An image projection system based on projector

Abstract

The present invention provides an image projection system based on a projector, which performs surface calibration on the projector based on a projection area, determines projector parameters and projection parameters according to the calibration result, ensures the accuracy of projection angle and distance, then determines an initial projection picture based on the projector parameters and projection parameters, performs picture evaluation on the initial projection picture based on an image evaluation model, obtains picture evaluation results, evaluates the projection picture, obtains substandard features of picture display based on the picture evaluation results, divides the substandard features into correctable features and uncorrectable features, determines features that can be corrected by parameter adjustment, provides a basis for parameter adjustment, and finally, based on the correctable features and in combination with an optimization method, optimizes the projector parameters and projection parameters, obtains a target projection picture, adjusts the projection image, improves the projection effect, and brings a good visual experience to users.

Description

Technical Field

[0001] The present invention relates to the field of projection display technology, and in particular to an image projection system based on a projector. Background Art

[0002] With the development of science and technology and the continuous improvement of people's living standards, people have higher and higher requirements for visual experience. On the one hand, people's requirements for display devices of human-computer interfaces are increasingly developing in the direction of miniature, large screen and high resolution; on the other hand, in terms of display effects, people tend to pursue augmented reality and immersive visual enjoyment.

[0003] The Chinese patent application number CN201711494846.5 provides a method, device and system for adaptive dynamic projection of the projection area to solve the problem in the prior art that when the direction of the user's intended projection is affected by the projection space environment, the projection display effect will be relatively poor and the user experience will be bad. However, the above scheme only improves the projection effect by adjusting the projection direction, and does not adjust the brightness, color saturation and clarity of the projected image according to the actual situation. The effect of the projection picture needs to be improved, and the user's visual experience needs to be improved. Summary of the invention

[0004] The present invention provides an image projection system based on a projector, so as to solve the problems raised in the background technology.

[0005] An image projection system based on a projector, comprising:

[0006] A parameter determination module, used to perform surface calibration on the projector based on the projection area, and determine the projector parameters and projection parameters according to the calibration results;

[0007] A picture evaluation module is used to determine an initial projection picture based on projector parameters and projection parameters, and to perform picture evaluation on the initial projection picture based on an image evaluation model to obtain a picture evaluation result;

[0008] A feature analysis module, used for obtaining non-standard features of the screen display based on the screen evaluation result, and classifying the non-standard features into correctable features and non-correctable features;

[0009] The parameter optimization module is used to optimize the projector parameters and projection parameters based on the modifiable features and in combination with the optimization method to obtain the target projection picture.

[0010] Preferably, the parameter determination module includes:

[0011] A calibration unit is used to establish an X-axis-Y-axis coordinate system of the projection area. The projector performs surface calibration based on the X-axis-Y-axis coordinate system to determine the correction error and the measurement error.

[0012] A setting unit, configured to set projector parameters based on the calibration error and the measurement error;

[0013] The matching unit is used to match the projection coefficient corresponding to the projector parameters based on the instrument-projection parameter correspondence.

[0014] Preferably, the picture evaluation module includes:

[0015] A projection unit, used to determine a projection image according to the projector parameters, and project the projection image using the projection parameters to obtain an initial projection image;

[0016] A marking unit, used for acquiring a screen image of the initial projection screen, and marking the screen image based on an evaluation index to obtain a marked screen image;

[0017] The evaluation unit is used to input the marked picture image into an image evaluation model to output an evaluation value, and generate a picture evaluation result based on the evaluation value.

[0018] Preferably, the marking unit comprises:

[0019] An extraction unit, used to determine a feature extraction method for the initial projection picture based on the evaluation index, and extract the initial projection picture according to the feature extraction method to obtain extraction layer information;

[0020] The information marking unit is used to mark the corresponding extraction layer information based on the indicator attributes of the evaluation indicator to obtain a marked screen image.

