US-12620073-B2 - Image recognition method, system and mobile vehicle

US12620073B2US 12620073 B2US12620073 B2US 12620073B2US-12620073-B2

Abstract

An image recognition method includes the steps of: receiving a captured image; acquiring a focusing zone image from a portion of the captured image; processing the captured image and/or the focusing zone image and then making the two images into a batch of image information; and executing an image analysis procedure on the batch of image information to generate an analysis result.

Inventors

Ming-Chen Wang
Yu-Ting Li
Shao-Yuan LIN
Jia-Lin LEE
Guan-Yi WU

Assignees

WHETRON ELECTRONICS CO., LTD.

Dates

Publication Date: 20260505
Application Date: 20231016
Priority Date: 20230210

Claims (13)

1 . An image recognition method comprising the following steps: receiving a captured image; acquiring a focusing zone image from a portion of the captured image; processing the captured image and the focusing zone image, and then making the two images into a batch of image information; and executing an image analysis procedure on the batch of image information to generate an analysis result; wherein, in the image analysis procedure, the captured image and the focusing zone image of the batch of image information are respectively analyzed to get a respective analyzed result, and then the respective analyzed result from the captured image and the respective analyzed result from the focusing zone image are combined to generate the analysis result.
2 . The image recognition method as claimed in claim 1 , wherein the image analysis procedure is performed by using both or one of an image caption model and an object detection model.
3 . The image recognition method as claimed in claim 2 , wherein in a state that the image analysis procedure is performed by using the image caption model, multiple batches of image information are analyzed to generate the analysis result.
4 . The image recognition method as claimed in claim 3 , wherein an original image pixel dimension of the focusing zone image is 10 to 50 percent of an original image pixel dimension of the captured image.
5 . The image recognition method as claimed in claim 1 , wherein an original image pixel dimension of the focusing zone image is 10 to 50 percent of an original image pixel dimension of the captured image.
6 . The image recognition method as claimed in claim 1 , wherein the resolution of the focusing zone image is the same with the resolution of the captured image.
7 . An image recognition system comprising: an image capture unit configured to capture a captured image; and an image processing unit configured to perform the following operations: acquiring a focusing zone image from a portion of the captured image; processing the captured image and the focusing zone image, and then making the two images into a batch of image information; and executing an image analysis procedure on the batch of image information to generate an analysis result; wherein, in the image analysis procedure, the captured image and the focusing zone image of the batch of image information are respectively analyzed to get a respective analyzed result, and then the respective analyzed result from the captured image and the respective analyzed result from the focusing zone image are combined to generate the analysis result.
8 . The image recognition system as claimed in claim 7 , wherein the resolution of the focusing zone image is the same with the resolution of the captured image.
9 . A mobile vehicle comprising: an image capture unit configured to capture a captured image; an image processing unit configured to perform the following operations: acquiring a focusing zone image from a portion of the at least one captured image; processing the at least one captured image and the focusing zone image, and then making the two images into a batch of image information; and executing an image analysis procedure on the batch of image information to generate an analysis result; wherein in the image analysis procedure, the captured image and the focusing zone image of the batch of image information are respectively analyzed to get a respective analyzed result, and the respective analyzed result from the captured image and the respective analyzed result from the focusing zone image are combined to generate the analysis result; a lamp having multiple switchable light modes; a lamp control module configured to receive the analysis result, wherein the lamp control module has a lamp control logic to switch the multiple switchable light modes according to the analysis result; and a power system configured to drive the mobile vehicle.
10 . The mobile vehicle as claimed in claim 9 , wherein the lamp control logic further includes a learning mechanism, which automatically adjusts the lamp control logic according to habits of a user.
11 . The mobile vehicle as claimed in claim 10 , wherein the learning mechanism includes: when a light mode manually adjusted by the user in a particular scene or situation is different from a corresponding light mode in the lamp control logic, and when a consecutive manual adjustment to the same light mode reaches a particular number of times, the light mode in the lamp control logic corresponding to the particular scene or situation is replaced with the light mode manually adjusted by the user.
12 . The mobile vehicle as claimed in claim 9 , wherein the mobile vehicle is any of a car, a boat and an aircraft.
13 . The mobile vehicle as claimed in claim 9 , wherein the resolution of the focusing zone image is the same with the resolution of the captured image.

Description

CROSS REFERENCE TO RELATED APPLICATION The application claims the benefit of Taiwan application serial No. 112104830, filed on Feb. 10, 2023, and the entire contents of which are incorporated herein by reference. BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a recognition method and, more particularly, to an image recognition method system and a mobile vehicle. 2. Description of the Related Art With the development of image recognition technologies, image recognition has gradually been applied to various fields. It can be especially applied to vehicle driving, to instantly recognize a driving scene/driving situation, serving as decision-making reference for a driver. However, in addition to the problem that presentation of real-time-inferenced information is unclear or puzzling in conventional image recognition methods/systems, there are also problems of time-consuming computing or unrecognizability for a zone that should be highly focused in the driving scene/driving situation. In light of the foregoing, it is necessary to improve the conventional image recognition technology. SUMMARY OF THE INVENTION In order to solve the above problems, it is an objective of the present invention to provide an image recognition method, which can improve the preciseness of scene/situation recognition. It is another objective of the present invention to provide an image recognition method, which can enhance the clarity and comprehensibility of presentation of real-time information. It is yet another objective of the present invention to provide an image recognition system, which can improve the preciseness of scene/situation recognition and improve computing efficiency. It is still another objective of the present invention to provide an image recognition system, which can enhance the clarity and comprehensibility of presentation of real-time information. It is a further objective of the present invention to provide a mobile vehicle, which can improve driving safety. As used herein, the term “one”, “a” or “an” for describing the number of the elements and members of the present invention is used for convenience, provides the general meaning of the scope of the present invention, and should be interpreted to include one or at least one. Furthermore, unless explicitly indicated otherwise, the concept of a single component also includes the case of plural components. As used herein, terms “engaged”, “combined”, “assembled” or “arranged” throughout the present invention mainly include patterns that the components can still be separated without destroying the components after connection, or the components are inseparable after connection and the like, which can be selected by a person having ordinary skill in the art based on the material or assembly requirements of the components to be connected. As used herein, the term “coupled” throughout the present invention includes direct or indirect electrical and/or signal connections, which can be selected by a person having ordinary skill in the art based on actual needs. As used herein, the term “narrative logic” throughout the present invention is, for example, implemented based on a natural language processing (NLP) technology, and the natural language processing technology is understandable to a person having ordinary skill in the art. As used herein, terms “image recognition system”, “smart lamp” and “mobile vehicle” throughout the present invention include at least one “processor” to perform corresponding flows and functions. In detail, the processor refers to various data processing devices, such as an electronic controller, a server, a cloud platform, a virtual machine, a desktop computer, a notebook computer, a tablet, or a smart phone, that have particular functions and are implemented in hardware or hardware and software, to process or analysis information and/or generate corresponding control information, which can be understood by a person having ordinary skill in the art. In addition, a corresponding data receiving or transmitting unit may be included to receive or transmit required data. In addition, a corresponding database/storage unit (especially a non-transitory computer-readable medium) may be included to store the required data. In particular, unless otherwise specifically excluded or contradicted, the processor may be a collection of multiple processors in an architecture based on a distributed system, which is used for including/representing processes, mechanisms, and results of information stream processing among the multiple processors. Furthermore, the “processor” used in the present invention may represent an integrated technical feature, which may be a case that a single processor is coupled to control one or more coupled devices in an integrated manner, or multiple processors individually control respective coupled devices, such that corresponding devices perform their functions under suitable conditions. An image