# US 12,118,804 B2 · GPU based embedded vision solution

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

- Number: US 12,118,804 B2
- Document ID: US12118804B2
- Status: Granted
- Kind: B2
- Application number: 17/578,911
- Filed: 2022-01-19
- Published: 2023-04-20
- Granted: 2024-10-15
- Earliest claimed: 2021-10-14
- Assignees: Seekright Limited
- Applicants: Seekright Limited
- Inventors: Mohamed Salman Yusuf
- Web page: https://patentgrep.com/patent/US12118804B2

## CPC

- G06V 20/54: of traffic, e.g. cars on the road, trains or boats
- G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road}
- G06T 11/20: Drawing from basic elements
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06T 2210/12: Bounding box
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present invention relates to system and method that detects objects and assigns trackers to each object and maps it to detections to its corresponding Geo-Coordinates. Based on the number of detections, it assigns new trackers and counts the objects identified using optimal and efficient computation. The present system requires just one detection and its location to create a tracker accurately. Also, if an object is missing in any given location, the present system identifies the Geo-Coordinates and shows the image along with its details.

## Claims

### Claim 1

A system for identifying and analyzing roadway assets on a roadway, comprising:
a video capturing unit configured to record a video while patrolling on the roadway;
a comparison unit configured to detect fixed assets by comparing data from a master video with the video recorded by the video capturing unit;
an identification unit configured to identify random assets in the video recorded by the video capturing unit;
a global positioning system (GPS) unit configured to provide location coordinates for the fixed assets and the random assets, such that the system uses this information to identify and track the fixed assets; and
a tracker module configured to receive: coordinates of the fixed asset in a frame; a relative position of the fixed asset, wherein the relative position being relative to the center of the frame; and a speed of the video capturing unit at the time of recording the video, and predict coordinates of the fixed asset in a consecutive frame of the video based on the speed of the video capturing unit, the relative position of the fixed asset and coordinates of the fixed assets in the frame.

### Claim 2 (depends on 1)

The system as claimed in claim 1, wherein master video is obtained from one or more users.

### Claim 3 (depends on 1)

The system as claimed in claim 1, wherein the comparison unit extracts data from the master video.

### Claim 4 (depends on 1)

The system as claimed in claim 1, wherein the GPS unit can be based on satellite-based system for determining geo-coordinates.

### Claim 5 (depends on 1)

The system as claimed in claim 1, wherein the system monitors the roadways assets by detecting the fixed assets and identifying the random assets.

### Claim 6 (depends on 1)

The system as claimed in claim 1, wherein the tracker module is configured to generate a count which identifies missing objects and its location based on the count.

### Claim 7 (depends on 1)

The system as claimed in claim 1, further comprises a mapping module configured to compute distance between a reference point in the master video and the identified assets captured in the video, and cross map the identified asset to original database coordinates.

### Claim 8 (depends on 1)

The system as claimed in claim 1, further comprises a localizing module configured to map the identified assets to corresponding chainage blocks for accurate location identification.

### Claim 9

A method for identifying and analyzing roadway assets on a roadway, comprising:
using a video capturing unit, recording a video while patrolling on the roadway;
using a comparison unit, detecting fixed assets by comparing data from a master video with the video recorded by the video capturing unit;
using an identification unit, identifying random assets in the video recorded by the video capturing unit;
using a global positioning system (GPS) unit, providing location coordinates for the fixed assets and the random assets, such that the system uses this information to identify and track the fixed assets;
using a tracker module receiving coordinates of the fixed asset in a frame, a relative position of the fixed asset and a speed of the video capturing unit at the time of recording the video, wherein the relative position being relative to the center of the frame; and
using the tracker module, predicting coordinates of the fixed asset in a consecutive frame of the video based on the speed of the video capturing unit, the relative position of the fixed asset and coordinates of the fixed assets in the frame.

### Claim 10 (depends on 9)

The method as claimed in claim 9, wherein master video is obtained from one or more users.

### Claim 11 (depends on 9)

The method as claimed in claim 9, wherein the comparison unit extracts data from the master video.

### Claim 12 (depends on 9)

The method as claimed in claim 9, wherein the GPS unit is be based on satellite-based system for determining geo-coordinates.

### Claim 13 (depends on 9)

The method as claimed in claim 9, and further comprising monitoring the roadway assets by detecting the fixed assets and identifying the random assets.

### Claim 14 (depends on 9)

The method as claimed in claim 9, wherein using the tracker module to generate a count that identifies missing objects and a location of the identified missing object based on the count.

### Claim 15 (depends on 9)

The method as claimed in claim 9, and further comprising using a mapping module to compute distance between a reference point in the master video and the identified assets captured in the video, and to cross map the identified asset to original database coordinates.

### Claim 16 (depends on 9)

The method as claimed in claim 9, and further comprising using a localizing module to map the identified assets to corresponding chainage blocks for accurate location identification.
