# US 2020/0349819 A1 · Passive optical detection method and system for vehicles

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

- Number: US 2020/0349819 A1
- Document ID: US20200349819A1
- Status: Published application
- Kind: A1
- Application number: 16/518,608
- Filed: 2019-07-22
- Published: 2020-11-05
- Earliest claimed: 2016-07-07
- Assignees: SRI International
- Applicants: SRI International
- Inventors: Richard Andrew Hill; Karen Marie Nashold; Zachary Flom; Erik Frank Matlin; Robert A. Brown
- Web page: https://patentgrep.com/patent/US20200349819A1

## CPC

- G06T 7/285: using a sequence of stereo image pairs
- B64C 19/00: Aircraft control not otherwise provided for
- G06V 10/431: {Frequency domain transformation; Autocorrelation}
- G06V 10/507: {Summing image-intensity values; Histogram projection analysis}
- G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G08B 13/19604: {involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change}
- H04N 5/144: {Movement detection (for video coding H04N19/503; analysis of motion in general G06T7/20)}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 2207/10021: Stereoscopic video; Stereoscopic image sequence
- G06V 2201/08: Detecting or categorising vehicles
- G08B 13/19602: {Image analysis to detect motion of the intruder, e.g. by frame subtraction}
- H04N 2013/0085: {Motion estimation from stereoscopic image signals}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- B64C: AEROPLANES; HELICOPTERS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A system, method, and apparatus are discussed for a passive optical camera-based system to detect a presence of one or more vehicles with one or more cameras. A detection algorithm is applied to recognize of the presence of the one or more vehicles using one or more imaging processors and the one or more cameras to detect fluctuations in light intensity from scattered light and/or reflections off of that vehicle. Those scattered light and/or reflections are captured in images contained in a set of frames from the one or more cameras.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system, comprising:
a passive optical camera-based system configured to detect a presence of one or more vehicles with one or more cameras, where the passive optical camera-based system also has a detection algorithm to recognize the presence of the one or more vehicles using one or more imaging processors, where the detection algorithm is further configured to detect the one or more vehicles captured in a set of frames by the one or more cameras via a fluctuation signature that is based on a frequency of at least one of i) a moving part of the given vehicle and ii) a vibration of a part of a given vehicle; and
where any portions of the detection algorithm implemented in software are stored in an executable format in a memory and are executed by the one or more imaging processors.

### Claim 22 (depends on 21)

The system of claim 21, further comprising:
a database to store known characteristics of possible vehicles including the frequency of the vibration of the part and/or the frequency of the moving part associated with vehicles, where the detection algorithm is configured to use the database to recognize the fluctuation signature of possible vehicle candidates to confirm the presence of the one or more vehicles captured in the set of frames by the one or more cameras.

### Claim 23 (depends on 22)

The system of claim 22, wherein the detection algorithm is further configured to use the database to further classify a type of vehicle captured in the set of frames by the one or more cameras based in part on an expected possible frequency band of operation of that type of vehicle.

### Claim 24 (depends on 22)

The system of claim 22, wherein the detection algorithm is further configured to additionally use i) a maneuver pattern, ii) a visual appearance, and ii) any combination of the maneuver pattern and the visual appearance, of possible vehicle candidates, to recognize the fluctuation signature of possible vehicle candidates to confirm the presence of the one or more vehicles captured in the set of frames by the one or more cameras.

### Claim 25 (depends on 21)

The system of claim 21, wherein the detection algorithm is further configured to recognize the presence of a first vehicle that is hovering via the frequency of at least one of i) the moving part of the given vehicle and ii) the vibration of the part of the given vehicle without a need to perceive the first vehicle to be moving vertically or laterally with respect to one or more of the cameras.

### Claim 26 (depends on 21)

The system of claim 21, wherein the detection algorithm and the image processors are further configured to detect frequency information for the vibration and/or moving part of the given vehicle by measuring a light modulation caused by surface vibrations or moving mechanical features of that vehicle.

### Claim 27 (depends on 21)

The system of claim 21, wherein the detection algorithm and its cooperation with a database is further configured to pick out two or more different fluctuation signatures, via a plurality of fluctuation signatures contained in the database, from the one or more vehicles captured in the set of frames.

### Claim 28 (depends on 21)

The system of claim 21, wherein the detection algorithm and the image processors are further configured to spatially locate and separate a frequency content of time-varying light sources in the set of frames; and therefore, enable the detection of i) the frequency of i) the moving part and/or ii) the vibration of the part of possible vehicle candidates captured in the set of frames by the one or more cameras.

