Indoor space evaluation method, device and equipment and computer readable storage medium
Through the neural network model, the distance difference between targets in the cab is identified and fitted, the problem of inconsistent human subjective evaluation is solved, and the accuracy and reliability of spatial evaluation are improved.
Patent Information
- Application Number
- CN202411152252.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-12-13
AI Technical Summary
In cab design, artificial subjective evaluations lead to inconsistent evaluation due to individual differences, resulting in poor spatial evaluation accuracy.
By inputting the image in the cab into the trained neural network model, the distance difference between the targets is identified, and the machine score value and manual subjective evaluation value are combined for fitting processing, the more accurate final score is output to reduce the influence of subjective factors. .
It improves the accuracy and reliability of cab space evaluation and reduces the evaluation differences caused by individual psychological and physiological qualities.
Smart Images
Figure CN119131764A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of cab interior space evaluation, and in particular to an interior space evaluation method, device, equipment and computer-readable storage medium. Background Art
[0002] When designing the human-machine layout of a commercial vehicle cab, key focus areas include the distance between seats in the cab, the distance from the seat to the dashboard, the distance from the gear lever to the dashboard, and the distance from the front top storage box to the upper berth, which have a great impact on the evaluation of the interior space.
[0003] Currently, after the cab design is completed, in order to ensure that the designed vehicle can meet the comfort requirements, that is, conform to human physiological functions and psychological characteristics, a model that is basically consistent with the real vehicle will be made first, and then the layout of the model will be verified and subjectively evaluated.
[0004] In the related art, different people have different experience values and different experiences with design solutions, which leads to different evaluations. The evaluation scores may be higher or lower, which is too subjective and leads to poor accuracy of space evaluation. Summary of the invention
[0005] The present application provides an indoor space evaluation method, device, equipment and computer-readable storage medium, which can solve the technical problems existing in the related art that different people have different experience values, have different experiences with design schemes, and thus have different evaluations, and there will be high or low evaluation scores, which are too subjective and lead to poor accuracy of space evaluation.
[0006] In a first aspect, an embodiment of the present application provides an indoor space evaluation method, the indoor space evaluation method comprising:
[0007] Import the collected in-cabin images into the trained neural network model, identify the distance difference between the objects in the image, and output the machine score value corresponding to the distance difference between the objects in the image;
[0008] The machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target are fitted and the final score of the distance difference between each target is output.
[0009] In combination with the first aspect, in one implementation, the fitting process is performed on the machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target, and the final score of the distance difference between each target is output, including:
[0010] The average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets is taken as the final score of the distance difference between the two targets.
[0011] In combination with the first aspect, in one implementation, the fitting process is performed on the machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target, and the final score of the distance difference between each target is output, including:
[0012] If the difference between the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between two targets exceeds the set range, a second manual subjective evaluation score of the distance difference between the two targets is obtained;
[0013] If the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score do not exceed the set range, the average of the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score is taken, and the average is used as the final score of the image.
[0014] In combination with the first aspect, in one implementation, before importing the collected in-cab image into a trained neural network model, identifying the distance difference between each target in the image, and outputting a machine score value corresponding to the distance difference between each target in the image, the method includes:
[0015] Importing multiple images with artificial subjective evaluation scores into a neural network model, identifying the distance difference between each target in each image; wherein the distance difference between each target in each image and the artificial subjective evaluation scores corresponding to the distance difference between each target form multiple neural network training samples;
[0016] The neural network model is trained using multiple neural network training samples to obtain a trained neural network model.
[0017] In combination with the first aspect, in one implementation, each target includes a person and surrounding target parts, and the method of importing the collected in-cab image into a trained neural network model, identifying the distance difference between each target in the image, and outputting a machine score value corresponding to the distance difference between each target in the image includes:
[0018] The collected images inside the cab are imported into the trained neural network model to identify the distance difference between the person in the image and the surrounding target parts, and output the machine score value corresponding to the distance difference between the person in the image and the target parts.
[0019] In a second aspect, an embodiment of the present application provides an indoor space evaluation device, the indoor space evaluation device comprising:
[0020] A machine scoring value output module is used to import the collected cab image into the trained neural network model, identify the distance difference between each target in the image, and output the machine scoring value corresponding to the distance difference between each target in the image;
[0021] The final score output module is used to fit the machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target, and output the final score of the distance difference between each target.
