In-vehicle image processing system

Abstract

The present invention relates to a system (1) for processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground.

Description

[0001] DESCRIPTION

[0002] IN-VEHICLE IMAGE PROCESSING SYSTEM

[0003] Technical Field

[0004] The present invention relates to a system for processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground.

[0005] Background of the Invention

[0006] Today, current methods involve various challenges in terms of efficiency, quality, cost and human error. Since manual visual editing processes require a lot of time and labour, they are highly inefficient. These methods often struggle to ensure consistency and can have quality differences among results, besides being prone to human error. Other background removal tools often provide low-quality results and may make mistakes on complex visuals; such tools are not specifically optimized for in-vehicle visuals and do not offer additional features such as background change. Basic segmentation models, on the other hand, require detailed data and training in order to provide high accuracy, but may frequently make errors on low-quality visuals. All of these methods increase costs due to high processing times and manual intervention requirements, and automated tools may also have additional costs such as license fees. As a result, current methods face challenges in many aspects such as efficiency, consistency, cost and human error, which lead to additional regulation and costs.

[0007] For this reason, it is understood that there is a need for a system for processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground.

[0008] The International patent document no. WO2019134590, an application included in the state of the art, discloses an in-vehicle display method. In the said invention, an in-vehicle display device, an in-vehicle display method, and a vehicle are described. The invention comprises in-vehicle display device; a first acquisition module for acquiring an imaging area of an in-vehicle image; a second acquisition module for acquiring an environment picture in a driving direction; a processing module for determining a background image of the imaging area from the environment picture; an adjustment module for adjusting the picture parameters of the in-vehicle image according to the picture parameters of the background image; and a display module for displaying the in-vehicle image in the imaging area after the picture parameters are adjusted.

[0009] Summary of the Invention

[0010] An object of the present invention is to realize a system developed with the aim of processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground.

[0011] Detailed Description of the Invention

[0012] “In-Vehicle Image Processing System” realized to fulfil the objective of the present invention is shown in the figure attached, in which:

[0013] Figure l is a schematic view of the inventive system. The components illustrated in the figure are individually numbered, where the numbers refer to the following:

[0014] 1. System

[0015] 2. Database

[0016] 3. Server

[0017] The inventive system (1) developed with the aim of processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground comprises; at least one database (2) which is configured to keep a record of in-vehicle visual data and information data in the form of visual format, size, content and intended use of the said data; and at least one server (3) which is configured to receive in-vehicle visual data from various sources and to enable them to be recorded in the database; to label specific areas of the visuals in the form of vehicle seats, steering wheel and control panel via various labelling tools; to train the artificial intelligence model by using the labelled data set; to remove the background and to add a new backdrop in in-vehicle visuals via the trained model; to enable the developed artificial intelligence models to be integrated into various web and application platforms; to enable visuals to be analysed and edited by artificial intelligence via automated processes; and to enable the developed flow and the changes made to be tested and validated.

[0018] The database (2) included in the inventive system (1) is configured to communicate and exchange data with the server (3) by using any communication protocol. The database (2) is configured to be managed by the server (3). The server (3) included in the inventive system (1) is configured to communicate and exchange data with the database (2) by using any communication protocol. The server (3) is configured to manage the database (2). The server (3) is configured to enable the visuals to be edited and published in a consistent manner via Al-supported changes. The server (3) is configured to enable human errors to be reduced through automated analysis and change processes. The server (3) is configured to enable the visuals to be changed in a unique and impressive way by using artificial intelligence, image processing and graphic design techniques. The server (3) is configured to collect existing in-vehicle visuals from the respective mobile platforms, to enable the information in the form of format, size, content and intended use of the visuals to be recorded in the database (2) and datasets to be prepared. The server (3) is configured to enable the specific areas in the form of vehicle seats, steering wheel and control panel in the visuals received by using data labelling software in the form of Labelme, Labelbox, Labelling, Label Studio to be labelled. The server (3) is configured to enable the segmentation of in- vehicle visuals to be performed by using high-level state-of-the-art models in the form of UNet, U2Net, ResNet and SegNet. The server (3) is configured to enable the performance of the model to be evaluated via metrics in the form of AP (Average Precision), loU (Intersection Over Union) and Dice Coefficient and improvements to be performed. The server (3) is configured to enable the background to be removed, a new backdrop to be added, and edits to be performed according to the factors in the form of aesthetic value, usability and brand compatibility, in in-vehicle visuals via the trained model. The server (3) is configured to enable artificial intelligence models to be integrated into various websites and mobile platforms, and visuals to be analysed and edited by artificial intelligence via automated processes on the said websites and platforms. The server (3) is configured to enable necessary corrections to be made and the respective project to be completed by testing different scenarios and user cases. The server (3) is configured to enable the model to be continuously improved by receiving feedback from users after the respective projects are completed. Industrial Application of the Invention