### Claim 29 (depends on 21)

The system of claim 21, wherein the detection algorithm is further configured to use a Fast Fourier transform (FFT), on the set of frames to convert fluctuations in light intensity over time to a frequency domain along a time axis of camera imagery captured by the one or more cameras in order to detect i) light fluctuations caused by moving mechanical features of that given vehicle and/or ii) vibration of other parts of the given vehicle.

### Claim 30 (depends on 21)

The system of claim 21, further comprising:
a software-based real-time digital image stabilization application that is configured to i) combine data from an inertial measurement unit that measures a motion of a first camera and ii) then generates motion compensation data to correct data captured in the set of frames in real time before image processing occurs, where the inertial measurement unit is configured to track camera pointing direction, where the digital image stabilization application and the inertial measurement unit are configured to enable the one or more cameras mounted on a moving or vibrating platform to prevent a motion of the cameras from interfering with the detection algorithm using the fluctuation signature that is based on the frequency of the vibration of the part and/or frequency of the moving part of the given vehicle.

### Claim 31

A method for a passive optical camera-based method, comprising:
detecting a presence of one or more vehicles with one or more cameras in the passive optical camera-based method; and
applying a detection algorithm to recognize of the presence of the one or more vehicles using one or more imaging processors and the one or more cameras, where the detection algorithm is further configured to detect the one or more vehicles captured in a set of frames by the one or more cameras via a fluctuation signature that is based on a frequency of at least one of i) a moving part of the given vehicle and ii) a vibration of a part of a given vehicle.

### Claim 32 (depends on 31)

The method of claim 31, further comprising:
using a database to store known characteristics of possible vehicles including the frequency of the vibration of the part and/or the frequency of the moving part associated with vehicles, where the detection algorithm is configured to use the database to recognize the fluctuation signature of possible vehicle candidates to confirm the presence of the one or more vehicles captured in the set of frames by the one or more cameras.

### Claim 33 (depends on 32)

The method of claim 32, further comprising:
using the detection algorithm and its cooperation with the database to further classify a type of vehicle captured in the set of frames by the one or more cameras based in part on an expected possible frequency band of operation of that type of vehicle.

### Claim 34 (depends on 32)

The method of claim 32, wherein the detection algorithm additionally uses i) a maneuver pattern, ii) a visual appearance, and ii) any combination of the maneuver pattern and the visual appearance, of possible vehicle candidates, to recognize the fluctuation signature of possible vehicle candidates to confirm the presence of the one or more vehicles captured in the set of frames by the one or more cameras.

### Claim 35 (depends on 31)

The method of claim 31, further comprising:
using the detection algorithm to recognize the presence of a first vehicle that is hovering via the frequency of at least one of i) the moving part of the given vehicle and ii) the vibration of the part of the given vehicle without a need to perceive the first vehicle to be moving vertically or laterally with respect to one or more of the cameras.

### Claim 36 (depends on 31)

The method of claim 31, further comprising:
using the detection algorithm and its cooperation with the image processors to detect frequency information for the vibration or moving part of the given vehicle by measuring a light modulation caused by surface vibrations or moving mechanical features of that vehicle.

### Claim 37 (depends on 31)

The method of claim 31, further comprising:
using the detection algorithm and its cooperation with a database to further pick out two or more different fluctuation signatures, via a plurality of fluctuation signatures contained in the database, from the one or more vehicles captured in the set of frames.

### Claim 38 (depends on 31)

The method of claim 31, further comprising:
using the detection algorithm and its cooperation with the image processors to spatially locate and separate a frequency content of time-varying light sources in the set of frames; and therefore, enable the detection of the frequency of i) the moving part and/or ii) the vibration of the part of possible vehicle candidates captured in the set of frames by the one or more cameras.

### Claim 39 (depends on 31)

The method of claim 31, wherein the detection algorithm is further configured to use a Fast Fourier transform (FFT), on the set of frames to convert fluctuations in light intensity over time to a frequency domain along a time axis of camera imagery captured by the one or more cameras in order to detect i) light fluctuations caused by moving mechanical features of that given vehicle and/or ii) vibration of other parts of the given vehicle.

### Claim 40 (depends on 31)

The method of claim 31, further comprising:
using a software-based real-time digital image stabilization application that i) combines data from an inertial measurement unit that measures a motion of a first camera and ii) then generates motion compensation data to correct data captured in the set of frames in real time before image processing occurs, where the inertial measurement unit is configured to track camera pointing direction, where the digital image stabilization application and the inertial measurement unit are configured to enable the one or more cameras mounted on a moving or vibrating platform to prevent a motion of the cameras from interfering with the detection algorithm using the fluctuation signature that is based on the frequency of the vibration of the part and/or frequency of the moving part of the given vehicle.
