# US 2023/0410352 A1 · Method for object detection using cropped images

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

- Number: US 2023/0410352 A1
- Document ID: US20230410352A1
- Status: Published application
- Kind: A1
- Application number: 18/333,890
- Filed: 2023-06-13
- Published: 2023-12-21
- Earliest claimed: 2022-06-20
- Assignees: Axis AB
- Applicants: Axis AB
- Inventors: Ludvig HASSBRING; Song YUAN
- Web page: https://patentgrep.com/patent/US20230410352A1

## CPC

- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06N 3/045: Combinations of networks
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 3/4053: based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V 10/776: Validation; Performance evaluation
- G06V 10/82: using neural networks
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20132: Image cropping
- G06V 20/625: {License plates}
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 2201/07: Target detection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and control unit for object detection in a video stream captured with an image acquisition device, especially for the purpose of anonymizing objects in the video stream.

## Claims

### Claim 1

A method for object detection in an image, comprising:
obtaining first resolution image acquired by an image acquisition device;
scaling the first resolution image to a second resolution image with lower resolution than the resolution of the first resolution image;
analyzing the second resolution image to determine a first probability that a detected object of a predetermined type is present in an area of the first resolution image, where a predetermined type is an object that should be masked;
if the first probability is below a first threshold and above or equal to a second threshold, cropping the area including the detected object in the first resolution image, where probabilities exceeding or equal to the first threshold indicate that a detected object is of the predetermined type and probabilities below the second threshold indicate that a detected object is not of the predetermined type;
analyzing the cropped image to determine a second probability that the detected object is of the predetermined type; and
if the second probability exceeds or is equal to the first threshold, providing an indication that the detected object is of the predetermined type that should be masked.

### Claim 2 (depends on 1)

The method according to claim 1, wherein analyzing the second resolution image and analyzing the cropped image are performed in a neural network.

### Claim 3 (depends on 1)

The method according to claim 1, wherein analyzing the second resolution image is performed in a first neural network and analyzing the cropped image is performed in a second neural network.

### Claim 4 (depends on 1)

The method according to claim 1, further comprising:
(a) analyzing the cropped image to determine a further probability that a detected object of the predetermined type is present in an area of the cropped image;
(b) if the further probability is below the first threshold and above or equal to the second threshold, cropping the area of the detected object in the cropped image to form a further cropped image;
(c) analyzing the further cropped image to determine a still further probability that the detected object is of the predetermined type; and
(d) if the still further probability exceeds or is equal to the first threshold, providing an indication that the detected object is of the predetermined type,
wherein the steps (a)-(d) are recursively performed until a predetermined condition is fulfilled.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the steps (a)-(d) are recursively performed until at least one of the following conditions is fulfilled:
the further probability in step (b) is below the second threshold or exceeds or is equal to the first threshold;
a predetermined number of iterations; and
if a resolution of the further cropped image is below a predetermined resolution.

### Claim 6 (depends on 1)

The method according to claim 1, wherein analyzing the first resolution image comprises to determine probabilities that detected objects of the predetermined type is present in more than one area, where more than one respective area is cropped in the first resolution image and analyzed.

### Claim 7 (depends on 1)

The method according to claim 1, further comprising:
analyzing a set of second resolution images;
detecting motion in the set of second resolution images; and
if the detected motion exceeds or is equal to a motion threshold, cropping a further area in a subsequent image frame, analyzing the cropped image, and, if the second probability exceeds or is equal to the first threshold, providing an indication that the detected object is of the predetermined type.

### Claim 8 (depends on 7)

The method according to claim 7, wherein if the detected motion is below the motion threshold in a first image frame, reusing the outcome of the analyzing step to determine the second probability in a first frame on the same cropped area in a subsequent image frame.

### Claim 9 (depends on 1)

The method according to claim 1, wherein if the first probability exceeds or is equal to the first threshold, providing an indication that the detected object is of the predetermined type.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the resolution of the first resolution image is as captured by the image capturing device.

### Claim 11 (depends on 1)

The method according to claim 1, wherein the resolution of the second resolution image depends on a size of a neural network used for analyzing the second resolution image.

### Claim 12 (depends on 1)

The method according to claim 1, wherein the method is performed at a rate substantially corresponding to the frame rate of a captured video stream including the first resolution image.

### Claim 13

A control unit for object detection in an image, the control unit is configured to:
obtain first resolution image acquired by an image acquisition device;
scale the first resolution image to a second resolution image with lower resolution than the resolution of the first resolution image;
analyze the second resolution image to determine a first probability that a detected object of a predetermined type is present in an area of the first resolution image, where a predetermined type is an object that should be masked;
if the first probability is below a first threshold and above or equal to a second threshold, crop the area including the detected object in the first resolution image, where probabilities exceeding or equal to the first threshold indicate that a detected object is of the predetermined type and probabilities below the second threshold indicate that a detected object is not of the predetermined type;
analyze the cropped image to determine a second probability that the detected object is of the predetermined type; and
if the second probability exceeds or is equal to the first threshold, provide an indication that the detected object is of the predetermined type that should be masked.

### Claim 14

A system comprising: an image acquisition device for capturing images of a scene including objects; and a control unit for object detection in said images, the control unit is configured to:
obtain first resolution image acquired by an image acquisition device;
scale the first resolution image to a second resolution image with lower resolution than the resolution of the first resolution image;
analyze the second resolution image to determine a first probability that a detected object of a predetermined type is present in an area of the first resolution image, where a predetermined type is an object that should be masked;
if the first probability is below a first threshold and above or equal to a second threshold, crop the area including the detected object in the first resolution image, where probabilities exceeding or equal to the first threshold indicate that a detected object is of the predetermined type and probabilities below the second threshold indicate that a detected object is not of the predetermined type;
analyze the cropped image to determine a second probability that the detected object is of the predetermined type; and
if the second probability exceeds or is equal to the first threshold, provide an indication that the detected object is of the predetermined type that should be masked.

### Claim 15

A non-transitory computer-readable storage medium having stored thereon a computer program for object detection in an image, the computer program comprising computer code which, when run on processing circuitry of a controller causes the control unit to:
obtain first resolution image acquired by an image acquisition device;
scale the first resolution image to a second resolution image with lower resolution than the resolution of the first resolution image;
analyze the second resolution image to determine a first probability that a detected object of a predetermined type is present in an area of the first resolution image, where a predetermined type is an object that should be masked;
if the first probability is below a first threshold and above or equal to a second threshold, crop the area including the detected object in the first resolution image, where probabilities exceeding or equal to the first threshold indicate that a detected object is of the predetermined type and probabilities below the second threshold indicate that a detected object is not of the predetermined type;
analyze the cropped image to determine a second probability that the detected object is of the predetermined type; and
if the second probability exceeds or is equal to the first threshold, provide an indication that the detected object is of the predetermined type that should be masked.