cues, to make the matching more reliable. Note that the ....
L. Lee, R. Romano and G. Stein. (2000). Monitoring activities from multiple video streams: Establishing a common coordinate frame. IEEE Transactions on Pattern Analysis and Machine Intelligence. Special Issue on Video Surveillance and Monitoring. 758-767.
Continuous Global Evidence-Based Bayesian Modality Fusion.. - Tracking Of Multiple (Correct)
....must be applied on the observations so that multiple object trackers do not continually claim responsibility for the same observation [6] There is generally a combinatorial explosion in the number of matching possibilities over time. Previous approaches at explicitly tracking multiple objects [7, 3, 9, 5] have used heuristic approaches to deal with this complexity. We propose a new Bayesian modality fusion, Continuous Global Evidence Based Bayesian Modality Fusion (CBMF) that makes four novel contributions but is also computationally tractable: 1) Continuous sampling: the formerly suggested ....
....single object case, but scales linearly with . This is a profoundly important property for simultaneous tracking of multiple objects: the usual combinatorial explosion in joint object location hypotheses is avoided by communication through the node. By comparison, other approaches such as [5] retain the complexity and assume tractability due to a small number of objects. Our approach can be compared with partitioned sampling [6] in which a hierarchical model of object independence is exploited to avoid complexity. However, our approach is deterministic, does not suffer from ....
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame. IEEE PAMI, 22(8):758--767, August 2000.
Algorithms for Cooperative Multisensor Surveillance - Collins, Lipton, Fujiyoshi.. (2001) (23 citations) (Correct)
....representing the terrain [see Fig. 7(a) Previous uses of the ray intersection technique for object localization in surveillance research have been restricted to small areas of planar terrain, where the relation between image pixels and terrain locations is a simple 2 D homography [9] 49] [74], 75] This has the benefit that no camera calibration is required to determine the backprojection of an image point onto the scene plane, provided the mappings of at least four coplanar scene points are known beforehand. However, large outdoor scene areas may contain significantly varied ....
L. Lee, R. Romano, and G. Stein, "Monitoring activities from multiple video streams: Establishing a common coordinate frame," IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, pp. 758--767, Aug. 2000.
Learning Patterns of Activity Using Real-Time Tracking - Stauffer, Grimson (2000) (44 citations) (Correct)
....the tasks listed above. In the following sec tions, we describe our tracking method [23] then out line our system for monitoring activities over extended time periods by simply observing object motions. Calibration of cameras, and extraction of ground plane information are covered separately in [18]. 2 Building a Robust Motion Tracker A robust video surveillance and monitoring system should not depend on careful placement of cameras. It should also be robust to whatever is in its visual field or whatever lighting effects occur. It should be capable of dealing with movement through ....
Lee, L., R. Romano, and G. Stein, "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame", separate paper in this issue.
Visual Learning in Surveillance Systems - Makris (2001) (Correct)
....and Quan examine the potential use of the gravity for camera calibration and pose estimation [20] Stein uses observations to establish a common spatio temporal frame. He uses object trajectories from multiple views to calibrate roughly multiple cameras, in car traffic surveillance system [21][22]. Boyd et al. estimates statistics of the activity in the scene. His method counts object transition among manual segmented regions of the scene[23] Fernyhough builds a database of object paths, by accumulating the frequency of trajectory occurrences in the spatial domain [24] He derived image ....
L. Lee, R. Romano, G. Stein, Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame, PAMI, vol. 22, num. 8, pp. 758-767, August 2000.
Plan-view Trajectory Estimation with Dense Stereo.. - Darrell, Demirdjian.. (2001) (11 citations) (Correct)
....global maxima of equation 2. 3.3 Implementation and Examples Figure 5 shows the configuration of cameras in our test environment. To align multiple views, we expect to use an automatic calibration process where objects moving on the plane are used to determine the orientation of each camera view [14, 13]. However, this section s results were obtained with an approximate manual calibration based on hand selected correspondences in each camera view. We collect variable gain and illumination images in our environment during a background acquisition phase. When there are multiple objects in the ....
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame. PAM1, 22(8):758 767, August 2000.