[0021] Preferably, the evaluation unit comprises:

[0022] A training unit, used to establish an indicator modal model of the evaluation indicator based on the artificial neural network model, and train the indicator modal model based on the first historical picture data of the evaluation indicator to obtain a target indicator modal model;

[0023] A model building unit is used to determine the resource allocation information of the target indicator modal model based on the proportion of the evaluation indicator in the standard comprehensive evaluation result, obtain the marking features of the evaluation indicator in the marking screen image, determine the model splicing method of the target indicator modal model based on the overlapping features between the marking features, splice all the target indicator modal models according to the resource allocation information and the model relying method, and obtain an initial image evaluation model;

[0024] A convergence training unit, used to train the initial image evaluation model based on the second historical picture data of the historical projection picture until a preset model convergence requirement is met to obtain an image evaluation model;

[0025] An evaluation unit, used for inputting the marked screen image into an image evaluation model to output an index evaluation value and a comprehensive evaluation value;

[0026] The result acquisition unit is used to match the indicator evaluation value with the evaluation indicator to obtain a single indicator evaluation result, obtain a comprehensive evaluation result based on the comprehensive evaluation value, and use the single indicator evaluation result and the comprehensive evaluation result as the picture evaluation result.

[0027] Preferably, the feature analysis module includes:

[0028] A judgment unit, configured to obtain a single indicator evaluation value from the picture evaluation result, and based on a preset evaluation threshold, obtain a first to-be-detected evaluation indicator that does not meet the evaluation requirement from the single indicator evaluation value;

[0029] The judging unit is further configured to obtain a comprehensive evaluation value from the picture evaluation result, and judge whether the comprehensive evaluation value meets the comprehensive evaluation requirement based on a preset comprehensive evaluation threshold;

[0030] If so, the comprehensive evaluation results show that there are no non-compliant features;

[0031] Otherwise, all evaluation indicators are used as the second evaluation indicators to be tested;

[0032] A feature acquisition unit, configured to acquire a non-standard feature of the screen display based on the first evaluation indicator to be detected and the second evaluation indicator to be detected;

[0033] The feature division unit is used to divide the substandard features into correctable features and uncorrectable features based on the feature analysis model.

[0034] Preferably, the feature acquisition unit includes:

[0035] A feature determination unit, used for obtaining a picture feature corresponding to the first evaluation indicator to be detected as a picture display non-standard feature;

[0036] A weighted judgment unit, used to obtain the evaluation indicator to be detected that is different from the first evaluation indicator to be detected, and determine the weighted evaluation value of the picture feature corresponding to the evaluation indicator to be detected based on the correlation between the evaluation indicator to be detected and the first evaluation indicator to be detected, combined with the single indicator evaluation value of the first evaluation indicator to be detected, and determine whether the weighted evaluation value is greater than a preset weighted evaluation value;

[0037] If so, determining that the picture feature corresponding to the evaluation indicator to be detected is a qualified feature;

[0038] Otherwise, the picture features corresponding to the evaluation index to be detected are used as the features that do not meet the standards for picture display.

[0039] Preferably, the feature division unit comprises:

[0040] A feature analysis unit, used for inputting the non-standard feature into the feature analysis model to obtain a feature dynamic index;

[0041] The classification unit is used to classify non-standard features that are greater than a preset feature dynamic index as correctable features, and classify other non-standard features as uncorrectable features.

