Dynamic image generation system
Through the dynamic image generation system, the journey movie is automatically generated based on the shooting data of the dash recorder, which solves the real-time analysis needs in the vehicle, and realizes the effect of generating journey movies without adding high-processing analysis devices, simplifying the system design And reduce costs.
Patent Information
- Application Number
- CN202410652328.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-06-29
- Filing Date
- 2024-05-24
- Publication Date
- 2024-12-31
AI Technical Summary
In driving vehicles, it is necessary to implement real-time analysis of occupants' expressions and speeches, resulting in the need to be equipped with a high processing capability analysis system, which increases system complexity and cost.
The dynamic image generation system analyzes the shooting data based on the driving recorder and automatically generates dynamic images, edits images of specific emotions, postures and places, and uses them as the editing range of the journey movie, using the dynamic image generation server outside the car for Analysis and editing of images and sounds.
It realizes automatic generation of travel movies without installing high-processing capability analysis devices in the vehicle, reducing the processing needs and costs of the system, simplifying the system design, and having the effect of creating travel movies.
Smart Images

Figure CN119233015A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a dynamic image generation system. Background Art
[0002] Japanese Patent Application Laid-Open No. 2017-194950 describes a technology for automatically generating a travel album by automatically recording images and sounds inside and outside the vehicle based on the analysis results of the expressions and speech of the passengers.
[0003] In the above-mentioned conventional technology, it is necessary to analyze the facial expressions and speech of passengers in real time while the vehicle is running, and therefore, it is necessary to install an analysis system with high processing capability in the vehicle. Summary of the invention
[0004] A moving image generation system for solving the above-mentioned problem is configured to set a trimming range based on an analysis result of captured data of a drive recorder, and automatically generate a moving image by trimming an image of the trimming range from the captured data.
[0005] The above-described dynamic image generation system has the effect of facilitating the creation of a travel movie.
[0006] Features, advantages, and technical and industrial significance of exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which like reference numerals denote like elements. BRIEF DESCRIPTION OF THE DRAWINGS
[0007] Figure 1 is a diagram schematically showing the configuration of one embodiment of a dynamic image generation system;
[0008] Figure 2 It is a timing chart showing the steps of generating a moving image in the moving image generating system. DETAILED DESCRIPTION
[0009] Below, refer to Figure 1 as well as Figure 2 An embodiment of a dynamic image generation system will be described in detail.
[0010] On the structure of the dynamic image generation system
[0011] First, refer to Figure 1 The configuration of the moving image generation system of the present embodiment will be described. The moving image generation system of the present embodiment automatically edits moving images captured by the drive recorder 11 during a trip and provides the same to the user of the vehicle 10 .
[0012] like Figure 1As shown, a driving recorder 11 is provided in a vehicle 10. The driving recorder 11 includes an in-vehicle camera 12 for photographing the interior of the vehicle, an out-vehicle camera 13 for photographing the exterior of the vehicle, and a microphone 14 for recording sounds in the vehicle. In addition, a data storage device 15 is provided in the vehicle 10, and the data storage device 15 records the images photographed by the in-vehicle camera 12 and the out-vehicle camera 13 of the driving recorder 11, and the data of the sounds recorded by the microphone 14. The data storage device 15 may be built in the driving recorder 11, or may be provided outside the driving recorder 11.
[0013] In addition, a human-machine interface (HMI) 16 and a communication module 17 are provided in the vehicle 10. The HMI 16 is an interface that connects the system of the vehicle 10 with the occupants. As an example of the HMI 16, a touch panel display can be cited. The communication module 17 is an electronic component for wirelessly communicating with the outside of the vehicle. The driving recorder 11, the data storage 15, the HMI 16, and the communication module 17 are connected via the in-vehicle network 18 so as to be able to communicate with each other.
[0014] The dynamic image generation system of this embodiment automatically generates a travel movie as a dynamic image based on the image captured by the driving recorder 11 of such a vehicle 10. The dynamic image generation system includes a dynamic image generation server 20, which is a server device for dynamic image generation. The dynamic image generation server 20 includes: a processor 21 that performs various processes for dynamic image generation; and a memory 22 that stores a program for dynamic image generation or various data for dynamic image generation. In addition, the dynamic image generation server 20 includes a communication module 23 for performing data communication with the vehicle 10.
[0015] About the creation of travel movies
[0016] Next, we will refer to Figure 2 The automatic generation of a travel movie according to the present embodiment is described. The dynamic image generation system of the present embodiment creates a travel movie based on the shooting data of the driving recorder 11 during the journey. The shooting data of the driving recorder 11 includes the images captured by the in-vehicle camera 12 and the out-vehicle camera 13 and the sounds picked up by the microphone 14. In addition, the shooting data includes the shooting location and time information of the dynamic image obtained from the vehicle-mounted GPS device.
[0017] When creating a journey movie, the user of the vehicle 10 inputs the dynamic image settings on the HMI 16 (S1). The dynamic image settings are the specifications of the dynamic image to be generated. As items of the dynamic image settings, the time of the dynamic image, the name of the music used as the background music of the dynamic image, the title of the dynamic image, etc. can be listed. In addition, in the dynamic image settings, specify the characters, period, and place that you want to include in the generated dynamic image. In addition, the user inputs the date and time of the journey in the dynamic image settings. Afterwards, when the user of the vehicle 10 performs a sending instruction operation on the HMI 16 (S2), the information of the dynamic image settings input by the user in S1 is sent to the dynamic image generation server 20 together with the shooting data during the journey stored in the data storage device 15 (S3).
