# US 12,118,792 B2 · Surveillance camera system and surveillance camera control apparatus

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

- Number: US 12,118,792 B2
- Document ID: US12118792B2
- Status: Granted
- Kind: B2
- Application number: 17/328,834
- Filed: 2021-05-24
- Published: 2021-09-09
- Granted: 2024-10-15
- Earliest claimed: 2013-05-17
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Atsushi Kawano
- Web page: https://patentgrep.com/patent/US12118792B2

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G01S 7/415: {Identification of targets based on measurements of movement associated with the target}
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion}
- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V 40/166: {using acquisition arrangements}
- H04N 23/61: based on recognised objects
- H04N 23/611: where the recognised objects include parts of the human body
- B60W 2554/4044: Direction of movement, e.g. backwards
- B60W 2554/80: Spatial relation or speed relative to objects
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT

## Abstract

A surveillance system includes an acquisition unit configured to acquire motion information of an object detected from an image captured by an image capturing unit, an association unit configured to associate a recognition processing result of the object with the motion information, and a determination unit configured to determine, from among a plurality of objects detected from the image captured by the image capturing unit, an object to be subjected to recognition processing based on the recognition result associated with the motion information. Thus, even when a plurality of abnormal regions is simultaneously present in a region to be monitored, face recognition can be efficiently performed.

## Claims

### Claim 1

An information processing apparatus comprising:
one or more processors; and
a memory storing programs configured to be executed by the one or more processors, wherein the programs stored in the memory cause, when executed by the one or more processors, the one or more processors to operate to:
obtain motion directions for each of a first plurality of objects detected from a first image captured by a first image capturing device;
determine, from among the first plurality of objects detected from the first image, an object on which recognition processing is performed;
associate, in a case where the recognition processing performed on the object determined from among the plurality of objects detected from the first image is failure, failure information indicating that the recognition processing is failure with a motion direction of the object;
determine a target object on which the recognition processing is performed from among a second plurality of objects detected from a second image captured after the first image by the first image capturing device based on a score of each of the second plurality of objects, wherein the score is determined by the one or more processors based on the failure information and the associated motion direction so that a score of a first object whose motion direction in the second image falls within a predetermined range from a motion direction of an object in the first image on which the recognition processing is failure is lower than a score of a second object whose motion direction in the second image does not fall within the predetermined range in a condition where the moving speeds of the first and second objects in the second image are the same with each other; and
perform the recognition processing on the target object in the second image which is captured by the first image capturing device.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1, wherein the first image capturing device is a wide-angle camera or a pan-tilt-zoom (PTZ) camera.

### Claim 3 (depends on 2)

The information processing apparatus according to claim 2, wherein the one or more processors further operate to:
control a zoom magnification of a second image capturing device to obtain a zoomed image of the target object, and
extract a feature amount of the target object in the zoomed image captured by the second image capturing device,
wherein the recognition processing is to specify the target object in the zoomed image captured by the second image capturing device from an object stored in a database by comparison between the extracted feature amount of the target object in the zoomed image captured by the second image capturing device and a feature amount stored in the database.

### Claim 4 (depends on 3)

The information processing apparatus according to claim 3, wherein the zoomed image is captured so that a rectangle of the target object satisfies a predetermined percentage of the zoomed image.

### Claim 5 (depends on 3)

The information processing apparatus according to claim 3, wherein the zoom magnification of the second image is controlled to obtain the zoomed image of an abnormal region determined based on a score from among a plurality of abnormal regions in each of which one or more objects are detected from the second image.

### Claim 6 (depends on 1)

The information processing apparatus according to claim 1, wherein the score is determined by the one or more processors so that the score of the first object is higher than a score of a third object detected from the second image in a case where moving directions of the first and third objects are the same with each other and a moving speed of the first object is lower than a moving speed of the third object.

### Claim 7 (depends on 1)

The information processing apparatus according to claim 1, wherein the one or more processors update a moving direction and a moving speed in tracking information corresponding to an object in a case where the recognition processing on the object is failure.

### Claim 8

A method for an information processing apparatus, the method comprising:
obtaining motion directions for each of a first plurality of objects detected from a first image captured by a first image capturing device;
determining, from among the first plurality of objects detected from the first image, an object on which recognition processing is performed;
associating, in a case where the recognition processing performed on the object determined from among the plurality of objects detected from the first image is failure, failure information indicating that the recognition processing is failure with a motion direction of the object;
determining a target object on which the recognition processing is performed from among a second plurality of objects detected from a second image captured after the first image by the first image capturing device based on a score of each of the second plurality of objects, wherein the score is determined by the one or more processors based on the failure information and the associated motion direction so that a score of a first object whose motion direction in the second image falls within a predetermined range from a motion direction of an object in the first image on which the recognition processing is failure is lower than a score of a second object whose motion direction in the second image does not fall within the predetermined range in a condition where the moving speeds of the first and second objects in the second image are the same with each other; and
performing the recognition processing on the target object in the second image which is captured by the first image capturing device.