Tracking in Uncalibrated Cameras with Overlapping Field of View - Khan, Javed, Shah (2001) (3 citations) (Correct)
....body in each projection to reduce the difference between perspectives. Geometric features such as the height of the person are also used. The system is able to predict when a person is about the exit the current view and picks the best next view for tracking. A different approach is described in [3] that does not require calibrated cameras. The camera calibration information is recovered by observing motion trajectories in the scene. The motion trajectories in different views are randomly matched against one another and plane homographies computed for each match. The correct homography is ....
L. Lee, R. Romano, G. Stein, "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame", IEEE Trans on PAMI, Aug 2000, pp. 758-768
Human Tracking in Multiple Cameras - Khan, Javed, Rasheed, Shah (2001) (6 citations) (Correct)
....body in each projection to reduce the difference between perspectives. Geometric features such as the height of the person are also used. The system is able to predict when a person is about the exit the current view and picks the best next view for tracking. A different approach is described in [3] that does not require calibrated cameras. The camera calibration information is recovered by observing motion trajectories in the scene. The motion trajectories in different views are randomly matched against one another and plane homographies computed for each match. The correct homography is ....
L. Lee, R. Romano, G. Stein, "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame", IEEE Trans on PAMI, Aug 2000, pp. 758-768
Parametric Sequence-to-Sequence Alignment - Caspi, Irani (Correct)
....frame does. Scene dynamics (such as moving object, changes in illumination, etc) is a property that is inherent to the scene, and is thus common to all sequences taken from different video cameras. It therefore forms an additional powerful cue for alignment. Stein [19] and later Lee et al. [15] proposed an elegant approach to estimating spatiotemporal correspondences between two sequences based on alignment of trajectories of moving objects. Centroids of moving objects were detected and tracked in each sequence. Spatio temporal alignment parameters were then seeked, which would bring ....
L. Lee R., Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame, to appear in. IEEE Trans. on Pattern Analysis and Machine Intelligence, (Special Issue on Video Surveillance and Monitoring), 2000.
The Anatomy of a Multi-Camera Video Surveillance System - Jiao, Wu, Wu, Chang, Wang (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate system. IEEE Trans. on PAMI, 22(8), Aug. 2000.
A Convenient Multi-Camera Self-Calibration for Virtual.. - Svoboda, Martinec, Pajdla (2005) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: establishing a common coordinate frame. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):758--767, August 2000. 22
A Particle Visualization Framework for Clustering and Anomaly .. - Davidson, Ward (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame.", to appear in IEEE PAMI Special Section on Video Surveillance and Monitoring (2000).
Tracking Across Multiple Cameras With Disjoint Views - Omar Javed Zeeshan (2003) (5 citations) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. "Monitoring activities from multiple video streams: Establishing a common coordinate frame". IEEE Trans. on PAMI, 22(8):758--768, Aug 2000.
KNIGHT^M: A Multi-Camera Surveillance System - Javed, Shah (2003) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein, "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame", IEEE Trans. on Pattern Recognition and Machine Intelligence, vol. 22, no. 8, August 2000.
Robust Automated Planar Normalization of Tracking Data - Stauffer, Tieu, Lee (2003) (1 citation) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame. Pattern Recognition and Machine Intelligence, Special Section on Video Surveillance and Monitoring, 22(8), August 2000.
Perceptual Data Mining: Bootstrapping visual intelligence from.. - Stauffer (2002) (Correct)
No context found.
Lily Lee, Raquel Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame. PAMI, 1999. separate paper in this issue.
Knight^m: A Real Time Surveillance System For Multiple .. - Javed, Rasheed.. (2003) (Correct)
No context found.
R. Romano L. Lee and G. Stein. "Monitoring activities from multiple video streams: Establishing a common coordinate frame". IEEE Trans. on PAMI, 22(8):758-- 768, Aug 2000.
Consistent Labeling of Tracked Objects in Multiple Cameras with .. - Khan, Shah (2003) (1 citation) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein, "Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 758-767, Aug. 2000.
Robust Automated Planar Normalization of Tracking Data - Stauffer, Tieu, Lee (2003) (1 citation) (Correct)
No context found.
L. Lee, R. Romano, and G. Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame. Pattern Recognition and Machine Intelligence, Special Section on Video Surveillance and Monitoring, 22(8), August 2000.
A Novel Graphical Interface and Context Aware Map for - Incident Detection And (Correct)
No context found.
L. Lee, R. Romano, G. Stein. "Monitoring activities from multiple video streams: establishing a common coordinate frame," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.22,
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC