초록 ▼

Tracking and surveillance methods and systems for monitoring objects passing in front of non-overlapping cameras. Invention finds corresponding tracks from different cameras and works out which object passing in front of the camera(s) made the tracks, in order to track the object from camera to came

Tracking and surveillance methods and systems for monitoring objects passing in front of non-overlapping cameras. Invention finds corresponding tracks from different cameras and works out which object passing in front of the camera(s) made the tracks, in order to track the object from camera to camera. The invention uses an algorithm to learn inter-camera spatial temporal probability using Parzen windows, learns inter-camera appearance probabilities using distribution of Bhattacharyya distances between appearance models, establishes correspondences based on Maximum A Posteriori (MAP) framework combining both spatial temporal and appearance probabilities, and updates learned probabilities throughout the lifetime of the system.

대표청구항 ▼

We claim: 1. A method of tracking an object passing before non-overlapping cameras, comprising the steps of: tracking the object between a first camera and a second camera; and automatically determining whether the object is identical in both the first camera and the second camera without calibrati

We claim: 1. A method of tracking an object passing before non-overlapping cameras, comprising the steps of: tracking the object between a first camera and a second camera; and automatically determining whether the object is identical in both the first camera and the second camera without calibrating the cameras or providing a site modeling, wherein the determining step includes the steps of: learning inter-camera spatial temporal probability between the first camera and the second camera using Parzen windows; learning inter-camera appearance probabilities between the first camera and the second camera using distribution of Bhattacharyya distances between appearance models; establishing correspondences between the first camera and the second camera based on Maximum A Posteriori (MAP) framework combining both the spatial temporal and the appearance probabilities; and updating learned probabilities throughout over time. 2. The method of claim 1, wherein the inter-camera spatial temporal probability learning step includes the steps of: assuming a known correspondence; and estimating a space-time probability density function for the first camera and the second camera using the Parzen windows. 3. The method of claim 2, wherein the estimating step includes the step of: learning exit and entry locations, velocities, and transition times of the object between the first camera and the second camera. 4. The method of claim 1, wherein the inter-camera appearance probabilities learning step includes the step of: estimating a change in appearance of the object from the first camera to the second camera. 5. The method of claim 4, wherein the estimating step includes the step of: generating color histograms of the object at the first camera and the second camera; and estimating the inter-camera brightness transfer function using the generated color histograms. 6. The method of claim 5, further including the step of: using the inter-camera brightness transfer function to estimate the probability that the object is identical in both the first camera and the second camera. 7. The method of claim 1, wherein the tracking step includes the step of: detecting a first observation and a second observation of the object passing before the first camera and the second camera. 8. The method of claim 7, further including the step of: establishing a correspondence between the first detected observation and the second detected observation to determine a path covered by the object. 9. The method of claim 7, further including the step of: establishing that the first observation is preceded and succeeded by only the second observation and vice versa. 10. The method of claim 7, wherein the detecting step includes the steps of: collecting a space-time feature and an appearance feature of the object in the first observation and the second observation. 11. The method of claim 1, further comprising the step of: using the updated learned probabilities to establish correspondences between the first camera and the second camera over time. 12. The method of claim 1, further comprising the step of: providing a third camera for the tracking of the object. 13. A system for tracking an object passing between non-overlapping cameras without calibrating the cameras or completing site modeling, comprising: plural cameras for tracking the object; and means for automatically determining whether the object in both a first one of the plural cameras and a second one of the plural cameras are a same object, wherein the determining means includes: means for learning inter-camera spatial temporal probability between a first camera and the second camera using Parzen windows, wherein the spatial temporal probability learning means includes means for collecting plural space-time features from the first camera and the second camera; and means for estimating a space-time probability density function for the first camera and the second camera; means for learning inter-camera appearance probabilities between the first camera and the second camera using distribution of Bhattacharyya distances between appearance models; means for establishing correspondences between the first camera and the second camera based on Maximum A Posteriora framework combining both the learned inter-camera spatial temporal and appearance probabilities; and means for updating the learned probabilities throughout over time. 14. The system of claim 13, wherein the plural cameras comprise: means for collecting plural observations of the object observed at the plural cameras; means for collecting a time-space feature and an appearance feature for each of the plural observations. 15. The system of claim 14, further comprising: means for grouping the ones of the plural observations to form a chain of consecutive observations of the object. 16. A system for tracking an object passing between non-overlapping cameras without calibrating the cameras or completing site modeling, comprising: plural cameras for tracking the object; and means for automatically determining whether the object in both a first one of the plural cameras and a second one of the plural cameras are a same object, wherein the determining means includes: means for learning inter-camera spatial temporal probability between a first camera and the second camera using Parzen windows; means for learning inter-camera appearance probabilities between the first camera and the second camera using distribution of Bhattacharyya distances between appearance models wherein the appearance probability learning means includes: means for estimating a change of appearance of the object from the first camera to the second camera; means for establishing correspondences between the first camera and the second camera based on Maximum A Posteriora framework combining both the learned inter-camera spatial temporal and appearance probabilities; and means for updating the learned probabilities throughout over time. 17. The system of claim 16 wherein the change of appearance estimating means comprises: means for generating color histograms of the object at the first camera and the second camera; and means for estimating an inter-camera brightness transfer function of the object using the generated color histograms.