公开(公告)号：US12094236B2

公开(公告)日：2024-09-17

申请号：US17038528

申请日：2020-09-30

Applicant: Axis AB

Inventor： Markus Skans ,  Christian Colliander ,  Martin Ljungqvist ,  Willie Betschart ,  Niclas Danielsson

IPC: G06V10/80 ,  G06F18/214 ,  G06F18/22 ,  G06N3/045 ,  G06T5/50 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V40/00 ,  G06V40/10 ,  G06V40/20

CPC classification number: G06V40/107 ,  G06F18/214 ,  G06F18/22 ,  G06N3/045 ,  G06T5/50 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V40/23

Abstract: A method of object re-identification in images of objects comprises providing a plurality of neural networks for object re-identification, wherein each of the plurality of neural networks is trained on image data with different sets of anatomical features, each set being represented by a reference vector; receiving a plurality of images of objects and an input vector representing anatomical features that are depicted in all of the plurality of images; comparing the input vector with the reference vectors for determining, according to a predefined condition, the most similar reference vector; and inputting image data of the plurality of objects to the neural network represented by the most similar reference vector for determining whether the plurality of objects have the same identity.

公开(公告)号：US20240386579A1

公开(公告)日：2024-11-21

申请号：US18616830

申请日：2024-03-26

Applicant: Axis AB

Inventor： Niclas DANIELSSON ,  Christian Colliander ,  Amanda Nilsson ,  Sarah Laross

IPC: G06T7/215 ,  G06T7/246 ,  G06V10/25 ,  G06V10/40

Abstract: A method for prioritizing feature extraction for object re-identification in an object tracking application. Region of interests (ROI) for object feature extraction is determined based on motion areas in the image frame. Each object detected in an image frame and which is at least partly overlapping with a ROI is associated with the ROI. A list of candidate objects for feature extraction is determined by, for each ROI associated with two or more objects: adding each object of the two or more objects that is not overlapping with any of the other objects among the two or more objects with more than a threshold amount. From the list of candidate objects, at least one object is selected, and image data of the image frame depicting the selected object is used for determining a feature vector for the selected object.

公开(公告)号：US12293529B2

公开(公告)日：2025-05-06

申请号：US18616830

申请日：2024-03-26

Applicant: Axis AB

Inventor： Niclas Danielsson ,  Christian Colliander ,  Amanda Nilsson ,  Sarah Laross

IPC: G06V10/40 ,  G06T7/215 ,  G06T7/246 ,  G06V10/25

Abstract: A method for prioritizing feature extraction for object re-identification in an object tracking application. Region of interests (ROI) for object feature extraction is determined based on motion areas in the image frame. Each object detected in an image frame and which is at least partly overlapping with a ROI is associated with the ROI. A list of candidate objects for feature extraction is determined by, for each ROI associated with two or more objects: adding each object of the two or more objects that is not overlapping with any of the other objects among the two or more objects with more than a threshold amount. From the list of candidate objects, at least one object is selected, and image data of the image frame depicting the selected object is used for determining a feature vector for the selected object.

公开(公告)号：US12190590B2

公开(公告)日：2025-01-07

申请号：US17675019

申请日：2022-02-18

Applicant: Axis AB

Inventor： Jakob Grundström ,  Martin Ljungqvist ,  Simon Molin ,  Christian Colliander

IPC: G06V20/52 ,  G06T7/215 ,  G06T7/73

Abstract: A method for determining images plausible to have a false negative object detection comprises providing a group of historic trajectories, wherein each historic trajectory comprises a reference track that represents one or more historic tracks and comprises an object class of historic object detections that belong to the one or more historic tracks; performing tracking; performing object detection; for a determined track that does not match any determined object detection, comparing the determined track with reference tracks of historic trajectories for identifying a matching reference track; upon identifying a matching reference track, defining images of the determined track as being plausible to have a false negative object detection for the object class of the historic trajectory comprising the matching reference track; and upon not identifying a matching reference track, defining the determined track as a false positive track.