# US 10,482,332 B2 · Pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle

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

- Number: US 10,482,332 B2
- Document ID: US10482332B2
- Status: Granted
- Kind: B2
- Application number: 15/562,398
- Filed: 2016-04-01
- Published: 2018-04-26
- Granted: 2019-11-19
- Earliest claimed: 2015-04-02
- Assignees: Denso Corporation
- Applicants: Denso Corporation
- Inventors: Takahiro Baba
- Web page: https://patentgrep.com/patent/US10482332B2

## CPC

- G01S 7/412: {based on a comparison between measured values and known or stored values}
- B60T 7/22: initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle {, or by means of contactless obstacle detectors mounted on the vehicle}
- B60T 8/17: Using electrical or electronic regulation means to control braking {(detecting or indicating faulty operation B60T8/885)}
- G01S 13/867: {Combination of radar systems with cameras}
- G01S 13/931: of land vehicles
- 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
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G08G 1/166: {for active traffic, e.g. moving vehicles, pedestrians, bikes}
- B60R 21/00: Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks (safety belts or body harnesses in vehicles B60R22/00; seats constructed to protect the occupant from the effect of abnormal g-forces, e.g. crash or safety seats, B60N2/42; energy-absorbing arrangements for hand wheels for steering vehicles B62D1/11; energy-absorbing arrangements for vehicle steering columns B62D1/19)
- B60T 2201/022: Collision avoidance systems
- B60T 2210/32: Vehicle surroundings
- B60Y 2400/3015: Optical cameras
- B60Y 2400/3017: Radars
- G01S 2013/93185: {Controlling the brakes}
- 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
- B60T: VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL (electrodynamic brake systems for vehicle, in general B60L; brakes per se, i.e. devices where braking effect occurs, including ultimate brake actuators, F16D); ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- 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})
- B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60Y: INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY

## Abstract

In a pedestrian determining apparatus, an object detecting unit detects, based on waves reflected by an object, the object as a radar-based object. The reflected waves are generated based on reflection, by the object, of radar waves transmitted ahead of the own vehicle. A likelihood calculating unit calculates, for the radar-based object, a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle. A pedestrian determining unit determines whether the likelihood is equal to or higher than a predetermined threshold, and determines that the radar-based object is a pedestrian crossing ahead of the own vehicle if the likelihood is equal to or higher than the predetermined threshold. The likelihood calculating unit sets the likelihood for the radar-based object to be lower if the radar-based object is detected as a part of an object group arranged at regular intervals than otherwise.

## Claims

### Claim 1

A pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle, the pedestrian determining apparatus comprising:
an object detecting unit that detects, based on waves reflected by an object, the object as a radar-based object, the reflected waves being generated based on reflection, by the object, of radar waves transmitted ahead of the own vehicle;
a likelihood calculating unit that calculates, for the radar-based object detected by the object detecting unit, a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle; and
a pedestrian determining unit that:
determines whether the calculated likelihood is equal to or higher than a predetermined threshold; and
determines that the radar-based object is a pedestrian crossing ahead of the own vehicle upon determination that the calculated likelihood is equal to or higher than the predetermined threshold,
the likelihood calculating unit being configured to set the likelihood for the radar-based object to be lower for a state in which the radar-based object is detected as a part of a group of objects arranged at regular intervals than for a state in which the radar-based object is not detected as a part of the group of objects arranged at regular intervals.

### Claim 2 (depends on 1)

The pedestrian determining apparatus according to claim 1, further comprising:
an image obtaining unit that obtains a captured image of scenery ahead of the own vehicle;
an image recognizing unit that recognizes an object in the obtained image as an image-based object; and
a matching level obtaining unit comprising a dictionary of pedestrians and configured to:
obtain, upon the image-based object recognized by the image recognizing unit being identical to the radar-based object detected by the object detecting unit, a matching level between the image-based object and the dictionary of pedestrians in accordance with a matching task between the image-based object and the dictionary of pedestrians,
the likelihood calculating unit being configured to set the likelihood for the radar-based object such that, the higher the matching level is, the higher the likelihood for the radar-based object.

### Claim 3 (depends on 1)

The pedestrian determining apparatus according to claim 1, further comprising:
an image obtaining unit that obtains a captured image of scenery ahead of the own vehicle;
an image recognizing unit that recognizes an object in the obtained image as an image-based object; and
an optical flow obtaining unit configured to, upon the image-based object recognized by the image recognizing unit being identical to the radar-based object detected by the object detecting unit, obtain optical flows of feature points on the image-based object,
the likelihood calculating unit being configured to set the likelihood for the radar-based object to be higher for a state in which the optical flows show lateral movements on the image than for a state in which the optical flows do not show the lateral movements on the image.

### Claim 4 (depends on 1)

The pedestrian determining apparatus according to claim 1, wherein:
the likelihood calculating unit is configured to:
determine whether intensities of the reflected waves are equal to or less than a predetermined threshold level; and
set the likelihood for the radar-based object to be higher for a state in which the intensities of the reflected waves are equal to or less than the predetermined threshold level than for a state in which the intensities of the reflected waves are more than the predetermined threshold level.

### Claim 5 (depends on 1)

The pedestrian determining apparatus according to claim 1, wherein:
the likelihood calculating unit is configured to:
determine whether magnitudes of fluctuations of the reflected waves are equal to or more than a predetermined threshold value; and
set the likelihood for the radar-based object to be higher for a state in which the magnitudes of the fluctuations of the reflected waves are equal to or more than the predetermined threshold value than for a state in which the magnitudes of the fluctuations of the reflected waves are less than the predetermined threshold value.

