# US 2022/0044045 A1 · Method for associating objects in a video

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

- Number: US 2022/0044045 A1
- Document ID: US20220044045A1
- Status: Published application
- Kind: A1
- Application number: 17/275,172
- Filed: 2018-09-11
- Published: 2022-02-10
- Earliest claimed: 2018-09-11
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Volodya Grancharov; Charles Kinuthia; Sigurdur Sverrisson
- Web page: https://patentgrep.com/patent/US20220044045A1

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/82: using neural networks
- G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The invention relates to a computer implemented method for associating objects in a video comprising subsequent frames, the method comprising obtaining first object proposal region information of a previous frame, determining second object proposal region information of a current frame, wherein the first and second object proposal region information are at least indicative of an appearance measure, a spatial location and a detection probability of each object proposal region of the respective frame, associating objects in the video by at least associating a first set of object proposal regions of the previous frame to a second set of object proposal regions of the current frame, wherein the object proposal regions are associated using distance measures calculated based on the appearance measures, the spatial locations and the detection probabilities.

## Claims

### Claim 1

A computer implemented method for associating proposal regions representing objects in a video comprising subsequent frames, the method comprising:
obtaining first object proposal region information of a previous frame,
determining second object proposal region information of a current frame,
wherein the first and second object proposal region information are at least indicative of an appearance measure, a spatial location and a detection probability of each object proposal region of the respective frame,
associating objects in the video by at least associating a first set of object proposal regions of the previous frame to a second set of object proposal regions of the current frame, wherein the object proposal regions are associated using distance measures calculated based on the appearance measures, the spatial locations and the detection probabilities.

### Claim 2 (depends on 1)

The method according to claim 1, wherein associating objects in the video further comprises:
mapping a first set of object proposal regions of the previous frame to a second set of object proposal regions of the current frame based on minimum distances of the distance measures,
adapting the detection probability of each mapped object proposal region of the current frame,
detecting objects of the current frame by determining mapped object proposal regions of the current frame having a detection probability above a threshold.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the distance measures between object proposal regions of the previous frame and the object proposal regions of the current frame are calculated as: Dn,n−1=d(Xn,Xn−1)+d(cn,cn−1), wherein d(Xn,Xn−1) is a combined spatial-probability distance measure and d(cn,cn−1) is an appearance distance measure.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the distance measures are calculated as a weighted sum of the combined spatial-probability distance measure and the appearance distance measure.

### Claim 5 (depends on 3)

The method according to claim 3, wherein the object proposal region is formed as a rectangle having a two dimensional center coordinate x,y, a width w and a height h, wherein the spatial-probability distance measure is calculated based on vectors formed by:
X=[x, y, w, h, p], wherein p detection probability of the object proposal region.

### Claim 6 (depends on 3)

The method according to claim 3, wherein the detection probability of each mapped object proposal region of the current frame is adapted if the corresponding appearance distance measure is below a second threshold.

### Claim 7 (depends on 1)

A computer configured to perform the method according to claim 1.

### Claim 8 (depends on 1)

A computer program comprising computer-executable instructions for causing a computer, when the computer-executable instructions are executed on a processing unit comprised in the computer, to perform any of the method steps according to claim 1.

### Claim 9 (depends on 8)

A computer program product comprising a computer-readable storage medium, the computer-readable storage medium having the computer program according to claim 8 embodied therein.

### Claim 10 (depends on 8)

A carrier containing the computer program according to claim 8, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.
