# US 11,113,900 B2 · Image processing device, number-of-axles detection system, toll setting device, toll setting system, and non-transitory computer-readable medium storing program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,900 B2 - Document ID: US11113900B2 - Status: Granted - Kind: B2 - Application number: 16/553,613 - Filed: 2019-08-28 - Published: 2020-03-05 - Granted: 2021-09-07 - Earliest claimed: 2018-08-31 - Assignees: Konica Minolta, Inc. - Applicants: Konica Minolta, Inc. - Inventors: Takumi Kaseda; Asahi Ebe - Web page: https://patentgrep.com/patent/US11113900B2 ## CPC - G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images - G06T 7/62: of area, perimeter, diameter or volume - G06T 7/73: using feature-based methods - G06T 7/74: {involving reference images or patches} - G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching} - G06V 20/54: of traffic, e.g. cars on the road, trains or boats - G07B 15/06: Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems - G06T 2207/30236: Traffic on road, railway or crossing - G06T 2207/30242: Counting objects in image - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G07B: TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS ## Abstract Disclosed is an image processing device including a hardware processor that: specifies a position of a plurality of tires of a moving vehicle from a captured image showing at least the plurality of tires of the vehicle; makes a determination of whether or not each of the plurality of tires is in contact with a ground on the basis of a position of the specified plurality of tires; and counts the number of axle of a tire in contact with the ground of the vehicle according to a result of the determination. ## Claims ### Claim 1 An image processing device comprising a hardware processor that: specifies a position of a plurality of tires of a moving vehicle from a captured image showing at least one of the plurality of tires of the vehicle; makes a determination of whether or not each of the plurality of tires is in contact with a ground on a basis of a position of the specified plurality of tires; and counts the number of axle of a tire in contact with the ground of the vehicle according to a result of the determination, wherein in the determination, the hardware processor determines whether or not each of the specified plurality of tires is in contact with the ground through comparison between an average level of predetermined parts of the plurality of tires and a level of a predetermined part of each of the plurality of tires. ### Claim 2 (depends on 1) The image processing device according to claim 1, wherein the predetermined part is a lower end of the tire. ### Claim 3 (depends on 1) The image processing device according to claim 1, wherein the level of the predetermined part is calculated on a basis of multiple points on an outer edge of each of the plurality of tires. ### Claim 4 (depends on 3) The image processing device according to claim 3, wherein, when at least one of the plurality of tires has a difference dimension from the other of the plurality of tires, the hardware processor corrects the level of the predetermined part according to dimensional difference between the plurality of tires. ### Claim 5 (depends on 1) The image processing device according to claim 1, wherein the level of the predetermined part is calculated on a basis of multiple points on an outer edge of a rim to which each of the plurality of tires is attached. ### Claim 6 (depends on 1) The image processing device according to claim 1, wherein the predetermined part is a rotation axis of the tire. ### Claim 7 (depends on 1) The image processing device according to claim 1, wherein the predetermined part is an upper end of each of the plurality of tires. ### Claim 8 (depends on 1) The image processing device according to claim 1, wherein the predetermined part is a point on an outer edge of a rim to which each of the plurality of tires is attached. ### Claim 9 (depends on 8) The image processing device according to claim 8, wherein the point on the outer edge of the rim is a lower end of the rim. ### Claim 10 (depends on 1) The image processing device according to claim 1, wherein in the determination, the hardware processor determines whether or not each of the plurality of tires is in contact with the ground on a basis of deformation of each of the plurality of tires at a lower end. ### Claim 11 (depends on 1) The image processing device according to claim 1, wherein in the determination, the hardware processor specifies a width in a height direction and a width in a horizontal direction of the plurality of tires and determines whether or not each of the plurality of tires is in contact with the ground on a basis of a difference between the two specified widths. ### Claim 12 (depends on 1) The image processing device according to claim 1, wherein in the determination, the hardware processor determines whether or not each of the plurality of tires is in contact with the ground by determining rotation of the plurality of tires on a basis of a plurality of images captured at different time points. ### Claim 13 (depends on 1) The image processing device according to claim 1, wherein in the determination, the hardware processor calculates a positional relationship in a horizontal direction of the specified plurality of tires and excludes any object that is not