IP Library Granted Patent US 12,450,947
Granted Patent B2
US 12,450,947 · App. 18/020,485 · Granted Oct 21, 2025

Device, method and system for providing a notification of a distinguishing activity

Inventors: Michal Filipowicz (Mogilno, PL); Pawel Jurzak (Cracow, PL); Marcin Witek (Cracow, PL); Jacek Doniec (Luborzyca, PL); Lukasz Kasprzyk (Nowa Wie Szlachecka, PL)
Assignee: MOTOROLA SOLUTIONS, INC.
G06V40/20G06V20/52G08B3/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,450,947
App. No.
18/020,485
Granted
Oct 21, 2025
Kind
B2
Abstract

A device, method and system for providing a notification of a distinguishing activity is provided. A devices receives information describing an appearance of a target object. The device determines, using the information, that the target object is located in images acquired by a camera. The device determines a distinguishing activity of the target object in the images. The device controls a notification device to provide a notification of the distinguishing activity.

Claims (65)

1. A method comprising:

receiving, at a computing device, information describing an appearance of a target object;

determining, at the computing device that the target object is located in images acquired by a camera by using the information to search the images via one or more of image analytics, video analytics and machine learning algorithms;

determining, at the computing device, a distinguishing activity of the target object in the images using one or more of the image analytics, the video analytics and the machine learning algorithms; and

controlling, by the computing device, a notification device to provide a notification of the distinguishing activity,

wherein determining the distinguishing activity of the target object in the images comprises:

determining that the target object is performing a given activity in a list of activities;

when one or more other objects in the images are not performing the given activity, determining that the distinguishing activity comprises the given activity; and

when at least one of the one or more other objects are performing the given activity: determining that the target object is performing a further activity of the list; and when the one or more other objects are not performing the further activity, determining that the distinguishing activity comprises the further activity.

2. The method of claim 1 , further comprising, when there is no single activity performed by the target object that distinguishes from respective activities performed by one or more other objects in the images, determining the distinguishing activity of the target object in the images by:

determining a combination of two or more activities of the target object that distinguish from respective combinations of the respective activities of the one or more other objects in the images.

3. The method of claim 1 , wherein determining the distinguishing activity of the target object in the images comprises:

determining one or more activities of the target object in the images;

determining one or more respective activities of one or more other objects in the images; and

determining that the distinguishing activity comprises one or more of the activities of the target object that distinguish from the one or more respective activities of the one or more other objects.

4. The method of claim 1 , wherein controlling the notification device to provide the notification of the distinguishing activity comprises:

controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity.

5. The method of claim 1 , wherein controlling the notification device to provide the notification of the distinguishing activity further comprises:

controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity and a respective audio description of the appearance of the target object.

6. The method of claim 1 , further comprising:

receiving, in real-time, the images acquired by the camera,

wherein determining that the target object is located in the images and determining the distinguishing activity of the target object occurs as the images are received.

7. The method of claim 1 , further comprising:

accessing the images acquired by the camera as previously stored at a memory,

wherein determining that the target object is located in the images and determining the distinguishing activity of the target object occurs using the images as previously stored.

8. The method of claim 1 , further comprising:

determining a time of the distinguishing activity in the images as previously stored at a memory,

wherein controlling the notification device to provide the notification of the distinguishing activity comprises: controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity and the time.

9. The method of claim 1 , further comprising:

determining a time of the distinguishing activity in the images;

identifying, using the time and the distinguishing activity, the target object in previously stored respective images from a further camera having a respective field-of-view that overlaps with a field-of-view of the camera; and

tracking the target object in one or more of the previously stored respective images from the further camera and respective real-time images from the further camera.

10. A device comprising:

a controller in communication with a camera and a notification device, the controller configured to:

receive information describing an appearance of a target object;

determine that the target object is located in images acquired by the camera by using the information to search the images via one or more of image analytics, video analytics and machine learning algorithms;

determine a distinguishing activity of the target object in the images using one or more of the image analytics, the video analytics and the machine learning algorithms; and

control the notification device to provide a notification of the distinguishing activity,

wherein the controller is further configured to determine the distinguishing activity of the target object in the images by:

determining that the target object is performing a given activity in a list of activities;

when one or more other objects in the images are not performing the given activity, determining that the distinguishing activity comprises the given activity; and

when at least one of the one or more other objects are performing the given activity: determining that the target object is performing a further activity of the list; and when the one or more other objects are not performing the further activity, determining that the distinguishing activity comprises the further activity.

11. The device of claim 10 , wherein the controller is further configured to: when there is no single activity performed by the target object that distinguishes from respective activities performed by one or more other objects in the images, determine the distinguishing activity of the target object in the images by:

determining a combination of two or more activities of the target object that distinguish from respective combinations of the respective activities of the one or more other objects in the images.

12. The device of claim 10 , wherein the controller is further configured to determine the distinguishing activity of the target object in the images by:

determining one or more activities of the target object in the images;

determining one or more respective activities of one or more other objects in the images; and

determining that the distinguishing activity comprises one or more of the activities of the target object that distinguish from the one or more respective activities of the one or more other objects.

13. The device of claim 10 , wherein the controller is further configured to control the notification device to provide the notification of the distinguishing activity by:

controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity.

14. The device of claim 10 , wherein the controller is further configured to control the notification device to provide the notification of the distinguishing activity by:

controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity and a respective audio description of the appearance of the target object.

15. The device of claim 10 , wherein the controller is further configured to:

receive, in real-time, the images acquired by the camera; and

determine that the target object is located in the images and determine the distinguishing activity of the target object as the images are received.

