Motion based event detection system and method
First Claim
1. A method of providing video indexing comprising the steps of:
- (a) detecting objects in video to provide detected objects comprising the step of performing motion segmentation including image differencing from a reference image and thresholding and storing meta-information in a database where said meta-information is in the form of a directed graph;
(b) analyzing motion of said detected objects including tracking said detected objects using linear prediction of object position;
(c) generating a symbolic motion description of object motion; and
(d) placing index marks in said symbolic motion description to identify occurrence of events in the video.
0 Assignments
0 Petitions
Accused Products
Abstract
A method to provide automatic content-based video indexing from object motion is described. Moving objects in video from a surveillance camera 11 detected in the video sequence using motion segmentation methods by motion segmentor 21. Objects are tracked through segmented data in an object tracker 22. A symbolic representation of the video is generated in the form of an annotated graphics describing the objects and their movement. A motion analyzer 23 analyzes results of object tracking and annotates the graph motion with indices describing several events. The graph is then indexed using a rule based classification scheme to identify events of interest such as appearance/disappearance, deposit/removal, entrance/exit, and motion/rest of objects. Clips of the video identified by spatio-temporal, event, and object-based queries are recalled to view the desired video.
-
Citations
8 Claims
-
1. A method of providing video indexing comprising the steps of:
-
(a) detecting objects in video to provide detected objects comprising the step of performing motion segmentation including image differencing from a reference image and thresholding and storing meta-information in a database where said meta-information is in the form of a directed graph;
(b) analyzing motion of said detected objects including tracking said detected objects using linear prediction of object position;
(c) generating a symbolic motion description of object motion; and
(d) placing index marks in said symbolic motion description to identify occurrence of events in the video. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
(a) receiving content-based queries;
(b) matching queries with symbolic video information and said index marks; and
(c) providing video sequences corresponding to the query.
-
-
4. The method of claim 3 wherein constraints for queries are specified by manipulation of video clips.
-
5. The method of claim 1 wherein said motion segmentation includes connected component analysis.
-
6. The method of claim 1 wherein said image differencing includes applying an edge detector operator to the current image and the reference image and checking for coincident boundary pixels in the segmented region.
-
7. The method of claim 1 wherein said detected objects in video are from an IR sensor and said image differencing compares the variance of pixel intensities within the region of interest of the current image and reference image.
-
8. The method of claim 1 wherein said motion segmentation includes morphological close operation.
Specification