# US 2021/0240851 A1 · System and method for privacy-aware analysis of video streams

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

- Number: US 2021/0240851 A1
- Document ID: US20210240851A1
- Status: Published application
- Kind: A1
- Application number: 17/168,654
- Filed: 2021-02-05
- Published: 2021-08-05
- Earliest claimed: 2020-02-05
- Assignees: C2Ro Cloud Robotics Inc.
- Applicants: C2RO Cloud Robotics Inc.
- Inventors: Riccardo Badalone; Soodeh Farokhi; Amir Abbas Haji Abolhassani; Felix-Olivier Duguay; Neil Barrett; Mostafa Erfani; Aldo Enrique Enrique Vargas Moreno
- Web page: https://patentgrep.com/patent/US20210240851A1

## CPC

- G06F 21/60: Protecting data
- G06F 16/73: Querying
- G06F 16/784: {the detected or recognised objects being people}
- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06V 20/48: {Matching video sequences}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/167: {using comparisons between temporally consecutive images}
- H04N 7/181: {for receiving images from a plurality of remote sources}
- H04W 4/029: Location-based management or tracking services
- H04W 12/02: Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
- G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A method and system for privacy-aware movement tracking includes receiving a series of images of a field of view, such as captured by a camera. The images containing movement of an unidentified person within the field of view. A body region corresponding to the person is detected within the images. A movement dataset for the unidentified person is generated based on tracking movement of the body region over the fired of view within the images is generated. A characterizing feature set is determined for the unidentified person. The set is associated within the movement dataset to form a first track entry. Anonymizing of the body region can be applied to remove identifying features while or prior to determining the characterizing feature set. A second track entry can be generated from a second series of images and match between the track entries can be determined. A method and system for privacy-aware operation and learning of a computer-implemented classification module is also contemplated.

## Claims

### Claim 1

A method for privacy-aware movement tracking, the method comprising:
receiving a first series of images containing movement of a first unidentified person;
generating a first movement dataset for the first unidentified person based on tracking movement of the first unidentified person within the first series of images;
determining a first characterizing feature set for the first unidentified person;
associating the first characterizing feature set with the first movement dataset, thereby forming a first track entry;
receiving a second series of images containing movement of a second unidentified person;
generating a second movement dataset for the second unidentified person based on tracking movement of the second unidentified person within the second series of images;
determining a second characterizing feature set for the second unidentified person;
associating the second characterizing feature set with the second movement dataset, thereby forming a second track entry; and
determining a match between the first track entry and the second track entry.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining a match between the first track entry and the second track entry comprises determining a matching level between the first characterizing feature set and the second characterizing feature set.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first series of images are captured of a first field of view;
wherein the second series of images are captured of a second field of view.

### Claim 4 (depends on 3)

The method of claim 3, wherein the first series of images is captured by a first camera having the first field of view; and
wherein the second series of images is captured by a second camera having the second field of view.

### Claim 5 (depends on 3)

The method of claim 3, wherein determining the match comprises:
determining whether the first track entry and the second track entry satisfy a set of constraints predetermined according to a physical relationship between the first field of view and the second field of view.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the match between the first track entry and the second track entry indicates the first unidentified person and the second unidentified person are the same real-world person.

### Claim 7 (depends on 1)

The method of claim 1, wherein if a match between the first track entry and the second track entry is determined, linking the first movement dataset and the second movement dataset.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
for at least one given image of the first series of images, anonymizing a first body region corresponding to the first unidentified person by applying at least one removal of identifying features within the first body region, thereby generating a first anonymized body region;
for at least one given image of the second series of images, anonymizing a second body region corresponding to the second unidentified person by applying at least one removal of identifying features within the second body region, thereby generating a second anonymized body region;
wherein the first characterizing feature set for the first unidentified person is determined based on processing of the first anonymized body region;
wherein the first characterizing feature set based on the first anonymized body region is associated with the first movement dataset to form the first track entry;
wherein the second characterizing feature set for the second unidentified person is determined based on processing of the second anonymized body region; and
wherein the second characterizing feature set based on the second anonymized body region is associated with the second movement dataset to form the second track entry.

### Claim 9 (depends on 8)

The method of claim 8, wherein the at least one removal of identifying features within the first body region comprises removal of at least one uniquely identifying biometric feature;
wherein the at least one removal of identifying features within the second body region comprises removal of at least one uniquely identifying biometric feature.

### Claim 10 (depends on 8)

The method of claim 8, wherein the at least one removal of identifying features within the first body region comprises:
detecting a first face subregion within the first body region; and
masking the detected first face subregion; and
wherein the at least one removal of identifying features within the second body region comprises:
detecting a second face subregion within the second body region;
and
masking the detected second face subregion.

### Claim 11 (depends on 8)

The method of claim 8, wherein the at least one removal of identifying features within the first body comprises randomly distorting the first body region to remove a silhouette of the first body region as a uniquely identifying feature; and
wherein the at least one removal of identifying features within the second body comprises randomly distorting the second body region to remove a silhouette of the second body region as a uniquely identifying feature.

### Claim 12 (depends on 11)

The method of claim 11, wherein randomly distorting the first body region comprises modifying the first body region by a first random aspect ratio;
wherein randomly distorting the second body region comprises modifying the second body region by a second random aspect ratio.

### Claim 13 (depends on 1)

The method of claim 1, wherein the first characterizing feature set comprises one or more of a color pattern, accessory feature set, color features, clothing features and personal accessory features.

