IP Library › Granted Patent US 12,272,147
Granted Patent B2
US 12,272,147 · App. 18/521,457 · Granted Apr 8, 2025

Server, vehicle detection system, and vehicle detection method

Inventors: Yui Sugie (Nagoya, JP); Koichi Suzuki (Miyoshi, JP); Naoki Uenoyama (Nagoya, JP); Hiroki Takeda (Okazaki, JP); Hirohiko Morikawa (Toyota, JP); Genshi Kuno (Kasugai, JP)
Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
G06V20/54G01J5/0025G06V10/255G06V20/17G06V40/103H04N5/33B64U10/13B64U30/20B64U2101/30B64U2201/10G06V2201/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,272,147
App. No.
18/521,457
Granted
Apr 8, 2025
Kind
B2
Abstract

A server includes a control unit. The control unit determines whether a parked vehicle is used as a shelter based on a first image which is included in an image captured by a camera and which is obtained by imaging the vehicle and surroundings of the vehicle.

Claims (39)

1. A server comprising a processor configured to determine whether a parked vehicle is used as a shelter based on a first image which is included in an image captured by a camera and which is obtained by imaging the vehicle and surroundings of the vehicle, wherein:

the camera is mounted in a mobile object; and

the processor is configured to

recognize identification information of the vehicle based on the first image, to acquire position information of the vehicle from the mobile object, and to transmit the identification information and the position information of the vehicle to the outside when it is determined that an evaluation value indicating a likelihood that the vehicle is used as a shelter is higher than a predetermined value, and

evaluate that there is a higher likelihood that the vehicle is used as a shelter when it is recognized from the first image that a member for preventing the inside from being viewed from the outside of the vehicle is disposed on a window of the vehicle than when the member is not recognized.

2. The server according to claim 1 , wherein the processor is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when an image of a predetermined article is included in the first image than when the article is not included in the first image.

3. The server according to claim 2 , wherein the predetermined article includes at least one of a tent, a chair, a table, an article of clothing, and a ground sheet.

4. The server according to claim 1 , wherein the processor is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when it is recognized from the first image that a person is in the vehicle than when it is recognized that a person is not in the vehicle.

5. The server according to claim 1 , wherein the processor is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when it is recognized from the first image that a window or a door of the vehicle is open than when it is recognized that a window or a door of the vehicle is not open.

6. The server according to claim 1 , wherein the processor is configured to further acquire a second image which is captured by the camera at a time different from a time at which the parked vehicle has been imaged at the position at which the parked vehicle has been imaged, and

wherein the processor is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when the vehicle is not included in the second image and an object installed at the position at which the vehicle is parked is included in the second image than when the object is not included in the second image.

7. The server according to claim 1 , wherein the camera is mounted in a mobile object, and

wherein the processor is configured to move the mobile object such that the first image is captured in at least one of a distance in a predetermined range and a direction in a predetermined range with respect to a direction of the vehicle when it is recognized that the parked vehicle is included in the image.

8. The server according to claim 1 , wherein the camera is mounted in a mobile object, and

wherein the processor is configured to recognize identification information of the vehicle based on the first image, to acquire position information of the vehicle from the mobile object, and to transmit the identification information and the position information of the vehicle to the outside when it is determined that an evaluation value indicating a likelihood that the vehicle is used as a shelter is higher than a predetermined value.

9. A vehicle detection system comprising:

a mobile object that includes a far-infrared camera; and

a server that is able to communicate with the mobile object, wherein

the mobile object captures a second image at a time different from the time at which a parked vehicle has been imaged at the same position at which the parked vehicle has been imaged,

the server includes a processor configured to determine whether the parked vehicle is used as a shelter based on a first image which is included in an image captured by the far-infrared camera and which is obtained by imaging the vehicle and surroundings of the vehicle,

the far-infrared camera is able to measure a temperature of a subject as at least a part of the first image, and

the processor is configured to

evaluate that there is a higher likelihood that the vehicle is used as a shelter when it is recognized from the image from the far-infrared camera that at least a part of the vehicle has a temperature different from that of surroundings than when it is recognized that at least a part of the vehicle does not have a temperature different from that of the surroundings, and

acquire the second image and to evaluate that there is a higher likelihood that the vehicle is used as a shelter when the vehicle is not included in the second image and an object installed at the position at which the vehicle is parked is included in the second image than when the object is not included in the second image.

10. The vehicle detection system according to claim 9 , wherein the processor of the server is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when an image of a predetermined article is included in the first image than when the article is not included in the first image.

11. The vehicle detection system according to claim 10 , wherein the predetermined article includes at least one of a tent, a chair, a table, an article of clothing, and a ground sheet.

12. The vehicle detection system according to claim 10 , wherein the mobile object transmits position information of the vehicle to the server, and

wherein the processor of the server is configured to recognize identification information of the vehicle based on the first image, to acquire position information of the vehicle from the mobile object, and to transmit the identification information and the position information of the vehicle to the outside when it is determined that an evaluation value indicating a likelihood that the vehicle is used as a shelter is higher than a predetermined value.