[0042] Preferably, the parameter optimization module includes:

[0043] A sequence determination unit, configured to obtain a time series feature sequence of the modifiable feature, and determine a correction weight sequence for the modifiable feature based on a fluctuation curve of the time series feature sequence and in combination with a feature attribute of the modifiable feature;

[0044] a structure establishing unit, for acquiring projector parameters and projection parameters related to the characteristic attributes of the modifiable feature, and establishing a parameter structure of the projector parameters and projection parameters based on the logical characteristics of the effects of the projector parameters and projection parameters on the modifiable feature, and setting an optimization target value for the parameter structure based on the correction weight sequence;

[0045] A method determination unit is used to select an initial optimization method that satisfies the parameter structure from the optimization method set, determine an optimization index of the initial optimization method for the optimization target value, and select the initial optimization method with the highest optimization index as the target optimization method;

[0046] An optimization unit, configured to optimize the parameter structure based on the target optimization method to obtain optimized projector parameters and projection parameters, and to obtain an optimized projection picture based on the optimized projector parameters and projection parameters;

[0047] A verification unit, used to verify the optimized projector parameters and projection parameters based on the picture parameters of the optimized projection picture, and determine whether the optimized projection picture is optimal;

[0048] If yes, the optimized projection picture is used as the target projection picture;

[0049] Otherwise, based on the parameter difference between the optimized projection picture and the optimal parameters, the optimized projector parameters and projection parameters are optimized again to obtain the target projection picture.

[0050] Preferably, the verification unit comprises:

[0051] A numerical judgment unit, used to compare the image parameters of the optimized projection image with the optimal parameters to obtain a difference value, and judge whether the difference value is greater than a preset difference value;

[0052] If so, it is determined that the optimized projection image is not optimal;

[0053] Otherwise, it is determined that the projection image is optimized to achieve the best result;

[0054] The secondary optimization unit is used to determine that the optimized projection picture has not reached the optimal state, select the parameters to be secondary optimized from the optimized projector parameters and projection parameters based on the parameter attributes of the parameter difference between the optimized projection picture and the optimal parameters, determine the optimized values ​​of the secondary optimization parameters based on the difference value of the parameter difference between the optimized projection picture and the optimal parameters, optimize the secondary optimization parameters according to the optimized values ​​to obtain the target parameters, and project according to the target parameters to obtain the target projection picture.

[0055] Compared with the prior art, the present invention has achieved the following beneficial effects: by performing surface calibration on the projector based on the projection area, determining the projector parameters and projection parameters according to the calibration results, ensuring the accuracy of the projection angle and distance, and then determining the initial projection picture based on the projector parameters and projection parameters, and performing picture evaluation on the initial projection picture based on the image evaluation model to obtain a picture evaluation result, thereby realizing the evaluation of the projection picture and providing a data basis for parameter adjustment, obtaining non-standard features of the picture display based on the picture evaluation result, and dividing the non-standard features into correctable features and uncorrectable features, determining the features that can be corrected by parameter adjustment, and providing a basis for parameter adjustment, and finally, based on the correctable features and in combination with the optimization method, optimizing the projector parameters and projection parameters to obtain the target projection picture, realizing the adjustment of the brightness, color saturation and clarity of the projected image according to actual conditions, improving the projection effect, and bringing a good visual experience to the user.

[0056] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 A structural diagram of an image projection system based on a projector in an embodiment of the present invention;

[0060] Figure 2is a structural diagram of a parameter determination module described in an embodiment of the present invention;

[0061] Figure 3 4 is a structural diagram of the picture evaluation module in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0063] Embodiment 1:

[0064] The embodiment of the present invention provides an image projection system based on a projector, such as Figure 1 As shown, including:

[0065] A parameter determination module, used to perform surface calibration on the projector based on the projection area, and determine the projector parameters and projection parameters according to the calibration results;

[0066] A picture evaluation module is used to determine an initial projection picture based on projector parameters and projection parameters, and to perform picture evaluation on the initial projection picture based on an image evaluation model to obtain a picture evaluation result;

[0067] A feature analysis module, used for obtaining non-standard features of the screen display based on the screen evaluation result, and classifying the non-standard features into correctable features and non-correctable features;

[0068] The parameter optimization module is used to optimize the projector parameters and projection parameters based on the modifiable features and in combination with the optimization method to obtain the target projection picture.

[0069] In this embodiment, the projector parameters include resolution, correction parameters, lens parameters, etc., and the projection parameters include projection angle and projection distance, etc.