16. The device of claim 10 , wherein the controller is further configured to:

access the images acquired by the camera as previously stored at a memory accessible to the controller; and

determine that the target object is located in the images and determine the distinguishing activity of the target object using the images as previously stored.

17. The device of claim 10 , wherein the controller is further configured to:

determine a time of the distinguishing activity in the images as previously stored at a memory accessible to the controller; and

control the notification device to provide the notification of the distinguishing activity by: controlling an audio device, located with the camera, to provide an audio description of the distinguishing activity and the time.

18. The device of claim 10 , wherein the controller is in communication with a further camera having a respective field-of-view that overlaps with a field-of-view of the camera, and the controller is further configured to:

determine a time of the distinguishing activity in the images;

identify, using the time and the distinguishing activity, the target object in previously stored respective images from the further camera; and

track the target object in one or more of the previously stored respective images from the further camera and respective real-time images from the further camera.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 9, 2023
From: FILIPOWICZ, MICHAL; JURZAK, PAWEL; WITEK, MARCIN; DONIEC, JACEK; KASPRZYK, LUKASZ
To: MOTOROLA SOLUTIONS, INC.
Reel/Frame 062641/0601 →
Continuity (1)
Related Publication 20230290184A1 · Sep 14, 2023
References Cited (34)
US 7496553B2 · Cerrato · 2009 [cited by applicant]
US 8295597B1 · Sharma · 2012 [cited by examiner]
US 8786702B2 · Cobb et al. · 2014 [cited by applicant]
US 20030058111A1 · Lee · 2003 [cited by examiner]
US 20160127457A1 · Shaw · 2016 [cited by examiner]
US 20160203641A1 · Bostick · 2016 [cited by examiner]
US 20180050800A1 · Boykin et al. · 2018 [cited by applicant]
US 20180115749A1 · Toshiyuki · 2018 [cited by examiner]
US 20180330610A1 · Wu · 2018 [cited by examiner]
US 20190236377A1 · Otake · 2019 [cited by examiner]
US 20190266414A1 · Stawiszynski et al. · 2019 [cited by applicant]
US 20190286901A1 · Blanco et al. · 2019 [cited by applicant]
US 20200104603A1 · Zucker · 2020 [cited by examiner]
US 20200279390A1 · Koskan et al. · 2020 [cited by applicant]
EP 2270761A1 · 2011 [cited by applicant]
JP H09114988 · 1997 [cited by examiner]
JP 2010205191 · 2010 [cited by examiner]
JP 2012032910 · 2012 [cited by examiner]
WO 2002087443A1 · 2002 [cited by applicant]
WO 2020204735A1 · 2020 [cited by applicant]
P. Curtis, M. Harb, R. Abielmona and E. Petriu, “Behavior-driven video analytics system for critical infrastructure protection,” the 2014 Seventh IEEE Symposium on Computational Intelligence for Security and Defense App… [cited by examiner]
Breidenich, Markus, Examiner, International Search Report mailed Apr. 30, 2021, issued in the corresponding PCT Application No. PCT/PL2020/050070, Filed Sep. 28, 2020. [cited by applicant]
“Human Identification Based on Gait” https://books.google.pl/books?id=tD42mXCGRGcC; May 26, 2010. [cited by applicant]
Niu, Wei., et al., “Human Activity Detection and Recognition for Video Surveillance”, pp. 719-2722, 004 IEEE International Conference on Multimedia and Expo (ICME), https://ieeexplore.ieee.org/document/1394293. [cited by applicant]
Sharma, Chandra Mani, et al., “Oh Human Activity Recognition in Video Sequences”, International Conference on Computer & Communication Technology (ICCCT)-2011, downloaded on Jan. 31, 2023, https://ieeexplore.ieee.org/do… [cited by applicant]
Win, Sandar, et al., “Real-Time Human Motion Detection, Tracking and Activity Recognition with Skeletal Model”, downloaded on Jan. 31, 2023, https://ieeexplore.ieee.org/document/9022822. [cited by applicant]
Albukhary, N., et al., “Real-Time Human Activity Recognition”, 6th International Conference on Mechatronics—ICOM'17, IOP Conf. Series: Materials Science and Engineering 260 (2017) 012017. [cited by applicant]
Lu, Di, et al., “Entity-aware Image Caption Generation”, In proceedings of EMNLP 2018, arXiv:1804.07889; https://blender.cs.illinois.edu/paper/imagecaption.pdf. [cited by applicant]
Bulling, Andreas, et al., “A Tutorial on Human Activity Recognition Using Body-Worn Inertial Sensors”, (2013). ACM Computing Surveys. 46. 10.1145/2499621; https://perceptualui.org/publications/bulling14_csur.pdf. [cited by applicant]
Two Stream RNN CNN for action recognition in 3D videos YouTube; https://www.youtube.com/watch?v=GOPXKCEglo (Nov. 17, 2016). [cited by applicant]
Rui Hou T-CNN for Action Detection in Videos ICCV 2017 YouTube; https://www.youtube.com/watch?v=CNa18Y95kJU (Aug. 28, 2017). [cited by applicant]
Real-time event detection for video surveillance applications—YouTube; https://www.youtube.com/watch?v=QcCjmWwEUgg (Jun. 21, 2016). [cited by applicant]
Samsung Gallery—Apps on Google Play—https://web.archive.org/web/20200815135309/https://play.google.com/store/apps/details?id=com.sec.android.gallery3d (Aug. 15, 2020). [cited by applicant]
Amazon Rekognition—Video and Image—AWS—https://web.archive.org/web/20200926032030/https://aws.amazon.com/rekognition/ (Sep. 26, 2020). [cited by applicant]