13. A vehicle detection method comprising causing a processor to determine whether a parked vehicle is used as a shelter based on a first image which is included in an image captured by a far-infrared camera and which is obtained by imaging the vehicle and surroundings of the vehicle, wherein:

the far-infrared camera is able to measure a temperature of a subject as at least a part of the first image; and

the processor

evaluates that there is a higher likelihood that the vehicle is used as a shelter when it is recognized from the image from the far-infrared camera that at least a part of the vehicle has a temperature different from that of surroundings than when it is recognized that at least a part of the vehicle does not have a temperature different from that of the surroundings,

acquires a second image which is captured by the far-infrared camera at a time different from the time at which the parked vehicle has been imaged at the same position at which the parked vehicle has been imaged, and

evaluates that there is a higher likelihood that the vehicle is used as a shelter when the vehicle is not included in the second image and an object installed at the position at which the vehicle is parked is included in the second image than when the object is not included in the second image.

14. The vehicle detection method according to claim 13 , wherein the processor is configured to evaluate that there is a higher likelihood that the vehicle is used as a shelter when an image of a predetermined article is included in the first image than when the article is not included in the first image.

15. The vehicle detection method according to claim 14 , wherein the predetermined article includes at least one of a tent, a chair, a table, clothes, and a ground sheet.

16. The vehicle detection method according to claim 14 , wherein the processor recognizes identification information of the vehicle based on the first image,

wherein the processor acquires position information of the vehicle from a mobile object having the far-infrared camera mounted therein, and

wherein the processor transmits the identification information and the position information of the vehicle to the outside when it is determined that an evaluation value indicating a likelihood that the vehicle is used as a shelter is higher than a predetermined value.

Priority Claims (1)
JP 2020-214292 · Dec 23, 2020 · national
Continuity (2)
Continuation 17538526 · Nov 30, 2021
Related Publication 20240096101A1 · Mar 21, 2024
References Cited (26)
US 10102586B1 · Marlow et al. · 2018 [cited by applicant]
US 10115029B1 · Day · 2018 [cited by examiner]
US 11900684B2 · Sugie · 2024 [cited by examiner]
US 20170124378A1 · High · 2017 [cited by examiner]
US 20180374345A1 · Suzuki · 2018 [cited by examiner]
US 20190193677A1 · Suzuki · 2019 [cited by examiner]
US 20200142419A1 · Pohl et al. · 2020 [cited by applicant]
US 20200150662A1 · Zhou · 2020 [cited by examiner]
US 20200346751A1 · Horelik et al. · 2020 [cited by applicant]
US 20210229629A1 · Ghannam · 2021 [cited by examiner]
JP 2003162784A · 2003 [cited by applicant]
JP 2016205142A · 2016 [cited by applicant]
JP 202027962A · 2020 [cited by applicant]
Gotovac et al, Analysis of saliency object detection algorithms for search and rescue operations, 2016, 24th International Conference on Software, Telecommunications and Computer Networks, pp. 1-7. (Year: 2016). [cited by examiner]
Paidi et al, Deep learning-based vehicle occupancy detection in an open parking lot using thermal camera, 2020, IET Intelligent Transport Systems, 14(1): 1295-1302. (Year: 2020). [cited by examiner]
Bastan et al, Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks, 2018, arXiv: 1804.10805v1, pp. 1-16. (Year: 2018). [cited by examiner]
Amato et al, Car parking occupancy detection using smart camera networks and Deep Learning, 2016, Conference Paper, pp. 1-7. (Year: 2016). [cited by examiner]
Kashid et al, Detection and identification of illegally parked vehicles at no parking area, 2014, International Conference on Communication and Signal Processing, pp. 1-6. (Year: 2014). [cited by examiner]
Gkolias et al, Convolutional Neural Networks for On-Street Parking Space Detection in Urban Networks, 2019, IEEE Transactions on Intelligent Transportation Systems, 20(12); pp. 4318-4327. (Year: 2019). [cited by examiner]
Stuparu D et al, Vehicle Detection in Overhead Satellite Images Using a One-Stage Object Detection Model, 2020, Sensors, 20: 6485; pp. 1-18. (Year: 2020). [cited by applicant]
Lin L et al, Hierarchical Heuristic Search Using a Gaussian Mixture Model for UAV Coverage Planning, 2014, IEEE Transactions on Cybernetics, 44:12. pp. 2532-2544. (Year: 2014). [cited by applicant]
Gotovac S et al, Analysis of Saliency Object Detection Algorithms for Search and Rescue Operations, 2016, IEEE International Conference on Software, Telecommunications and Computer Networks, pp. 1-14. (Year: 2016). [cited by applicant]
Jul. 6, 2023 Office Action issued in U.S. Appl. No. 17/538,526. [cited by applicant]
Oct. 12, 2023 Notice of Allowance issued in U.S. Appl. No. 17/538,526. [cited by applicant]
De Alcantara Andrade et al, Autonomous Unmanned Aerial Vehicles in Search and Rescue Missions Using Real-Time Cooperative Model Predictive Control, 2019, Sensors (19) 4067: 1-22. (Year: 2019). [cited by applicant]
Rodin et al, Object Classification in Thermal Images using Convolutional Neural Networks for Search and Rescue Missions with Unmanned Aerial Systems, 2018, 2018 International Joint Conference on Neural Networks, Jul. 20… [cited by applicant]