[0070] In this embodiment, the non-standard features that cannot be adjusted by parameters are non-correctable features, and the non-standard features that can be adjusted by parameters are correctable features.

[0071] In this embodiment, the optimization methods include an exception algorithm, a particle algorithm, and the like.

[0072] In this embodiment, the picture evaluation includes evaluation of brightness, color saturation, clarity, and the like.

[0073] In this embodiment, the image assessment model is an artificial neural network model, which is trained based on historical data.

[0074] The beneficial effects of the above design scheme are as follows: by calibrating the surface of the projector based on the projection area, determining the projector parameters and projection parameters according to the calibration results, ensuring the accuracy of the projection angle and distance, and then determining the initial projection picture based on the projector parameters and projection parameters, and performing picture evaluation on the initial projection picture based on the image evaluation model to obtain the picture evaluation result, thereby realizing the evaluation of the projection picture and providing a data basis for parameter adjustment, obtaining the substandard features of the picture display based on the picture evaluation result, and dividing the substandard features into correctable features and uncorrectable features, determining the features that can be corrected by parameter adjustment, and providing a basis for parameter adjustment, and finally, based on the correctable features, combining with the optimization method, optimizing the projector parameters and projection parameters to obtain the target projection picture, realizing the adjustment of the brightness, color saturation and clarity of the projected image according to the actual situation, improving the projection effect, and bringing a good visual experience to the user.

[0075] Embodiment 2:

[0076] Based on Example 1, the present invention provides an image projection system based on a projector, such as Figure 2 As shown, the parameter determination module includes:

[0077] A calibration unit is used to establish an X-axis-Y-axis coordinate system of the projection area. The projector performs surface calibration based on the X-axis-Y-axis coordinate system to determine the correction error and the measurement error.

[0078] A setting unit, configured to set projector parameters based on the calibration error and the measurement error;

[0079] The matching unit is used to match the projection coefficient corresponding to the projector parameters based on the instrument-projection parameter correspondence.

[0080] The beneficial effect of the above design scheme is: by calibrating the surface of the projector based on the projection area, the projector parameters and projection parameters are determined according to the calibration results, so as to ensure the accuracy of the projection angle and distance and the projection effect.

[0081] Embodiment 3:

[0082] Based on Example 1, the present invention provides an image projection system based on a projector, such as Figure 3 As shown, the picture evaluation module includes:

[0083] A projection unit, used to determine a projection image according to the projector parameters, and project the projection image using the projection parameters to obtain an initial projection image;

[0084] A marking unit, used for acquiring a screen image of the initial projection screen, and marking the screen image based on an evaluation index to obtain a marked screen image;

[0085] The evaluation unit is used to input the marked picture image into an image evaluation model to output an evaluation value, and generate a picture evaluation result based on the evaluation value.

[0086] In this embodiment, the evaluation indexes include brightness, color saturation, clarity, etc.

[0087] The beneficial effects of the above design scheme are: based on the projector parameters and projection parameters, the initial projection picture is determined, and the initial projection picture is evaluated based on the image evaluation model to obtain the picture evaluation result, thereby realizing the evaluation of the projection picture and providing a data basis for parameter adjustment.

[0088] Embodiment 4:

[0089] Based on Example 3, an embodiment of the present invention provides an image projection system based on a projector, wherein the marking unit includes:

[0090] An extraction unit, used to determine a feature extraction method for the initial projection picture based on the evaluation index, and extract the initial projection picture according to the feature extraction method to obtain extraction layer information;

[0091] The information marking unit is used to mark the corresponding extraction layer information based on the indicator attributes of the evaluation indicator to obtain a marked screen image.

[0092] In this embodiment, the extraction layer information corresponds to the feature information required by the evaluation index.