[0019] By means of the inventive system (1), it is enabled to process visuals taken from inside a vehicle with the support of artificial intelligence, to change the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and to publish them on a standardised ground.

[0020] Within these basic concepts; it is possible to develop various embodiments of the inventive “In-Vehicle Image Processing System (1)”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

CLAIMS1. A system (1) for processing visuals taken from inside a vehicle with the support of artificial intelligence, changing the backdrop by removing the background and the exterior parts of the vehicle -including the windows, exterior parts through the open door- from the visual, and publishing them on a standardised ground comprising; at least one database (2) which is configured to keep a record of in-vehicle visual data and information data in the form of visual format, size, content and intended use of the said data; and characterized by at least one server (3) which is configured to receive in-vehicle visual data from various sources and to enable them to be recorded in the database; to label specific areas of the visuals in the form of vehicle seats, steering wheel and control panel via various labelling tools; to train the artificial intelligence model by using the labelled data set; to remove the background and to add a new backdrop in in-vehicle visuals via the trained model; to enable the developed artificial intelligence models to be integrated into various web and application platforms; to enable visuals to be analysed and edited by artificial intelligence via automated processes; and to enable the developed flow and the changes made to be tested and validated.

2. A system (1) according to Claim 1; characterized by the database (2) which is configured to communicate and exchange data with the server (3) by using any communication protocol.

3. A system (1) according to Claim 1 or 2; characterized by the database (2) which is configured to be managed by the server (3).

4. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to communicate and exchange data with the database (2) by using any communication protocol.

5. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to manage the database (2).

6. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the visuals to be edited and published in a consistent manner via Al-supported changes.

7. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable human errors to be reduced through automated analysis and change processes.

8. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the visuals to be changed in a unique and impressive way by using artificial intelligence, image processing and graphic design techniques.

9. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to collect existing in-vehicle visuals from the respective mobile platforms, to enable the information in the form of format, size, content and intended use of the visuals to be recorded in the database (2) and datasets to be prepared.

10. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the specific areas in the form of vehicle seats, steering wheel and control panel in the visuals received by using data labelling software in the form of Labelme, Labelbox, Labelling, Label Studio to be labelled.

11. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the segmentation of in-vehicle visuals to be performed by using high-level state-of-the-art models in the form of UNet, U2Net, ResNet and SegNet.

12. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the performance of the model to be evaluated via metrics in the form of AP (Average Precision), loU (Intersection Over Union) and Dice Coefficient and improvements to be performed.

13. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the background to be removed, a new backdrop to be added, and edits to be performed according to the factors in the form of aesthetic value, usability and brand compatibility, in in-vehicle visuals via the trained model.

14. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable artificial intelligence models to be integrated into various websites and mobile platforms, and visuals to be analysed and edited by artificial intelligence via automated processes on the said websites and platforms.

15. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable necessary corrections to be made and the respective project to be completed by testing different scenarios and user cases.

16. A system (1) according to any one of the preceding claims; characterized by the server (3) which is configured to enable the model to be continuouslyimproved by receiving feedback from users after the respective projects are completed.

Images