a tire of the vehicle from the determination on a basis of the positional relationship. ### Claim 14 (depends on 1) The image processing device according to claim 1, wherein the hardware processor overlays a plurality of images that are captured at different time points and generates, as the captured image, a panoramic photograph including all tires at least one side of the vehicle. ### Claim 15 (depends on 14) The image processing device according to claim 14, wherein the hardware processor generates the panoramic photograph by using some of the captured plurality of images that is captured at predetermined time intervals. ### Claim 16 (depends on 1) The image processing device according to claim 1, wherein the hardware processor detects the vehicle on a basis of comparison between a background image and the captured image, wherein the background image has a same angle of view as the captured image. ### Claim 17 (depends on 16) The image processing device according to claim 16, wherein the hardware processor weights a difference between the captured image and the background image, the difference being weighted with respect to each pixel according to a predetermined condition, and detects the vehicle on a basis of the weighted difference. ### Claim 18 (depends on 1) The image processing device according to claim 1, wherein the hardware processor specifies a range of each vehicle from the captured image, and counts the number of axle of the tire in contact with the ground with respect to each specified range. ### Claim 19 (depends on 18) The image processing device according to claim 18, wherein in specifying the range of each vehicle, the hardware processor detects a front end and a rear end of the vehicle within a predetermined area of the captured image. ### Claim 20 (depends on 19) The image processing device according to claim 19, wherein in detecting the front end and the rear end of the vehicle, the hardware processor changes the predetermined area of the captured image. ### Claim 21 (depends on 19) The image processing device according to claim 19, wherein the hardware processor changes the predetermined area between when detecting the front end of the vehicle and when detecting the rear end of the vehicle. ### Claim 22 (depends on 1) The image processing device according to claim 1, wherein the hardware processor obtains a plurality of captured images captured from different directions and selectively uses one of the plurality of captured images as the captured image to specify the position of the plurality of tires. ### Claim 23 (depends on 22) The image processing device according to claim 22, wherein the hardware processor selects one of the plurality of captured images according to a surrounding environment condition. ### Claim 24 (depends on 23) The image processing device according to claim 23, wherein the surrounding environment condition includes a direction of sunlight. ### Claim 25 (depends on 23) The image processing device according to claim 23, wherein the hardware processor selects one of the plurality of captured images after reducing noise by performing image processing on the plurality of captured images according to the environment condition. ### Claim 26 (depends on 1) A number-of-axles detection system comprising: the image processing device according to claim 1; and an imaging unit that captures the captured image. ### Claim 27 (depends on 1) A toll setting device comprising the image processing device according to claim 1, wherein the hardware processor sets a toll for entry of the vehicle into a predetermined section on a basis of the counted number of axle. ### Claim 28 (depends on 27) A toll setting system comprising: the toll setting device according to claim 27; and an imaging unit that captures the captured image. ### Claim 29 An image processing device comprising a hardware processor that: specifies a position of a plurality of tires of a moving vehicle from a captured image showing at least one of the plurality of tires of the vehicle; makes a determination of whether or not each of the plurality of tires is in contact with a ground on a basis of a position of the specified plurality of tires; and counts the number of axle of a tire in contact with the ground of the vehicle according to a result of the determination, wherein in response to the level of the predetermined part of one of the plurality of tires being higher than the level of the predetermined part of the other tire of the plurality of tires, the hardware processor determines that the one of the plurality of tires is not in contact with the ground. ### Claim 30 A non-transitory computer-readable medium storing a program that causes a computer to: specify a position of a plurality of tires of a moving vehicle from a captured image showing at least the plurality of tires; make a determination of whether or not each tire is in contact with a ground on a basis of a position of the plurality of tires specified by the specifier; and count the number of axle of a tire in contact with the ground of the vehicle according to a result of the determination, wherein in the determination, the computer determines whether or not each of the specified plurality of tires is in contact with the ground through comparison between an average level of predetermined parts of the plurality of tires and a level of a predetermined part of each of the plurality of tires.