[0022] In combination with the second aspect, in one embodiment, the final score output module is also used to take the average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets, and the average value is used as the final score of the distance difference between the two targets.
[0023] In conjunction with the second aspect, in one implementation, the indoor space evaluation device further includes:
[0024] A frame and a plurality of target components assembled in the frame, wherein an adjustment mechanism is installed between the target components and the frame, and the adjustment mechanism can adjust the spatial position of the target components in the frame.
[0025] In a third aspect, an embodiment of the present application provides an indoor space evaluation device, characterized in that the indoor space evaluation device includes a processor, a memory, and an indoor space evaluation program stored in the memory and executable by the processor, wherein when the indoor space evaluation program is executed by the processor, the steps of the indoor space evaluation method described in some of the above embodiments are implemented.
[0026] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which an indoor space evaluation program is stored, wherein when the indoor space evaluation program is executed by a processor, the steps of the indoor space evaluation method as described in some of the above embodiments are implemented.
[0027] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0028] By importing the collected images in the cab into the trained neural network model, the distance difference between each target in the image is identified, and the machine score corresponding to the distance difference between each target in the image is output; and the machine score corresponding to the distance difference between each target and the manual subjective evaluation score are fitted to output the final score of the distance difference between each target. In the development process of the interior layout of the cab of a new model, the collected images in the cab are input into the trained neural network model, and the corresponding machine score can be output. In combination with the manual subjective evaluation score corresponding to the distance difference between each target, a more accurate final score of the distance difference between each target is output, which improves the problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers. Due to the differences in psychological and physiological qualities of each person, the sensitivity to distance difference is also very different, so it is difficult to obtain a recognized evaluation method. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 This is a flow chart of an embodiment of an indoor space evaluation method of the present application;
[0030] Figure 2 This is a schematic diagram of the three-dimensional structure of the indoor space evaluation device of this application;
[0031] Figure 3 for Figure 2 Schematic diagram of the structure from the top of the interior;
[0032] Figure 4 This is a schematic diagram of the hardware structure of the indoor space evaluation device involved in the embodiment of the present application.
[0033] In the picture: 1. Instrument panel; 2. Seat; 3. Bunk; 4. Top cover interior; 5. Front top storage box; 6. Gear lever guard; 7. Frame. DETAILED DESCRIPTION
[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0035] It is important to understand that when designing the human-machine layout of a commercial vehicle cab, the distance between seats, the distance from the seat to the dashboard, the distance from the gear lever to the dashboard, and the distance from the front top storage box to the upper berth are key areas of concern, which have a great impact on the evaluation of the interior space. Currently, after the cab design is completed, in order to ensure that the designed vehicle can meet the comfort requirements, that is, in line with human physiological functions and psychological characteristics, a model that is basically consistent with the real vehicle will be made first, and then the layout of the model will be verified and subjectively evaluated.
[0036] Because different people have different experience values and different experiences with design solutions, they give different evaluations. The evaluation scores may be higher or lower, which is too subjective and leads to poor accuracy in space evaluation.
[0037] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.
[0038] In a first aspect, an embodiment of the present application provides an indoor space evaluation method.
[0039] In one embodiment, referring to Figure 1 , Figure 1This is a flow chart of an embodiment of the indoor space evaluation method of the present application. Figure 1 As shown in Figure 2, the indoor space evaluation methods include:
[0040] S100: importing the collected in-cabin image into the trained neural network model, identifying the distance difference between each target in the image, and outputting the machine score value corresponding to the distance difference between each target in the image;
[0041] S200: Fitting the machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target, and outputting the final score of the distance difference between each target.
[0042] In this embodiment, the distance difference between each target in the image is identified by importing the collected image into the trained neural network model, and the machine score corresponding to the distance difference between each target in the image is output; and the machine score corresponding to the distance difference between each target and the manual subjective evaluation score are fitted to output the final score of the distance difference between each target. In the development process of the interior layout of the new model cab, the collected image in the cab is input into the trained neural network model, and the corresponding machine score can be output, and combined with the manual subjective evaluation score corresponding to the distance difference between each target, a more accurate final score of the distance difference between each target is output, which improves the problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers. Due to the differences in psychological and physiological qualities of each person, the sensitivity to the distance difference is also very different, so it is difficult to obtain a recognized evaluation method. .
