# US 2016/0259975 A1 · Method of searching data to identify images of an object captured by a camera system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0259975 A1
- Document ID: US20160259975A1
- Status: Published application
- Kind: A1
- Application number: 15/068,433
- Filed: 2016-03-11
- Published: 2016-09-08
- Earliest claimed: 2008-03-03
- Assignees: Avigilon Patent Holding 2 Corporation
- Applicants: Avigilon Patent Holding 2 Corporation
- Inventors: Mahesh SAPTHARISHI; Dimitri A. LISIN
- Web page: https://patentgrep.com/patent/US20160259975A1

## CPC

- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06T 7/73: using feature-based methods
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N 7/181: {for receiving images from a plurality of remote sources}
- H04N 23/611: where the recognised objects include parts of the human body
- H04N 23/63: by using electronic viewfinders
- H04N 23/631: {Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters}
- H04N 23/66: Remote control of cameras or camera parts, e.g. by remote control devices
- H04N 23/661: Transmitting camera control signals through networks, e.g. control via the Internet
- G06F 2218/12: Classification; Matching
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30232: Surveillance
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A camera system comprises an image capturing device, object detection module, object tracking module, and match classifier. The object detection module receives image data and detects objects appearing in one or more of the images. The object tracking module temporally associates instances of detected objects, each of which has a signature representing features of the detected object. The match classifier matches object instances by analyzing data derived from the signatures. The match classifier determines whether the signatures match.

## Claims

### Claim 1

A camera system, comprising:
an object detection module operable to receive image data produced by at least one image capturing device, the image data representing multiple images of a field of view of the at least one image capturing device, and the object detection module operable to detect objects appearing in one or more of the multiple images;
an object tracking module connected to the object detection module and operable to temporally associate instances of objects detected by the object detection module, wherein each detected object has a signature representing features of the detected object from the multiple images; and
a match classifier connected to the object tracking module and operable to match object instances by analyzing data derived from the signature of each detected object to indicate if two or more of the detected objects correspond to a same physical object.

### Claim 2 (depends on 1)

The camera system of claim 1, further comprising
a user interface including a display for displaying objects detected by the object detection module and an input device operable to select objects detected by the object detection module in response to user commands.

### Claim 3 (depends on 2)

The camera system of claim 2, further comprising
a search module connected to the match classifier and the user interface, the search module being operable to retrieve stored images of objects selected by the input device, the search module being operable to call on the match classifier to locate a stored image of a selected object.

### Claim 4 (depends on 1)

The camera system of claim 1, wherein the analyzing data derived from the signature of each detected object is based on matching parameters and non-matching parameters.

### Claim 5 (depends on 1)

The camera system of claim 1, wherein the object tracking module temporally associates instances of objects using a motion modeling module and the match classifier.

### Claim 6 (depends on 1)

The camera system of claim 1, further comprising:
a rule engine operable to determine a rule violation based at least in part on the image data; and
an object search module operable to identify images of an object in the image data captured prior to the rule violation.

### Claim 7 (depends on 6)

The camera system of claim 6, wherein a video analytics module includes the object detection module, the object tracking module, the match classifier, and the object search module, and wherein the rule engine uses the video analytics module to determine a rule violation.

### Claim 8 (depends on 1)

The camera system of claim 1, wherein:
the at least one capturing device includes a first image capturing device and a second image capturing device;
the image data includes first image data produced by the first image capturing device and second image data produced by the second image capturing device; and
the match classifier is further operable to determine that a first object detected in the first image data is the same as a second object detected in the second image data.

### Claim 9 (depends on 8)

The camera system of claim 8, wherein the match classifier is operable to make the determination by matching a first signature representing features of the first object with a second signature representing features of the second object.

### Claim 10 (depends on 9)

The camera system of claim 9, wherein the first signature is an average signature and the second signature is an average signature.

### Claim 11 (depends on 1)

The camera system of claim 1, wherein the camera system is operable to send a first signature of a detected object to a second camera system.

### Claim 12 (depends on 11)

The camera system of claim 11, further comprising:
a routing table including a probability that a detected object will also appear in a field of view of an image capturing device of the second camera system; and
a match notification responder operable to receive, from the second camera system, match notification information indicating whether a match to the first signature was detected at the second camera system, and is further operable to update the probability in the routing table based on the match notification information.

### Claim 13 (depends on 12)

The camera system of claim 12, wherein the match notification information includes a second signature of a matching object at the second camera system, and the match notification responder is operable to update the first signature with the second signature.

### Claim 14 (depends on 13)

The camera system of claim 13, wherein the first signature is updated with the second signature by averaging the first signature with the second signature to produce an updated first signature.

### Claim 15 (depends on 1)

The camera system of claim 1, further comprising:
a match database including one or more signatures received from a second camera system, the one or more signatures representing features of a remote object detected at the second camera system; and
wherein the match classifier is operable to determine whether the one or more signatures match any of the signatures of the objects detected the camera system.

### Claim 16 (depends on 15)

The camera system of claim 15, wherein, in response to the one or more signatures matching any of the signatures of the objects detected by the camera system, the match classifier is operable to update the signature of the object detected using the one or more signatures and send match notification information to the second camera system.

### Claim 17 (depends on 16)

The camera system of claim 16, wherein the signatures of the objects detected by the camera system are updated by averaging the signature of the object detected by the camera system with the one or more signatures.
