Granted Patent B2

US 12,293,529 · App. 18/616,830 · Granted May 6, 2025

Inventors: Niclas Danielsson (Lund, SE); Christian Colliander (Lund, SE); Amanda Nilsson (Lund, SE); Sarah Laross (Lund, SE)

Assignee: AXIS AB

G06T7/215G06T7/246G06V10/25G06V10/40

Abstract

Claims (41)

1. A computer-implemented method for prioritizing objects for feature extraction for the purpose of object re-identification in an object tracking application, comprising the steps of:

receiving an image frame depicting a scene comprising a plurality of objects;

receiving object detection data comprising, for each of the plurality of objects, localization data indicating location and spatial extent of the object in the image frame;

receiving motion data indicating one or more motion areas in the image frame, each motion area corresponding to an area in the scene where motion has been detected, wherein the motion data further comprises, for each motion area in the image frame, an indication of a velocity of the detected motion in the corresponding area of the scene;

for each motion area, determining a region of interest (ROI) for object feature extraction in the image frame, the ROI for object feature extraction overlapping with the motion area, and extending the ROI based on the velocity;

for each ROI for object feature extraction, determining a list of objects at least partly overlapping with the ROI for object feature extraction using the object detection data, and associating the ROI for object feature extraction with the list of objects;

determining a list of prioritized candidate objects for feature extraction by, for each ROI for object feature extraction associated with two or more objects:

for each object of the two or more objects, upon determining that the object is not overlapping with any of the other objects of the plurality of objects with more than a threshold amount, adding the object to the list of prioritized candidate objects for feature extraction; and

selecting at least one object among the list of prioritized candidate objects, and for each selected object determining a feature vector for the selected object based on image data of the image frame according to the localization data of the object.

2. The method of claim 1 , wherein the step of determining an ROI for object feature extraction comprises extending the motion area by a predetermined extent in each direction.

3. The method of claim 2 , wherein the ROI for object feature extraction is determined by extending the motion area to a greater extent in a direction corresponding to the direction of the velocity compared to a direction not corresponding to the direction of the velocity.

4. The method of claim 1 , wherein a shape of the ROI for object feature extraction is one of: a pixel mask, a circle, an ellipse, or a rectangle.

5. The method of claim 1 , wherein the threshold amount is 0.

6. The method of claim 1 , wherein the threshold amount is a predetermined percentage of the spatial extent of one of the overlapping objects.

7. The method of claim 1 , wherein a maximum of N objects among the list of prioritized candidate objects is selected, wherein N is a predetermined number.

8. The method of claim 7 , wherein upon the list of prioritized candidate objects comprising more than N objects, the step of selecting comprises comparing each prioritized candidate object to one or more selection criteria, and selecting the N objects meeting at least one of the one or more selection criteria.

9. The method of claim 7 , wherein upon the list of prioritized candidate objects comprising more than N objects, the step of selecting comprises ranking each prioritized candidate object according to one or more ranking criteria, and selecting the N highest ranked objects.

10. The method of claim 1 , further comprising the step of:

for each selected object, associating the determined feature vector with at least parts of the localization data of the selected object.

11. The method of claim 1 , further comprising the step of:

for each selected object, associating the determined feature vector with a time stamp indicating a capturing time of the image frame.

12. A system for prioritizing feature extraction for object re-identification in an object tracking application, comprising:

one or more processors; and

one or more non-transitory computer-readable media storing computer executable instructions that, when executed by the one or more processors, cause the system to perform actions comprising:

receiving an image frame depicting a scene comprising a plurality of objects;

receiving object detection data comprising, for each of the plurality of objects, localization data indicating location and spatial extent of the object in the image frame;

receiving motion data indicating one or more motion areas in the image frame, wherein the motion data further comprises, for each motion area in the image frame, an indication of a velocity of the detected motion in the corresponding area of the scene, each motion area corresponding to an area in the scene where motion has been detected;

for each motion area, determining a region of interest (ROI) for object feature extraction in the image frame, the ROI for object feature extraction overlapping with the motion area, and extending the ROI based on the velocity;

for each ROI for object feature extraction, determining a list of objects at least partly overlapping with the ROI for object feature extraction using the object detection data, and associating the ROI for object feature extraction with the list of objects;

determining a list of prioritized candidate objects for feature extraction by, for each ROI for object feature extraction associated with two or more objects:

for each object of the two or more objects, upon determining that the object is not overlapping with any of the other objects of the plurality of objects with more than a threshold amount, adding the object to the list of prioritized candidate objects for feature extraction; and

selecting at least one object among the list of prioritized candidate objects, and for each selected object determining a feature vector for the selected object based on image data of the image frame according to the localization data of the object.

13. At least one non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:

receiving an image frame depicting a scene comprising a plurality of objects;

receiving object detection data comprising, for each object of the plurality of objects, localization data indicating location and spatial extent of the object in the image frame;

receiving motion data indicating one or more motion areas in the image frame, wherein the motion data further comprises, for each motion area in the image frame, an indication of a velocity of the detected motion in the corresponding area of the scene, each motion area corresponding to an area in the scene where motion has been detected;

for each motion area, determining a region of interest (ROI) for object feature extraction in the image frame, the ROI for object feature extraction overlapping with the motion area, and extending the ROI based on the velocity;

for each ROI for object feature extraction, determining a list of objects at least partly overlapping with the ROI for object feature extraction using the object detection data, and associating the ROI for object feature extraction with the list of objects;

determining a list of prioritized candidate objects for feature extraction by, for each ROI for object feature extraction associated with two or more objects:

for each object of the two or more objects, upon determining that the object is not overlapping with any of the other objects of the plurality of objects with more than a threshold amount, adding the object to the list of prioritized candidate objects for feature extraction; and

selecting at least one object among the list of prioritized candidate objects, and for each selected object determining a feature vector for the selected object based on image data of the image frame according to the localization data of the object.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (17)