[0043] Furthermore, in one embodiment, S200 includes the following steps:
[0044] S201: Take the average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets, and use the average as the final score of the distance difference between the two targets.
[0045] In this embodiment, by taking the average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets, the average value is used as the final score of the distance difference between the two targets, which can further improve the accuracy and reliability of the evaluation of the cab interior space.
[0046] Furthermore, in one embodiment, S200 includes the following steps:
[0047] S201: If the difference between the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between the two targets exceeds a set range, a second manual subjective evaluation score of the distance difference between the two targets is obtained;
[0048] S202: If the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score do not exceed the set range, take an average of the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score, and use the average as the final score of the image.
[0049] In this embodiment, when the difference between the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between two targets exceeds the set range, it may be due to the lack of experience of the engineer or misjudgment, which means that the manual subjective evaluation is not accurate enough and the subjective factor accounts for too large a proportion. Consider re-obtaining the second manual subjective evaluation score of the distance difference between the two targets. If the machine scoring score and the second manual subjective evaluation score corresponding to the distance difference between the two targets do not exceed the set range, the machine scoring score and the second manual subjective evaluation score corresponding to the distance difference between the two targets are averaged, and the average value is used as the final score of the image. This can further improve the accuracy and reliability of the evaluation of the interior space of the cab.
[0050] Furthermore, in one embodiment, before S100, the following steps are included:
[0051] S000-1: Import multiple images with human subjective evaluation scores into the neural network model to identify the distance difference between each target in each image; wherein the distance difference between each target in each image and the human subjective evaluation score corresponding to the distance difference between each target form multiple neural network training samples;
[0052] S000-2: Use multiple neural network training samples to train the neural network model, thereby obtaining a trained neural network model.
[0053] In this embodiment, before the space evaluation in the cab is performed, the neural network model to be used needs to be trained, wherein the neural network model has the advantages of self-learning, automatic optimization, good fault tolerance, etc., can automatically learn the intrinsic characteristics of the input data, does not need to manually design the feature extraction algorithm, can continuously adjust its own weight during the network training process, so that the neural network model has higher efficiency and accuracy during operation, to output the distance difference between each target in the image. Import multiple images of artificial subjective evaluation scores into the neural network model, identify the distance difference between each target in each image, and form multiple neural network training samples with the distance difference between each target in each image and the artificial subjective evaluation score corresponding to the distance difference between each target. Use multiple neural network training samples to train the neural network model, that is, obtain a trained neural network model. To achieve the subsequent space evaluation in the cab, import the collected cab images into the trained neural network model, identify the distance difference between each target in the image, and output the machine scoring value corresponding to the distance difference between each target in the image; then fit the machine scoring value corresponding to the distance difference between each target and the artificial subjective evaluation score, and output the final score of the distance difference between each target.
[0054] Furthermore, in one embodiment, in S100, the following steps are included:
[0055] S100-1: Each target includes a person and surrounding target parts. The collected images inside the cab are imported into the trained neural network model to identify the distance difference between the person and the surrounding target parts in the image, and output the machine score value corresponding to the distance difference between the person and the target parts in the image.
[0056] In this embodiment, the distance difference between each target in the image can be the distance difference between a person and the surrounding target parts. According to the distance difference between a person and the surrounding target parts, the trained neural network model outputs a machine scoring value corresponding to the distance difference between a person and the target parts in the image. The machine scoring value corresponding to the distance difference between a person and the target parts and the manual subjective evaluation score are fitted to output the final score of the distance difference between each target.
[0057] Furthermore, in one embodiment, in S100, the following steps are included:
[0058] S100-1: Import the collected in-cab image into the trained neural network model, identify the distance difference between target components in the image, and output the machine score value corresponding to the distance difference between target components in the image.
[0059] In this embodiment, the distance difference between each target in the image can also be the distance difference between each target component. According to the distance difference between each target component, the trained neural network model outputs a machine scoring value corresponding to the distance difference between a person and the target component in the image. The machine scoring value corresponding to the distance difference between the target components and the manual subjective evaluation score are fitted to output the final score of the distance difference between each target.
[0060] In a second aspect, an embodiment of the present application also provides an indoor space evaluation device, which includes: a machine scoring value output module, which is used to import the collected cab interior image into a trained neural network model, identify the distance difference between each target in the image, and output the machine scoring value corresponding to the distance difference between each target in the image; a final score output module, which is used to fit the machine scoring value corresponding to the distance difference between each target and the manual subjective evaluation score, and output the final score of the distance difference between each target.