[0093] The beneficial effects of the above design scheme are: determining the feature extraction method for the initial projection picture based on the evaluation index, and extracting the initial projection picture according to the feature extraction method to obtain the extraction layer information, marking the corresponding extraction layer information based on the indicator attributes of the evaluation index to obtain the marked picture image, thereby achieving accurate marking of the picture and providing a basis for the evaluation of the picture.

[0094] Embodiment 5:

[0095] Based on Example 3, the embodiment of the present invention provides an image projection system based on a projector, wherein the evaluation unit includes:

[0096] A training unit, used to establish an indicator modal model of the evaluation indicator based on the artificial neural network model, and train the indicator modal model based on the first historical picture data of the evaluation indicator to obtain a target indicator modal model;

[0097] A model building unit is used to determine the resource allocation information of the target indicator modal model based on the proportion of the evaluation indicator in the standard comprehensive evaluation result, obtain the marking features of the evaluation indicator in the marking screen image, determine the model splicing method of the target indicator modal model based on the overlapping features between the marking features, splice all the target indicator modal models according to the resource allocation information and the model relying method, and obtain an initial image evaluation model;

[0098] A convergence training unit, used to train the initial image evaluation model based on the second historical picture data of the historical projection picture until a preset model convergence requirement is met to obtain an image evaluation model;

[0099] An evaluation unit, used for inputting the marked screen image into an image evaluation model to output an index evaluation value and a comprehensive evaluation value;

[0100] The result acquisition unit is used to match the indicator evaluation value with the evaluation indicator to obtain a single indicator evaluation result, obtain a comprehensive evaluation result based on the comprehensive evaluation value, and use the single indicator evaluation result and the comprehensive evaluation result as the picture evaluation result.

[0101] The beneficial effects of the above design scheme are: by training the indicator modal model based on the first historical picture data of the evaluation index, the target indicator modal model is obtained, the accuracy of the target indicator modal model for the evaluation index is ensured, the resource allocation information of the target indicator modal model is determined based on the proportion of the evaluation index in the standard comprehensive evaluation result, the marking feature of the evaluation index in the marked picture image is obtained, and the model splicing method of the target indicator modal model is determined based on the overlapping features between the marking features, all the target indicator modal models are spliced ​​according to the resource allocation information and the model relying method to obtain the initial image evaluation model, and the initial image evaluation model is obtained from multiple dimensions, providing a model basis for accurately obtaining the evaluation result, and finally, the marked picture image is input into the image evaluation model to output the indicator evaluation value and the comprehensive evaluation value, the indicator evaluation value is matched with the evaluation index to obtain a single indicator evaluation result, and a comprehensive evaluation result is obtained based on the comprehensive evaluation value, and the single indicator evaluation result and the comprehensive evaluation result are used as the picture evaluation result, and the picture evaluation result is obtained from the whole and the part, providing a basis for parameter adjustment.

[0102] Embodiment 6:

[0103] Based on Example 1, the embodiment of the present invention provides an image projection system based on a projector, wherein the feature analysis module includes:

[0104] A judgment unit, configured to obtain a single indicator evaluation value from the picture evaluation result, and based on a preset evaluation threshold, obtain a first to-be-detected evaluation indicator that does not meet the evaluation requirement from the single indicator evaluation value;

[0105] The judging unit is further configured to obtain a comprehensive evaluation value from the picture evaluation result, and judge whether the comprehensive evaluation value meets the comprehensive evaluation requirement based on a preset comprehensive evaluation threshold;

[0106] If so, the comprehensive evaluation results show that there are no non-compliant features;

[0107] Otherwise, all evaluation indicators are used as the second evaluation indicators to be tested;

[0108] A feature acquisition unit, configured to acquire a non-standard feature of the screen display based on the first evaluation indicator to be detected and the second evaluation indicator to be detected;

[0109] The feature division unit is used to divide the substandard features into correctable features and uncorrectable features based on the feature analysis model.

[0110] The beneficial effect of the above design scheme is: using the single indicator evaluation results and the comprehensive evaluation results as the picture evaluation results, obtaining the picture evaluation results from the overall and local aspects, and providing a basis for parameter adjustment.