### Claim 14 (depends on 1)

The method of claim 1 wherein the first characterizing feature set is insufficient for determining a unique identity of the first unidentified person; and
wherein the second characterizing feature set is insufficient for determining a unique identity of the second unidentified person.

### Claim 15 (depends on 1)

The method of claim 1, wherein the first characterizing feature set is determined free of applying any biometric template generation; and
wherein the second characterizing feature set is determined free of applying any biometric template generation.

### Claim 16 (depends on 8)

The method of claim 8, wherein anonymizing the first body region and anonymizing the second body region are carried out at a secured network location; and
wherein the secured network location is shared with a surveillance system having a plurality of cameras.

### Claim 17

A system for performing privacy-aware movement tracking, the system comprising:
at least one processor;
at least one memory coupled to the processor and storing instructions executable by the processor and that such execution causes the processor to perform operations comprising:
receiving a first series images of containing movement of a first unidentified person;
generating a first movement dataset for the first unidentified person based on tracking movement of the first unidentified person within the first series of images;
determining a first characterizing feature set for the first unidentified person;
associating the first characterizing feature set with the first movement dataset, thereby forming a first track entry;
receiving a second series of images containing movement of a second unidentified person;
generating a second movement dataset for the second unidentified person based on tracking movement of the second unidentified person within the second series of images;
determining a second characterizing feature set for the second unidentified person;
associating the second characterizing feature set with the second movement dataset, thereby forming a second track entry; and
determining a match between the first track entry and the second track entry.

### Claim 18 (depends on 17)

The system of claim 17, wherein determining a match between the first track entry and the second track entry comprises determining a matching level between the first characterizing feature set and the second characterizing feature set.

### Claim 19 (depends on 17)

The system of claim 17, wherein the first series of images are captured of a first field of view;
wherein the second series of images are captured of a second field of view.

### Claim 20 (depends on 19)

The system of claim 19, wherein the first series of images is captured by a first camera having the first field of view; and
wherein the second series of images is captured by a second camera having the second field of view.

### Claim 21 (depends on 19)

The system of claim 19, wherein determining the match comprises:
determining whether the first track entry and the second track entry satisfy a set of constraints predetermined according to a physical relationship between the first field of view and the second field of view.

### Claim 22 (depends on 17)

The system of claim 17, wherein determining the match between the first track entry and the second track entry indicates the first unidentified person and the second unidentified person are the same real-world person.

### Claim 23 (depends on 17)

The system of claim 17, wherein if a match between the first track entry and the second track entry is determined, linking the first movement dataset and the second movement dataset.

### Claim 24 (depends on 17)

The system of claim 17, wherein the at least one processor is further configured for:
for at least one given image of the first series of images, anonymizing a first body region corresponding to the first unidentified person by applying at least one removal of identifying features within the first body region, thereby generating a first anonymized body region;
for at least one given image of the second series of images, anonymizing a second body region corresponding to the second unidentified person by applying at least one removal of identifying features within the second body region, thereby generating a second anonymized body region;
wherein the first characterizing feature set for the first unidentified person is determined based on processing of the first anonymized body region;
wherein the first characterizing feature set based on the first anonymized body region is associated with the first movement dataset to form the first track entry;
wherein the second characterizing feature set for the second unidentified person is determined based on processing of the second anonymized body region; and
wherein the second characterizing feature set based on the second anonymized body region is associated with the second movement dataset to form the second track entry.

### Claim 25 (depends on 24)

The system of claim 24, wherein the at least one removal of identifying features within the second body region comprises removal of at least one uniquely identifying biometric feature;
wherein the at least one removal of identifying features within the second body region comprises removal of at least one uniquely identifying biometric feature.

### Claim 26 (depends on 24)

The system of claim 24, wherein the at least one removal of identifying features within the first body region comprises:
detecting a first face subregion within the first body region; and
masking the detected first face subregion; and
wherein the at least one removal of identifying features within the second body region comprises:
detecting a second face subregion within the second body region;
and
masking the detected second face subregion.

### Claim 27 (depends on 24)

The system of claim 24, wherein the at least one removal of identifying features within the first body comprises randomly distorting the first body region to remove a silhouette of the first body region as a uniquely identifying feature; and
wherein the at least one removal of identifying features within the second body comprises randomly distorting the second body region to remove a silhouette of the second body region as a uniquely identifying feature.

### Claim 28 (depends on 27)

The system of claim 27, wherein randomly distorting the first body region comprises modifying the first body region by a first random aspect ratio;
wherein randomly distorting the second body region comprises modifying the second body region by a second random aspect ratio.

### Claim 29 (depends on 17)

The system of claim 17, wherein the first characterizing feature set comprises one or more of a color pattern, accessory feature set, color features, clothing features and personal accessory features.

### Claim 30 (depends on 17)

The system of claim 17, wherein the first characterizing feature set is insufficient for determining a unique identity of the first unidentified person; and
wherein the second characterizing feature set is insufficient for determining a unique identity of the second unidentified person.

### Claim 31 (depends on 17)

The system of claim 17, wherein the first characterizing feature set is determined free of applying any biometric template generation; and
wherein the second characterizing feature set is determined free of applying any biometric template generation.

### Claim 32 (depends on 24)

The system of claim 24, wherein anonymizing the first body region and anonymizing the second body region are carried out at a secured network location; and
wherein the secured network location is shared with a surveillance system having a plurality of cameras, including the first camera and the second camera.