EP0805405A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Motion event detection for video indexing
Assignee: Texas Instruments Inc
•
Filing: 1997-02-04
•
Granted: —
•
Expires: 2017-02-04
Abstract
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. <IMAGE>
Inventors
- 👤 Jonathan D. Courtney
- 👤 Dinesh R. Nair
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 21:10
CPC Classifications
G; G11; G11B; G11B27/00; G11B27/10; G11B27/102; G11B27/105; G06; G06F; G06F16/00; G06F16/70; G06F16/78; G06F16/783; G06F16/7837; G06F16/7847; G06F16/786; G06T; G06T7/00; G06T7/20; G06T7/246; G06T7/254; G06T7/277; G06V; G06V10/00; G06V10/20; G06V10/255; G06V20/00; G06V20/50; G06V20/52; G06V40/00; G06V40/20; G11B27/19; G11B27/28; H; H04; H04N; H04N19/00; H04N19/10; H04N19/134; H04N19/142; H04N19/169; H04N19/179; H04N19/85; H04N19/87; H04N7/00; H04N7/18; H04N7/188; G06V10/40; G06V10/62; G11B27/34
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
63 words
A method of providing video indexing comprising the steps of: motion segmenting video objects in said video; generating a record of segmented video objects describing said segmented video objects and movement through successive frames; determining path of said objects and intersection with paths of other objects to thereby detect the occurrence of events; and placing an index mark to identify occurrence of events.
Claim 2
Dependent Claim
27 words
The method of Claim 1, wherein said step of determining the occurrence of events comprises determining one or more of appearance/disappearance; deposit/removal, motion/rest, or entrance/exit of objects.
Claim 3
Dependent Claim
30 words
The method of Claim 1 or Claim 2, wherein said generating step includes generating a record of size, shape, position, timestamp, and image of each object in each video frame.
Claim 4
Independent Claim
49 words
A method of providing video indexing from object motion in video data comprising the steps of: detecting moving objects by motion segmentation; generating an annotated directed motion graph describing objects and their movement through successive frames of video data; and indexing said motion graph to identifying events of intersect.
Claim 5
Dependent Claim
14 words
The method of Claim 4, wherein said indexing step uses a rule-based classification scheme.
Claim 6
Dependent Claim
23 words
The method of Claim 4 or Claim 5, wherein said step of identifying events includes identifying appearance/disappearance, deposit/removal, entrance/exit, or motion/rest of objects.
Claim 7
Independent Claim
64 words
A method to assist human analysis of video data comprising: detecting moving objects by motion segmentation; generating an annotated directed motion graph describing objects and their movement through successive frames of video data; indexing said motion graph to identify events of intersect; and querying clips of said video data associated with said motion graph by said index to analyze schematic context of the video.
Claim 8
Independent Claim
50 words
A system for video indexing comprising: means for detecting moving objects; means coupled to said detecting means for generating an annotated directed motion graph describing objects and movement through successive frames of video data; means coupled to said generating means for indexing said motion graphs according to events of interest.
Claim 9
Dependent Claim
23 words
The system of Claim 8, wherein said means for indexing is arranged to index events of appearance/disappearance, deposit/removal, entrance/exit, or motion/rest of objects.
Claim 10
Independent Claim
67 words
A method of performing object detection for scene change analysis, wherein a statistical test is applied to data extracted from two images taken of the same scene from identical viewpoints using a change region corresponding to an object that is present in one image but absent in the other, the test being indicative of which change region of the two images in which the object is present.
Claim 11
Dependent Claim
33 words
The method of Claim 10, wherein for the case of TV data the statistical test consists of measuring the coincidence of edge pixels in each image with the boundary of the change region.
Claim 12
Dependent Claim
32 words
The method of Claim 10 or Claim 11, wherein for the case of IR data the statistical test consists of measuring the pixel intensity variance within the change region in each image.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.