[0018] The dynamic image generation server 20 performs image analysis and sound analysis on the received shooting data (S4), and sets a clipping range of the dynamic image based on the analysis result (S5). Subsequently, the dynamic image generation server 20 generates data obtained by editing the dynamic images in the clipping range from the shooting data during the journey and connecting them, as dynamic image data of the journey movie (S6). Thereafter, the dynamic image generation server 20 transmits the generated dynamic image data to the vehicle 10 (S7). The vehicle 10 stores the received dynamic image data in the data storage 15 (S8).
[0019] About clip range settings
[0020] Description Figure 2 The setting of the editing range implemented by the dynamic image generation server 20 in S5. Based on the analysis results of the image and sound, the dynamic image generation server 20 extracts the period when the occupant of the vehicle 10 is in an excited mood, and sets the period as the editing range. By analyzing the occupant's expression and sound, it is determined whether the occupant is in an excited mood. The music played in the car can be used as a criterion for judging whether the occupant is in an excited mood. Specifically, the dynamic image generation server 20 analyzes the volume, melody or song name of the music played in the car, and uses the analysis result to determine whether the occupant is in an excited mood.
[0021] Furthermore, the moving image generation server 20 sets the following period of the moving image as a clipping range.
[0022] When confirming, based on the analysis result of the video, that the occupant is making a predetermined gesture, the moving image generation server 20 sets a period starting from the time when the occupant is making the gesture as the editing range.
[0023] The video generation server 20 sets the video of the time and place specified by the user as the clipping range in the video setting. Examples of the above-mentioned time include the departure time of the journey and the arrival time at the destination. The video generation server 20 sets such a clipping range based on the information of the shooting location and shooting time included in the video data.
[0024] The video generation server 20 sets the range in the video that includes the person specified in the video setting as the trimming range. The video generation server 20 identifies the person in the video by face recognition.
[0025] The video generation server 20 sets the editing range so that the time of the generated video matches the time set in the video setting. Furthermore, when generating the video, the video generation server 20 inserts the music specified by the user in the video setting as background music.
[0026] Effects of implementation methods
[0027] The operation of the moving image generation system according to this embodiment will be described.
[0028] In this embodiment, the shooting data of the driving recorder 11 during the journey is sent to the dynamic image generation server 20 outside the vehicle. Then, the dynamic image generation server 20 sets a clipping range based on the analysis results of the image and sound of the shooting data, and generates a dynamic image as a journey movie by clipping the image of the clipping range from the shooting data.
[0029] When such image and sound analysis for dynamic image generation is performed in real time during the shooting of the driving recorder 11, it is necessary to install an analysis device with high processing capabilities in the vehicle 10. In the case of this embodiment, the image and sound analysis for dynamic image generation is performed by the dynamic image generation server 20 outside the vehicle after shooting. Even if an analysis device with high processing capabilities is not installed in the vehicle 10, a travel movie can be automatically generated.
[0030] As described above, in this embodiment, even if an analysis device with high processing power is not installed in the vehicle 10, a travel movie can be automatically generated using the shooting data of the drive recorder 11. Therefore, the dynamic image generation system of this embodiment has the effect of facilitating the creation of a travel movie.
[0031] Other Implementations
[0032] This embodiment can be implemented by being modified as follows. This embodiment and the following modified examples can be implemented in combination with each other within the range that there is no technical contradiction.
[0033] The music played in the car during the shooting of the shooting data may also be used as the background music of the generated dynamic image. In this case, the dynamic image generation server 20 determines the music played in the car by sound analysis of the shooting data. Then, the dynamic image generation server 20 inserts the determined music as background music into the generated dynamic image. At this time, the cheerful part of the image may also be synchronized with the chorus part of the music.
[0034] It can also be done through a user terminal (PC, etc.) outside the vehicle. Figure 2 In this case, the shooting data of the driving recorder 11 is moved or copied to the user terminal using a memory card, etc., and then sent from the user terminal to the dynamic image generation server 20. Furthermore, the processing performed by the dynamic image generation server 20 can also be performed by the user terminal. In this case, the user terminal constitutes a dynamic image generation system.
[0035] The processing related to the dynamic image generation performed by the dynamic image generation server 20 in the above-mentioned embodiment may also be implemented in the vehicle 10. In this case, it is also unnecessary to perform the analysis of the image and sound for dynamic image generation in real time. Therefore, the processing capacity required of the processing device mounted on the vehicle 10 for generating dynamic images can be suppressed to a low level.
Claims
1. A dynamic image generation system, wherein: A clipping range is set according to the analysis result of the shooting data of the driving recorder, and a dynamic image is automatically generated by clipping the image of the clipping range from the shooting data.
2. The dynamic image generation system according to claim 1, wherein: The clipping range is set based on the sound inside the vehicle recorded in the photographic data.
3. The dynamic image generation system according to claim 1, wherein: The trimming range is set based on a piece of music played in a car during shooting of the shot data.
4. The dynamic image generation system according to claim 1, wherein: The music played in the car during the shooting of the shooting data is used as the background music of the moving image.
5. The dynamic image generation system according to claim 1, wherein: The range of the video that includes the designated person, or the range starting from the time when the person in the video performs a specific gesture is set as the editing range.