[0111] Embodiment 7:

[0112] Based on Example 6, an embodiment of the present invention provides an image projection system based on a projector, wherein the feature acquisition unit includes:

[0113] A feature determination unit, used for obtaining a picture feature corresponding to the first evaluation indicator to be detected as a picture display non-standard feature;

[0114] A weighted judgment unit, used to obtain the evaluation indicator to be detected that is different from the first evaluation indicator to be detected, and determine the weighted evaluation value of the picture feature corresponding to the evaluation indicator to be detected based on the correlation between the evaluation indicator to be detected and the first evaluation indicator to be detected, combined with the single indicator evaluation value of the first evaluation indicator to be detected, and determine whether the weighted evaluation value is greater than a preset weighted evaluation value;

[0115] If so, determining that the picture feature corresponding to the evaluation indicator to be detected is a qualified feature;

[0116] Otherwise, the picture features corresponding to the evaluation index to be detected are used as the features that do not meet the standards for picture display.

[0117] The beneficial effect of the above design scheme is: using the single indicator evaluation results and the comprehensive evaluation results as the picture evaluation results, obtaining the picture evaluation results from the overall and local aspects, and providing a basis for parameter adjustment.

[0118] Embodiment 8:

[0119] Based on Example 6, an embodiment of the present invention provides an image projection system based on a projector, wherein the feature division unit includes:

[0120] A feature analysis unit, used for inputting the non-standard feature into the feature analysis model to obtain a feature dynamic index;

[0121] The classification unit is used to classify non-standard features that are greater than a preset feature dynamic index as correctable features, and classify other non-standard features as uncorrectable features.

[0122] The beneficial effect of the above design scheme is: to achieve the division of non-compliant features and provide a basis for correction and optimization.

[0123] Embodiment 9:

[0124] Based on Example 1, the embodiment of the present invention provides an image projection system based on a projector, wherein the parameter optimization module includes:

[0125] A sequence determination unit, configured to obtain a time series feature sequence of the modifiable feature, and determine a correction weight sequence for the modifiable feature based on a fluctuation curve of the time series feature sequence and in combination with a feature attribute of the modifiable feature;

[0126] a structure establishing unit, for acquiring projector parameters and projection parameters related to the characteristic attributes of the modifiable feature, and establishing a parameter structure of the projector parameters and projection parameters based on the logical characteristics of the effects of the projector parameters and projection parameters on the modifiable feature, and setting an optimization target value for the parameter structure based on the correction weight sequence;

[0127] A method determination unit is used to select an initial optimization method that satisfies the parameter structure from the optimization method set, determine an optimization index of the initial optimization method for the optimization target value, and select the initial optimization method with the highest optimization index as the target optimization method;

[0128] An optimization unit, configured to optimize the parameter structure based on the target optimization method to obtain optimized projector parameters and projection parameters, and to obtain an optimized projection picture based on the optimized projector parameters and projection parameters;

[0129] A verification unit, used to verify the optimized projector parameters and projection parameters based on the picture parameters of the optimized projection picture, and determine whether the optimized projection picture is optimal;

[0130] If yes, the optimized projection picture is used as the target projection picture;

[0131] Otherwise, based on the parameter difference between the optimized projection picture and the optimal parameters, the optimized projector parameters and projection parameters are optimized again to obtain the target projection picture.

[0132] In this embodiment, the action logic feature is, for example, parallel action, or pair action, or sequential action, etc.

[0133] In this embodiment, the parameter structure represents a parameter structure inside the projector.