[0061] In this embodiment, the collected cab image is imported into the trained neural network model through the machine scoring value output module, the distance difference between each target in the image is identified, and the machine scoring value corresponding to the distance difference between each target in the image is output; and the final score output module fits the machine scoring value corresponding to the distance difference between each target and the manual subjective evaluation score, and outputs the final score of the distance difference between each target. This improves the problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers, and because each person has different psychological and physiological qualities, the sensitivity to distance difference is also very different, so it is difficult to obtain a recognized evaluation method.
[0062] Furthermore, in one embodiment, the indoor space evaluation device may also include: a frame 7 and a plurality of target components assembled in the frame 7, an adjustment mechanism is installed between the target components and the frame 7, and the adjustment mechanism can adjust the spatial position of the target components in the frame 7.
[0063] In this embodiment, Figure 2 and Figure 3As shown, the frame 7 is sequentially installed with an instrument panel 1, a seat 2, a berth 3, a top cover interior 4, a front top sundries box 5 and a gear lever shield 6, wherein the seat 2 includes a driver seat and a passenger seat, and the berth 3 includes an upper berth and a lower berth. A corresponding adjustment mechanism is installed between each component and the frame 7, and the adjustment mechanism can adjust the spatial position of the components connected thereto in the frame 7 to achieve the change of the distance difference between the components, so as to facilitate the engineers to perform manual subjective scoring, and facilitate the image acquisition module to collect the image of the cab environment, import the subsequently trained neural network model, identify the distance difference between the targets in the image, and output the machine score value corresponding to the distance difference between the targets in the image, fit the machine score value corresponding to the distance difference between the targets and the manual subjective evaluation score, and output the final score of the distance difference between the targets. The problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers is improved, and the sensitivity to the distance difference is also very different due to the differences in the psychological and physiological qualities of each person, so it is difficult to obtain a recognized evaluation method.
[0064] Specifically, the adjustment mechanism will not be described in detail. The adjustment mechanism can connect the cylinder or electric push rod with the corresponding target component to achieve forward and backward or left and right movement of the target component; the adjustment mechanism can also be a manipulator to achieve spatial movement of the target component; the adjustment mechanism can also realize the linear movement of the target component driven by the servo linear motor.
[0065] Among them, the functional implementation of each module in the above-mentioned indoor space evaluation device corresponds to each step in the above-mentioned indoor space evaluation method embodiment, and its functions and implementation processes are no longer repeated here.
[0066] In a third aspect, an embodiment of the present application provides an indoor space evaluation device, which may be a device with data processing function, such as a personal computer (PC), a laptop computer, or a server.
[0067] In this embodiment, the device imports the collected images in the cab into the trained neural network model, identifies the distance difference between each target in the image, and outputs the machine score corresponding to the distance difference between each target in the image; and performs fitting processing on the machine score corresponding to the distance difference between each target and the manual subjective evaluation score, and outputs the final score of the distance difference between each target. In the development process of the interior layout of the cab of a new model, the collected images in the cab are input into the trained neural network model, and the corresponding machine score can be output, and combined with the manual subjective evaluation score corresponding to the distance difference between each target, a more accurate final score of the distance difference between each target is output, which improves the problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers. Due to the differences in psychological and physiological qualities of each person, the sensitivity to the distance difference is also very different, so it is difficult to obtain a recognized evaluation method.
[0068] Reference Figure 4 , Figure 4 Schematic diagram of the hardware structure of the indoor space evaluation device involved in the embodiment of the present application. In the embodiment of the present application, the indoor space evaluation device may include a processor, a memory, a communication interface and a communication bus.
[0069] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0070] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the indoor space evaluation device, and the interface used to realize the interconnection between the indoor space evaluation device and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0071] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0072] The processor may be a general-purpose processor, and the general-purpose processor may call the indoor space evaluation program stored in the memory and execute the indoor space evaluation method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the indoor space evaluation program is called may refer to the various embodiments of the indoor space evaluation method of the present application, and will not be repeated here.
[0073] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0074] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.
[0075] The readable storage medium of the present application stores an indoor space evaluation program, wherein when the indoor space evaluation program is executed by a processor, the steps of the indoor space evaluation method described above are implemented.
