# US 2017/0254896 A1 · Tracking apparatus, tracking method, and computer-readable storage medium

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

- Number: US 2017/0254896 A1
- Document ID: US20170254896A1
- Status: Published application
- Kind: A1
- Application number: 15/447,091
- Filed: 2017-03-01
- Published: 2017-09-07
- Earliest claimed: 2016-03-02
- Assignees: Oki Electric Industry Co., Ltd.
- Applicants: Oki Electric Industry Co., Ltd.
- Inventors: Kohei YAMAMOTO; Motoko KAGAYA; Kurato MAENO
- Web page: https://patentgrep.com/patent/US20170254896A1

## CPC

- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G01S 7/2921: {based on data belonging to one radar period}
- G01S 7/354: {Extracting wanted echo-signals (Doppler systems G01S13/50)}
- G01S 7/40: Means for monitoring or calibrating
- G01S 13/723: {by using numerical data}
- G01S 13/867: {Combination of radar systems with cameras}
- G06F 18/25: Fusion techniques
- G06T 7/001: {using an image reference approach}
- G06T 7/97: {Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85)}
- G06V 10/758: {Involving statistics of pixels or of feature values, e.g. histogram matching}
- G06V 10/80: Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level (multimodal speaker identification or verification G10L17/10)
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G01S 13/931: of land vehicles
- G06T 2207/10044: Radar image
- G06T 2207/30168: Image quality inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A tracking apparatus, including (1) a first target object tracking unit having a first processor, configured to correct a first information of at least one first candidate target object, detected by an image sensor, according to a first predetermined motion model, and to determine a distribution of the first information, (2) a second target object tracking unit including a second processor, configured to correct a second information of at least one second candidate target object, detected by an active type sensor, according to a second predetermined motion model, and to determine a distribution of the second information, (3) a matching unit configured to obtain a plurality of distribution parameters based on a correlation of the distributions of the first and second information, and (4) a false image determining unit configured to determine whether or not the second information corresponds to a false image based on the plurality of distribution parameters.

## Claims

### Claim 1

A tracking apparatus, comprising:
a first target object tracking unit including a first processor, which is configured
to correct a first information of at least one first candidate target object, detected by an image sensor, according to a first predetermined motion model, and
to determine a first distribution that is a distribution of the first information;
a second target object tracking unit including a second processor, which is configured
to correct a second information of at least one second candidate target object, detected by an active type sensor by measuring a reflected wave, according to a second predetermined motion model, and
to determine a second distribution that is a distribution of the second information;
a matching unit configured to obtain a plurality of distribution parameters from the first distribution and the second distribution based on a correlation therebetween; and
a false image determining unit configured to determine whether or not the second information corresponds to a false image based on the plurality of distribution parameters, wherein
each of the first information and the second information includes at least one of a relative speed and a distance, and
both the at least one first candidate target object and the at least one second candidate target object are obtained by detecting at least one target object existing in a predetermined space.

### Claim 2 (depends on 1)

The tracking apparatus according to claim 1, wherein the matching unit obtains the plurality of distribution parameters based on a third distribution, which corresponds to a product of the first distribution and the second distribution.

### Claim 3 (depends on 2)

The tracking apparatus according to claim 2, wherein the first distribution, the second distribution, and the third distribution are all Gaussian distributions.

### Claim 4 (depends on 2)

The tracking apparatus according to claim 2, wherein the false image determining unit determines whether or not the second information is the false image based on a Mahalanobis distance obtained using an exponent part of the third distribution.

### Claim 5 (depends on 1)

The tracking apparatus according to claim 1, further comprising:
an image processing unit that is configured
to perform a first image processing on the first information, responsive to non-receipt of a signal indicating that the second information is information derived from other than the at least one target object, and to output the first information, after performing the first image processing, to the first target object tracking unit,
to perform a second image processing on the first information using a processing parameter different from that for the first image processing, responsive to receipt of the signal indicating that the second information is information derived from other than the at least one target object, and to output the first information, after performing the second image processing, to the first target object tracking unit, wherein
the false image determining unit is configured
to send, to the image processing unit, the signal indicating that the second information is derived from other than the at least one target object, upon determining that the second information is derived from other than the at least one target object based on the first information after performing the first image processing, and
to determine that the second information corresponds to the false image upon determining that the second information is derived from other than the at least one target object based on the second information after performing the second image processing.

### Claim 6 (depends on 5)

The tracking apparatus according to claim 5, wherein the processing parameter includes at least one of a resolution of an image, luminance of the image, a frame rate, and a threshold value for edge extraction.

### Claim 7 (depends on 1)

The tracking apparatus according to claim 1, wherein the false image determining unit changes a parameter of the image sensor when a difference between a detection ratio by the active type sensor and a detection ratio by the image sensor exceeds a predetermined threshold.

### Claim 8 (depends on 7)

The tracking apparatus according to claim 7, wherein the parameter of the image sensor includes at least one of a white balance and an aperture.

### Claim 9 (depends on 1)

The tracking apparatus according to claim 1, wherein the false image determining unit is configured to
output the second information to the second target object tracking unit upon determining that the second information does not correspond to the false image, and
output the first information detected by the image sensor to the second target object tracking unit upon determining that the second information corresponds to the false image.

### Claim 10 (depends on 1)

The tracking apparatus according to claim 1, wherein the first distribution is a predicted distribution or a posterior distribution of the first information, and the second distribution is a predicted distribution of the second information.

### Claim 11

A tracking method, comprising:
correcting a first information of at least one first candidate target object, detected by an image sensor, according to a first predetermined motion model, and determining a first distribution that is a distribution of the first information;
correcting a second information of at least one second candidate target object, detected by an active type sensor by measuring a reflected wave, according to a second predetermined motion model, and determining a second distribution that is a distribution of the second information;
obtaining a plurality of distribution parameters from the first distribution and the second distribution based on a correlation therebetween; and
determining whether or not the second information corresponds to a false image based on the plurality of distribution parameters, wherein
each of the first information and the second information includes at least one of a relative speed and a distance, and
both the at least one first candidate target object and the at least one second candidate target object are obtained by detecting at least one target object existing in a predetermined space.

### Claim 12

A computer-readable storage medium storing computer-executable program instructions, execution of which by a computer causes the computer to track an object, the program instructions comprise:
instructions to correct a first information of at least one first candidate target object, detected by an image sensor, according to a first predetermined motion model, and to determine a first distribution that is a distribution of the first information;
instructions to correct a second information of at least one second candidate target object, detected by an active type sensor by measuring a reflected wave, according to a second predetermined motion model, and to determine a second distribution that is a distribution of the second information;
instructions to obtain a plurality of distribution parameters from the first distribution and the second distribution based on a correlation therebetween; and
instructions to determine whether or not the second information corresponds to a false image based on the plurality of distribution parameters, wherein
each of the first information and the second information includes at least one of a relative speed and a distance, and
both the at least one first candidate target object and the at least one second candidate target object are obtained by detecting at least one target object existing in a predetermined space.
