Back to results
US 12,586,232 B2Granted
Method for object detection using cropped images
AssigneeAxis AB
InventorsLudvig Hassbring, Song Yuan
Life of this patent
Estimating the term…
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.
Claims14
A computer-implemented method for object detection in an image acquired by a camera of a surveillance system, comprising the steps of:
- obtaining first resolution image acquired by the camera;
- 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;
- 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, and
- if the second probability is below the first threshold and above or equal to the second threshold:
- (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.
10 more elements
A processing circuitry comprising one or more processors and memory storing instructions for object detection in an image acquired by a camera, the processing circuitry is configured to:
- obtain first resolution image acquired by the camera;
- 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;
- 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, and
- if the second probability is below the first threshold and above or equal to the second threshold:
- (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.
10 more elements
A system comprising:
- a camera for capturing images of a scene including objects;
- and a processing circuitry comprising one or more processors and memory storing instructions for object detection in said images, the processing circuitry is configured to:
- obtain first resolution image acquired by the camera;
- 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;
- 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,
- if the second probability is below the first threshold and above or equal to the second threshold:
- (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.
12 more elements
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 a processing circuitry comprising one or more processors causes the processing circuitry to:
- obtain first resolution image acquired by a camera of a surveillance system;
- 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;
- 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,
- if the second probability is below the first threshold and above or equal to the second threshold:
- (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.
10 more elements
Dependencies are inferred from the claim text.