# US 2022/0035022 A1 · Process for monitoring vehicles by a plurality of sensors

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

- Number: US 2022/0035022 A1
- Document ID: US20220035022A1
- Status: Published application
- Kind: A1
- Application number: 17/443,373
- Filed: 2021-07-26
- Published: 2022-02-03
- Earliest claimed: 2020-07-31
- Assignees: Idemia Identity & Security France
- Applicants: Idemia Identity & Security France
- Inventors: Samuel ALLIOT; Grégoire CARRION; Eric GUIDON; Nicolas FOUGEROUX
- Web page: https://patentgrep.com/patent/US20220035022A1

## CPC

- G01S 13/92: for velocity measurement
- G01S 13/931: of land vehicles
- G01S 7/2955: {Means for determining the position of the radar coordinate system for evaluating the position data of the target in another coordinate system (G01S7/24 takes precedence; sighting devices adapted for indirect laying of fire F41G3/16; inertial navigation G01C21/16)}
- G01S 13/865: {Combination of radar systems with lidar systems}
- G01S 13/867: {Combination of radar systems with cameras}
- 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
- G08G 1/017: identifying vehicles (G08G1/015, G08G1/054 take precedence)
- G08G 1/04: using optical or ultrasonic detectors
- G08G 1/054: photographing overspeeding vehicles
- G01S 2013/932: {using own vehicle data, e.g. ground speed, steering wheel direction}
- G01S 2013/9325: {for inter-vehicle distance regulation, e.g. navigating in platoons}
- G08G 1/048: with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})

## Abstract

The invention relates to a process for monitoring vehicles on a road by a system comprising at least one radar sensor and a second sensor different from the radar sensor, wherein the second remote sensor is a time-of-flight optical sensor or optical image sensor, the process comprising a temporal readjustment and a spatial matching in order to obtain a set of measurement points each assigned to first characteristics derived from the radar data and second characteristics derived from the optical data, the determination of the radar vehicle trackings and of the optical vehicle trackings, a comparison of similarity between the radar vehicle trackings and the optical vehicle trackings, the elimination of the radar vehicle trackings for which no optical vehicle tracking is similar, the process comprising monitoring a parameter derived from first characteristics of a retained radar vehicle tracking.

## Claims

### Claim 1

A process for monitoring vehicles (3, 4) on a road (2) comprising at least two traffic lanes (2a, 2b), by a system for monitoring vehicles (1) arranged in a fixed manner and comprising at least one radar sensor (10) and a second remote sensor (20) different from the radar sensor (10), the radar sensor (10) operating over a radar detection range (11) of the road covering at least two traffic lanes and emitting a stream of radar data representative of the detection of vehicles (3, 4) on the road (2), the second remote sensor (20) operating over a second detection range (21) of the road (2), the radar detection range (11) and the second detection range (21) being at least partially superimposed,
wherein the second remote sensor (20) is an optical sensor emitting a stream of optical data representative of the detection of vehicles (3, 4) on the road (2), said optical sensor (20) being a time-of-flight optical sensor or an optical image sensor,
the process comprising, in a continually repeated manner for a plurality of successive frames:
a) temporal readjustment and spatial matching (S3) in a fixed shared spatial marker of the radar data and of the optical data in order to obtain a set of measurement points each assigned to first characteristics derived from the radar data comprising position measurements and speed measurements, and second characteristics derived from the optical data, the second characteristics comprising at least position measurements,
b) determination of radar vehicle trackings (S4) from the first characteristics derived from the radar data and optical vehicle trackings (S5) from the second characteristics derived from the optical data, comprising:
b1) a first segmentation which groups together, in first clusters, measurement points having first characteristics derived from radar data evolving in a similar way over several consecutive frames, the following over time of a first cluster forming a radar vehicle tracking (3, 4),
b2) a second segmentation which groups together, in second clusters, measurement points having second characteristics derived from optical data evolving in a similar way over several consecutive frames, the following over time of a second cluster forming an optical vehicle tracking (3, 4),
c) comparison of similarity between the radar vehicle trackings and the optical vehicle trackings, the comparison of similarity being based at least on the presence of shared measurement points over several consecutive frames, and matching of similar radar and optical vehicle trackings,
d) elimination of the radar vehicle trackings for which no optical vehicle tracking is similar, in order to retain only the radar vehicle trackings for which at least one optical vehicle tracking is similar,
the process comprising:
e) monitoring a parameter derived from first characteristics of a retained radar vehicle tracking,
and wherein, after the comparison of similarity between the radar vehicle trackings and the optical vehicle trackings, when an optical vehicle tracking does not have any similar radar vehicle tracking, the monitored parameter is derived from first characteristics derived from radar data corresponding to measurement points of the second aggregated of said optical vehicle tracking.

### Claim 2 (depends on 1)

The process according to claim 1, wherein the system for monitoring vehicles 1 is arranged in a fixed manner outside the traffic lanes (2a, 2b) of the road, at at least 0.5 m from the edge of a traffic lane (2a, 2b) and at a height of greater than 1.2 m from a surface of said traffic lanes (2a, 2b).

### Claim 3 (depends on 1)

The process according to claim 1, wherein the second characteristics of an optical vehicle tracking comprise dimensions of the vehicle (3, 4), the monitoring of a parameter comprising assigning, based on the dimensions assigned to said vehicle (3, 4), a dimension class to said optical vehicle tracking and/or to a retained radar vehicle tracking similar to said optical vehicle tracking, the parameter being monitored based on the dimension class.

### Claim 4 (depends on 1)

The process according to claim 1, wherein the parameter monitored is derived from first speed measurements determined by means of the radar.

### Claim 5 (depends on 1)

The process according to claim 1, wherein, following the comparison of similarity between the radar vehicle trackings and the optical vehicle trackings, a radar vehicle tracking is maintained even in the absence of a similar optical vehicle tracking, when said radar vehicle tracking previously had a similar optical vehicle tracking.

### Claim 6 (depends on 1)

The process according to claim 1, wherein the optical sensor (20) is an optical image sensor that acquires images of the second detection range (21) of the road, and the emitting of the stream of optical data representative of the detection of vehicles (3, 4) on the road comprises an analysis of the images acquired, involving a pattern recognition in order to carry out a second segmentation which groups together, in second clusters, measurement points having second characteristics that evolve in a similar manner over time.

### Claim 7 (depends on 1)

The process according to claim 1, wherein the optical sensor (20) is a lidar sensor.

### Claim 8 (depends on 1)

A system for monitoring vehicles (1) comprising at least one radar sensor (10) and a second remote sensor (20) different from the radar sensor (10), the second remote sensor (20) being an optical sensor, said optical sensor (20) being a time-of-flight optical sensor or an optical image sensor, the system for monitoring vehicles (1) being configured to be arranged in a fixed manner in the vicinity of a road comprising at least two traffic lanes (2a, 2b), the radar sensor (10) being configured to operate over a radar detection range (11) of the road covering at least two traffic lanes (2a, 2b) and to emit a stream of radar data representative of the detection of vehicles (3, 4) on the road (2), the optical sensor (20) being configured to operate over a second detection range (21) of the road (2) covering at least two traffic lanes (2a, 2b) and to emit a second stream of optical data representative of the detection of vehicles (3, 4) on the road (2), the radar detection range (11) and the second detection range (21) being at least partially superimposed, the system for monitoring vehicles (1) being configured to implement the process according to claim 1.