### Claim 6 (depends on 1)

The pedestrian determining apparatus according to claim 1, further comprising:
a moving speed obtaining unit that obtains a lateral moving speed of the radar-based object,
the likelihood calculating unit being configured to:
determine whether the lateral moving speed of the radar-based object is within a predetermined range; and
set the likelihood for the radar-based object to be higher for a state in which the lateral moving speed of the radar-based object is within the predetermined range than for a state in which the lateral moving speed of the radar-based object is outside the predetermined range.

### Claim 7 (depends on 1)

The pedestrian determining apparatus according to claim 1, further comprising:
a movement distance obtaining unit that obtains a lateral movement distance of the radar-based object,
the likelihood calculating unit being configured to:
determine whether the lateral movement distance of the radar-based object is within a predetermined distance range; and
set the likelihood for the radar-based object to be higher for a state in which the lateral movement distance of the radar-based object is within the predetermined distance range than for a state in which the lateral movement distance of the radar-based object is outside the predetermined distance range.

### Claim 8 (depends on 1)

The pedestrian determining apparatus according to claim 1, wherein:
the likelihood calculating unit is configured to:
determine whether the radar-based object is detected as a part of a group of objects arranged at regular intervals; and
set the likelihood for the radar-based object to be lower in response to determining that the radar-based object being detected as a part of the group of objects arranged at regular intervals rather than determining that the radar-based object being not detected as a part of the group of objects arranged at regular intervals.

### Claim 9 (depends on 7)

The pedestrian determining apparatus according to claim 7, wherein
the predetermined distance range is previously defined as a range including movement distances of pedestrians crossing ahead of the own vehicle.

### Claim 10 (depends on 6)

The pedestrian determining apparatus according to claim 6, wherein
the predetermined range is previously defined as a range including speeds of pedestrians crossing ahead of the own vehicle.

### Claim 11

A pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle, the pedestrian determining apparatus comprising:
an object detecting unit that detects, based on waves reflected by an object, the object as a radar-based object, the reflected waves being generated based on reflection, by the object, of radar waves transmitted ahead of the own vehicle;
an image obtaining unit that obtains a captured image of scenery ahead of the own vehicle;
an image recognizing unit that recognizes an object in the obtained image as an image-based object;
a matching level obtaining unit comprising a dictionary of pedestrians and configured to obtain, upon the image-based object recognized by the image recognizing unit being identical to the radar-based object detected by the object detecting unit, a matching level between the image-based object and the dictionary of pedestrians in accordance with a matching task between the image-based object and the dictionary of pedestrians;
an optical flow obtaining unit configured to, upon the image-based object recognized by the image recognizing unit being identical to the radar-based object detected by the object detecting unit, obtain optical flows of feature points on the image-based object;
a moving speed obtaining unit that obtains a lateral moving speed of the radar-based object;
a movement distance obtaining unit that obtains a lateral movement distance of the radar-based object; and
a likelihood calculating unit that executes at least one of:
a first task to set a first likelihood for the radar-based object to be lower for a state in which the radar-based object is detected as a part of a group of objects arranged at regular intervals than for a state in which the radar-based object is not detected as a part of the group of objects arranged at regular intervals, the first likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle;
a second task to set a second likelihood for the radar-based object such that, the higher the matching level is, the higher the second likelihood for the radar-based object is, the second likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle;
a third task to set a third likelihood for the radar-based object to be higher for a state in which the optical flows show lateral movements on the image than for a state in which the optical flows do not show the lateral movements on the image, the third likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle;
a fourth task to:
set a fourth likelihood for the radar-based object to be higher for a state in which intensities of the reflected waves are equal to or less than a predetermined threshold level than for a state in which the intensities of the reflected waves are more than the predetermined threshold level; and
set the fourth likelihood for the radar-based object to be higher for a state in which magnitudes of fluctuations of the reflected waves are equal to or more than a predetermined threshold value than for a state in which the magnitudes of the fluctuations of the reflected waves are less than the predetermined threshold value, the fourth likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle;
a fifth task to set a fifth likelihood for the radar-based object to be higher for a state in which the lateral moving speed of the radar-based object is within a predetermined range than for a state in which the lateral moving speed of the radar-based object is outside the predetermined range, the fifth likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle; and
a sixth task to set a sixth likelihood for the radar-based object to be higher for a state in which the lateral movement distance of the radar-based object is within a predetermined distance range than for a state in which the lateral movement distance of the radar-based object is outside the predetermined distance range, the sixth likelihood being a likelihood of the radar-based object being a pedestrian crossing ahead of the own vehicle; and
a pedestrian determining unit that determines whether the radar-based object is a pedestrian crossing ahead of the own vehicle in accordance with at least one of the first to sixth likelihoods obtained by a corresponding at least one of the first to sixth tasks.

### Claim 12 (depends on 11)

The pedestrian determining apparatus according to claim 11, wherein:
the likelihood calculating unit is configured to:
execute at least two of the first to sixth tasks to obtain at least two likelihoods in the first to sixth likelihoods; and
execute a predetermined calculation based on the at least two of the first to sixth likelihoods to correspondingly calculate an overall likelihood for the radar-based object; and
the pedestrian determining unit is configured to:
determine whether the calculated overall likelihood is equal to or more than a predetermined threshold; and
determine that the radar-based object is a pedestrian crossing ahead of the own vehicle upon determination that the calculated overall likelihood is equal to or more than the predetermined threshold.

### Claim 13 (depends on 11)

The pedestrian determining apparatus according to claim 11, wherein:
the likelihood calculating unit is configured to:
determine whether the radar-based object is detected as a part of a group of objects arranged at regular intervals; and
wherein execution of the first task sets the first likelihood for the radar-based object to be lower in response to determining that the radar-based object being detected as a part of the group of objects arranged at regular intervals rather than determining that the radar-based object being not detected as a part of the group of objects arranged at regular intervals.