[0134] The beneficial effect of the above-mentioned design scheme is: by obtaining the time series feature sequence of the modifiable feature, and based on the fluctuation curve of the time series feature sequence, combined with the feature attributes of the modifiable feature, a correction weight sequence for the modifiable feature is determined, and the projector parameters and projection parameters related to the feature attributes of the modifiable feature are obtained, and based on the logical characteristics of the effects of the projector parameters and projection parameters on the modifiable feature, a parameter structure of the projector parameters and projection parameters is established, and based on the correction weight sequence, the optimization target value of the parameter structure is set, and the optimization target is determined to provide a basis for subsequent optimization, and then a suitable target optimization method is selected to ensure the optimization effect, and finally optimization verification and secondary optimization are performed to ensure the optimization effect, so as to adjust the brightness, color saturation and clarity of the projected image according to the actual situation, improve the projection effect, and bring a good visual experience to the user.

[0135] Embodiment 10:

[0136] Based on Example 9, the embodiment of the present invention provides an image projection system based on a projector, wherein the verification unit includes:

[0137] A numerical judgment unit, used to compare the image parameters of the optimized projection image with the optimal parameters to obtain a difference value, and judge whether the difference value is greater than a preset difference value;

[0138] If so, it is determined that the optimized projection image is not optimal;

[0139] Otherwise, it is determined that the projection image is optimized to achieve the best result;

[0140] The secondary optimization unit is used to determine that the optimized projection picture has not reached the optimal state, select the parameters to be secondary optimized from the optimized projector parameters and projection parameters based on the parameter attributes of the parameter difference between the optimized projection picture and the optimal parameters, determine the optimized values ​​of the secondary optimization parameters based on the difference value of the parameter difference between the optimized projection picture and the optimal parameters, optimize the secondary optimization parameters according to the optimized values ​​to obtain the target parameters, and project according to the target parameters to obtain the target projection picture.