[0076] In this embodiment, the readable storage medium imports the collected images in the cab into the trained neural network model, identifies the distance difference between each target in the image, and outputs the machine score corresponding to the distance difference between each target in the image; and performs fitting processing on the machine score corresponding to the distance difference between each target and the manual subjective evaluation score, and outputs the final score of the distance difference between each target. In the development process of the interior layout of the cab of a new model, the collected images in the cab are input into the trained neural network model, and the corresponding machine score can be output, and combined with the manual subjective evaluation score corresponding to the distance difference between each target, a more accurate final score of the distance difference between each target is output, which improves the problem that the traditional space evaluation method simply relies on the subjective evaluation of engineers. Due to the differences in psychological and physiological qualities of each person, the sensitivity to the distance difference is also very different, so it is difficult to obtain a recognized evaluation method.
[0077] Among them, the method implemented when the indoor space evaluation program is executed can refer to the various embodiments of the indoor space evaluation method of the present application, and will not be repeated here.
[0078] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0079] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0080] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0081] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or. For example, A / B can mean A or B. The “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0082] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0083] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0084] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for evaluating indoor space, characterized in that: The indoor space evaluation method comprises: Import the collected in-cabin images into the trained neural network model, identify the distance difference between the objects in the image, and output the machine score value corresponding to the distance difference between the objects in the image; The machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target are fitted and the final score of the distance difference between each target is output.
2. The indoor space evaluation method according to claim 1, characterized in that: The machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target are fitted to output the final score of the distance difference between each target, including: The average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets is taken as the final score of the distance difference between the two targets.
3. The indoor space evaluation method according to claim 1, characterized in that: The machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target are fitted to output the final score of the distance difference between each target, including: If the difference between the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between two targets exceeds the set range, a second manual subjective evaluation score of the distance difference between the two targets is obtained; If the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score do not exceed the set range, the average of the machine scoring score corresponding to the distance difference between the two targets and the second manual subjective evaluation score is taken, and the average is used as the final score of the image.
4. The indoor space evaluation method according to claim 1, characterized in that: Before importing the collected in-cab image into the trained neural network model, identifying the distance difference between the objects in the image, and outputting the machine score value corresponding to the distance difference between the objects in the image, the following steps are included: Importing multiple images with artificial subjective evaluation scores into a neural network model, identifying the distance difference between each target in each image; wherein the distance difference between each target in each image and the artificial subjective evaluation scores corresponding to the distance difference between each target form multiple neural network training samples; The neural network model is trained using multiple neural network training samples to obtain a trained neural network model.
5. The indoor space evaluation method according to claim 1, characterized in that: Each target includes people and surrounding target parts. The method of importing the collected in-cabin image into the trained neural network model, identifying the distance difference between each target in the image, and outputting the machine score value corresponding to the distance difference between each target in the image includes: The collected images inside the cab are imported into the trained neural network model to identify the distance difference between the person in the image and the surrounding target parts, and output the machine score value corresponding to the distance difference between the person in the image and the target parts.
6. An indoor space evaluation device, characterized in that: The indoor space evaluation device comprises: A machine scoring value output module is used to import the collected cab image into the trained neural network model, identify the distance difference between each target in the image, and output the machine scoring value corresponding to the distance difference between each target in the image; The final score output module is used to fit the machine scoring value and the manual subjective evaluation score corresponding to the distance difference between each target, and output the final score of the distance difference between each target.
7. The indoor space evaluation device according to claim 6, characterized in that: The final score output module is also used to take the average of the machine scoring score and the manual subjective evaluation score corresponding to the distance difference between any two adjacent targets, and use the average as the final score of the distance difference between the two targets.
8. The indoor space evaluation device according to claim 6, characterized in that: The indoor space evaluation device further comprises: A frame and a plurality of target components assembled in the frame, wherein an adjustment mechanism is installed between the target components and the frame, and the adjustment mechanism can adjust the spatial position of the target components in the frame.
9. An indoor space evaluation device, characterized in that: The indoor space evaluation device includes a processor, a memory, and an indoor space evaluation program stored in the memory and executable by the processor, wherein when the indoor space evaluation program is executed by the processor, the steps of the indoor space evaluation method according to any one of claims 1 to 6 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an indoor space evaluation program, wherein when the indoor space evaluation program is executed by a processor, the steps of the indoor space evaluation method according to any one of claims 1 to 6 are implemented.