# US 2021/0081669 A1 · Event-based identification and tracking of objects

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

- Number: US 2021/0081669 A1
- Document ID: US20210081669A1
- Status: Published application
- Kind: A1
- Application number: 17/020,350
- Filed: 2020-09-14
- Published: 2021-03-18
- Earliest claimed: 2019-09-18
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Alexander Kugele
- Web page: https://patentgrep.com/patent/US20210081669A1

## CPC

- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/75: Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44)
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- 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 2207/10016: Video; Image sequence
- G06T 2207/30261: Obstacle
- G06V 20/44: {Event detection}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for identifying and/or tracking objects in a spatial area. The method includes observing the area with the aid of at least one event-based sensor, the event-based sensor including light-sensitive pixels, and a relative change of the light intensity incident upon a pixel by at least a predefined percentage prompting the sensor to output an event assigned to this pixel. The method further includes, in response to the sensor, outputting a new event, ascertaining an assessment for this event which is a measure of the extent to which this event matches an already detected distribution of events, and/or of the extent to which it is plausible that the event stems from an already detected object; and in response to the ascertained assessment meeting a predefined criterion, assigning the new event to the already detected distribution, or the already detected object.

## Claims

### Claim 1

A method for identifying and/or tracking objects in a spatial area, comprising the following steps:
observing the area using at least one event-based sensor, the event-based sensor including light-sensitive pixels, wherein a relative change of the light intensity incident upon a pixel of the sensor, by at least a predefined percentage, prompting the sensor to output an event assigned to the pixel;
ascertaining, in response to the sensor outputting a new event, an assessment for the event, which is a measure of the extent to which the new event matches an already detected distribution of events, and/or of the extent to which it is plausible that the new event stems from an already detected object; and
assigning, in response to the ascertained assessment meeting a predefined criterion, the new event to the already detected distribution, or the already detected object.

### Claim 2 (depends on 1)

The method as recited in claim 1, wherein, in response to the new event being assigned to an already detected object and/or a distribution of events belonging to the already detected object, an updated position of the already detected object, and/or an updated speed of the already detected object, and/or an updated movement direction of the already detected object, is ascertained, taking the new event into consideration.

### Claim 3 (depends on 1)

The method as recited in claim 1, wherein, in response to establishing that a number of events do not match any already detected distribution of events, but form a new distribution in accordance with a predefined criterion, the new distribution is detected.

### Claim 4 (depends on 3)

The method as recited in claim 3, wherein, in response to the new distribution being detected, and/or a number of events not matching any already detected distribution meeting another predefined criterion, at least one image of objects present in the observed area is ascertained.

### Claim 5 (depends on 4)

The method as recited in claim 4, wherein the image is detected using an image sensor divided into light-sensitive pixels, which outputs, for each pixel, a measure of light intensity incident upon this pixel.

### Claim 6 (depends on 4)

The method as recited in claim 4, wherein the image is ascertained, taking already detected events into consideration.

### Claim 7 (depends on 4)

The method as recited in claim 4, wherein the image is selectively ascertained for a portion of the observed area from which the events which prompted the ascertainment of the image stem.

### Claim 8 (depends on 4)

The method as recited in claim 4, wherein, based on the image, the new distribution, and/or the number of events not matching any already detected distribution, is assigned to at least one object.

### Claim 9 (depends on 1)

The method as recited in claim 1, wherein, from a number of events which form a new distribution, and/or from a number of events not matching any already detected distribution which meets another predefined criterion, a position, and/or a speed, and/or a movement direction, of at least one object with which the events are consistent, is ascertained.

### Claim 10 (depends on 1)

The method as recited in claim 1, further comprising:
ascertaining an activation signal from: (i) at least one assignment of events to an object, and/or a distribution of events, and/or (ii) at least one position, and/or movement direction, and/or speed, of at least one object ascertained based on events; and
activating, using the activation signal, a vehicle and/or a monitoring system for monitoring the spatial area.

### Claim 11

A system for activating a vehicle, and/or a monitoring system for monitoring a spatial area, comprising:
at least one event-based sensor configured to output events;
at least one assessment module configured to ascertain an assessment, for each of the events output by the event-based sensor, as to the extent to which the event matches an already detected distribution of events, and/or the extent to which it is plausible that the event stems from an already detected object;
at least one activation module configured to form an activation signal: (i) from at least one assignment of the events to an object and/or to a distribution of events, and/or (i) from at least one position, and/or movement direction, and/or speed, of at least one object ascertained based on the events, wherein the activation module is further configured to activate the vehicle, or the monitoring system, using the activation signal; and
at least one interface module configured to transmit the events output by the event-based sensor to the activation module, the interface module being configured to increase a priority given to an event during the transmission to the activation module, the less the event matches the assessment by the assessment module for an already detected distribution, or for an already detected object.

### Claim 12 (depends on 11)

The system as recited in claim 11, wherein the activation module is further configured to communicate, to the assessment module, already detected distributions and objects.

### Claim 13 (depends on 11)

The system as recited in claim 11, wherein the interface module is connected via a CAN bus of the vehicle to the activation module.

### Claim 14

A non-transitory machine-readable data carrier on which is stored a computer program for identifying and/or tracking objects in a spatial area, the computer program, when executed by a computer, causing the computer to perform the following steps:
observing the area using at least one event-based sensor, the event-based sensor including light-sensitive pixels, wherein a relative change of the light intensity incident upon a pixel of the sensor, by at least a predefined percentage, prompting the sensor to output an event assigned to the pixel;
ascertaining, in response to the sensor outputting a new event, an assessment for the event, which is a measure of the extent to which the new event matches an already detected distribution of events, and/or of the extent to which it is plausible that the new event stems from an already detected object; and
assigning, in response to the ascertained assessment meeting a predefined criterion, the new event to the already detected distribution, or the already detected object.

### Claim 15

A computer configured to identify and/or track objects in a spatial area, the computer configured to:
observe the area using at least one event-based sensor, the event-based sensor including light-sensitive pixels, wherein a relative change of the light intensity incident upon a pixel of the sensor, by at least a predefined percentage, prompting the sensor to output an event assigned to the pixel;
ascertain, in response to the sensor outputting a new event, an assessment for the event, which is a measure of the extent to which the new event matches an already detected distribution of events, and/or of the extent to which it is plausible that the new event stems from an already detected object; and
assign, in response to the ascertained assessment meeting a predefined criterion, the new event to the already detected distribution, or the already detected object.