[0141] The beneficial effects of the above design scheme are: optimization verification and secondary optimization are carried out to ensure the optimization effect, and the brightness, color saturation and clarity of the projected image can be adjusted according to actual conditions, thereby improving the projection effect and bringing a good visual experience to users.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of this application document and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. An image projection system based on a projector, characterized in that: include: A parameter determination module, used to perform surface calibration on the projector based on the projection area, and determine the projector parameters and projection parameters according to the calibration results; A picture evaluation module is used to determine an initial projection picture based on projector parameters and projection parameters, and to perform picture evaluation on the initial projection picture based on an image evaluation model to obtain a picture evaluation result; A feature analysis module, used for obtaining non-standard features of the screen display based on the screen evaluation result, and classifying the non-standard features into correctable features and non-correctable features; A parameter optimization module is used to optimize the projector parameters and projection parameters based on the modifiable features and in combination with the optimization method to obtain the target projection image; The picture evaluation module comprises: A projection unit, used to determine a projection image according to the projector parameters, and project the projection image using the projection parameters to obtain an initial projection image; A marking unit, used for acquiring a screen image of the initial projection screen, and marking the screen image based on an evaluation index to obtain a marked screen image; An evaluation unit, configured to input the marked screen image into an image evaluation model to output an evaluation value, and generate a screen evaluation result based on the evaluation value; The marking unit comprises: An extraction unit, used to determine a feature extraction method for the initial projection picture based on the evaluation index, and extract the initial projection picture according to the feature extraction method to obtain extraction layer information; An information marking unit, used for marking the corresponding extraction layer information based on the indicator attribute of the evaluation indicator to obtain a marked screen image; The evaluation unit comprises: A training unit, used to establish an indicator modal model of the evaluation indicator based on the artificial neural network model, and train the indicator modal model based on the first historical picture data of the evaluation indicator to obtain a target indicator modal model; A model building unit is used to determine the resource allocation information of the target indicator modal model based on the proportion of the evaluation indicator in the standard comprehensive evaluation result, obtain the marking features of the evaluation indicator in the marking screen image, determine the model splicing method of the target indicator modal model based on the coincidence features between the marking features, splice all the target indicator modal models according to the resource allocation information and the model relying method, and obtain an initial image evaluation model; A convergence training unit, used to train the initial image evaluation model based on the second historical picture data of the historical projection picture until a preset model convergence requirement is met to obtain an image evaluation model; An evaluation unit, used for inputting the marked screen image into an image evaluation model to output an index evaluation value and a comprehensive evaluation value; A result acquisition unit, used to match the index evaluation value with the evaluation index to obtain a single index evaluation result, obtain a comprehensive evaluation result based on the comprehensive evaluation value, and use the single index evaluation result and the comprehensive evaluation result as the picture evaluation result; The parameter optimization module comprises: A sequence determination unit, configured to obtain a time series feature sequence of the modifiable feature, and determine a correction weight sequence for the modifiable feature based on a fluctuation curve of the time series feature sequence and in combination with a feature attribute of the modifiable feature; a structure establishing unit, for acquiring projector parameters and projection parameters related to the characteristic attributes of the modifiable feature, and establishing a parameter structure of the projector parameters and projection parameters based on the logical characteristics of the effects of the projector parameters and projection parameters on the modifiable feature, and setting an optimization target value for the parameter structure based on the correction weight sequence; A method determination unit is used to select an initial optimization method that satisfies the parameter structure from the optimization method set, determine an optimization index of the initial optimization method for the optimization target value, and select the initial optimization method with the highest optimization index as the target optimization method; An optimization unit, configured to optimize the parameter structure based on the target optimization method to obtain optimized projector parameters and projection parameters, and to obtain an optimized projection picture based on the optimized projector parameters and projection parameters; A verification unit, used to verify the optimized projector parameters and projection parameters based on the picture parameters of the optimized projection picture, and determine whether the optimized projection picture is optimal; If yes, the optimized projection picture is used as the target projection picture; Otherwise, based on the parameter difference between the optimized projection picture and the optimal parameters, the optimized projector parameters and projection parameters are optimized again to obtain the target projection picture; The verification unit comprises: A numerical judgment unit, used to compare the image parameters of the optimized projection image with the optimal parameters to obtain a difference value, and judge whether the difference value is greater than a preset difference value; If so, it is determined that the optimized projection image is not optimal; Otherwise, it is determined that the optimized projection image is optimal; The secondary optimization unit is used to determine that the optimized projection picture has not reached the optimal state, select the parameters to be secondary optimized from the optimized projector parameters and projection parameters based on the parameter attributes of the parameter difference between the optimized projection picture and the optimal parameters, determine the optimized values ​​of the secondary optimized parameters based on the difference value of the parameter difference between the optimized projection picture and the optimal parameters, optimize the secondary optimized parameters according to the optimized values ​​to obtain the target parameters, and project according to the target parameters to obtain the target projection picture.

2. The image projection system based on a projector according to claim 1, characterized in that: The feature analysis module comprises: A judgment unit, configured to obtain a single indicator evaluation value from the picture evaluation result, and based on a preset evaluation threshold, obtain a first to-be-detected evaluation indicator that does not meet the evaluation requirement from the single indicator evaluation value; The judging unit is further configured to obtain a comprehensive evaluation value from the picture evaluation result, and judge whether the comprehensive evaluation value meets the comprehensive evaluation requirement based on a preset comprehensive evaluation threshold; If so, the comprehensive evaluation results show that there are no non-compliant features; Otherwise, all evaluation indicators are used as the second evaluation indicators to be tested; A feature acquisition unit, configured to acquire a non-standard feature of the screen display based on the first evaluation indicator to be detected and the second evaluation indicator to be detected; The feature division unit is used to divide the substandard features into correctable features and uncorrectable features based on the feature analysis model.

3. The image projection system based on a projector according to claim 2, characterized in that: The feature division unit comprises: A feature analysis unit, used for inputting the non-standard feature into the feature analysis model to obtain a feature dynamic index; The classification unit is used to classify non-standard features that are greater than a preset feature dynamic index as correctable features, and classify other non-standard features as uncorrectable features.

Images