Camera shooting parameter adjustment method, device and electronic equipment

Abstract

The present application provides a camera shooting parameter adjustment method, device and electronic device, which relate to the field of communication technology. The method includes: obtaining image feature information of a captured image, performing significant target detection on the captured image based on the image feature information, and obtaining a significant target detection result; and adjusting the camera shooting parameters based on the image feature information and the significant target detection result.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a camera shooting parameter adjustment method, device and electronic device. Background Art

[0002] With the popularization of electronic devices, their functions are becoming more and more sophisticated. Electronic devices are now integrated with cameras to meet people's daily photography needs. Currently, when using electronic devices for photography, photographers rely on their own shooting experience to adjust camera shooting parameters. To obtain good shooting results, photographers need to repeatedly adjust camera shooting parameters, resulting in low efficiency in camera shooting parameter adjustment. Summary of the Invention

[0003] The embodiments of the present application provide a camera shooting parameter adjustment method, device and electronic device, which can solve the problem in the prior art that the photographer needs to repeatedly adjust the camera shooting parameters and the efficiency of camera shooting parameter adjustment is low.

[0004] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for adjusting camera shooting parameters, the method comprising:

[0006] Acquiring image feature information of a captured image, and performing salient object detection on the captured image based on the image feature information to obtain a salient object detection result;

[0007] Adjusting camera shooting parameters based on the image feature information and the salient object detection result.

[0008] In a second aspect, an embodiment of the present application provides a device for adjusting camera shooting parameters, the device comprising:

[0009] an acquisition module, configured to acquire image feature information of a captured image, and perform salient object detection on the captured image based on the image feature information to obtain a salient object detection result;

[0010] An adjustment module is used to adjust camera shooting parameters based on the image feature information and the salient object detection result.

[0011] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps in the camera shooting parameter adjustment method as described in the first aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the camera shooting parameter adjustment method as described in the first aspect are implemented.

[0013] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0014] In the embodiments of the present application, image feature information of a captured image is obtained, salient object detection is performed on the captured image based on the image feature information to obtain a salient object detection result, and camera shooting parameters are adjusted based on the image feature information and the salient object detection result. In this way, by combining the adjustment of camera shooting parameters with salient object detection, the camera shooting parameters can be automatically adjusted, eliminating the need for the photographer to repeatedly adjust the camera shooting parameters and improving the efficiency of camera shooting parameter adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a camera shooting parameter adjustment method provided by an embodiment of the present application;

[0016] Figure 2 This is a schematic diagram of the structure of a neural network model provided in an embodiment of the present application;

[0017] Figure 3 This is one of the structural diagrams of a camera shooting parameter adjustment device provided in an embodiment of the present application;

[0018] Figure 4 This is a second structural diagram of a camera shooting parameter adjustment device provided in an embodiment of the present application;

[0019] Figure 5 This is the third structural diagram of a camera shooting parameter adjustment device provided in an embodiment of the present application;

[0020] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0021] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0023] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0024] The following describes in detail the camera shooting parameter adjustment method provided by the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0025] See also Figure 1 , Figure 1 This is a flow chart of a camera shooting parameter adjustment method provided by an embodiment of the present application. Figure 1 As shown, the following steps are included:

[0026] Step 101: Acquire image feature information of a captured image, perform salient object detection on the captured image based on the image feature information, and obtain a salient object detection result.

[0027] Among them, the captured image can be any image captured by a camera. Feature extraction can be performed on the captured image based on the first sub-network model to obtain image feature information. For example, the captured image can be input into the first sub-network model for feature extraction to obtain image feature information. Salient object detection can be performed on the image feature information based on the second sub-network model to obtain a salient object detection result. Salient object detection (SOD) can be used to find the most salient object in an image or video, i.e., a salient target, and mark it. The salient target detection result can be used for image editing and synthesis, etc.

[0028] Step 102: Adjust camera shooting parameters based on the image feature information and the salient object detection result.

[0029] The camera shooting parameters may include exposure parameters, white balance parameters, aperture parameters, backlight compensation parameters, etc. For example, the camera shooting parameters may be any one or more of the exposure parameters, white balance parameters, aperture parameters, and backlight compensation parameters.

[0030] In addition, target shooting parameters can be obtained based on the image feature information and the salient target detection result, and camera shooting parameters can be adjusted according to the target shooting parameters. The target shooting parameters can be any one or more of target exposure parameters, target white balance parameters, target aperture parameters, and target backlight compensation parameters. For example, the image feature information and the salient target detection result can be input into a third sub-network model to perform shooting parameter prediction to obtain the target shooting parameters; or, target image parameters can be obtained based on the image feature information and the salient target detection result; and camera shooting parameters can be adjusted according to the target image parameters.

[0031] It should be noted that the captured image can be predicted based on the neural network model to obtain the target image parameters; the camera shooting parameters can be adjusted according to the target image parameters; wherein the neural network model can be used to predict the image parameters based on the image feature information of the captured image and the salient target detection results corresponding to the captured image.

[0032] In one embodiment, Figure 2 As shown, the neural network model may include a first sub-network model 201 for feature extraction, a second sub-network model 202 for salient target detection, and a third sub-network model 203 for image parameter prediction. The first sub-network model 201 may be a MobilenetV3 model, which is a convolutional neural network model. The MobilenetV3 model may include a conv2d layer and multiple bneck layers, and the bneck layer may be used to extract image features. The second sub-network model 202 may be a lightweight network model CSF, which may perform cross-domain feature fusion. CSF may include a gOctConv layer, which is a generalized octave convolution (OctConv). The third sub-network model 203 may include a conv2d layer, a pooling layer, a conv2d layer, and a fully connected layer connected in sequence. The conv2d layer may implement a two-dimensional convolution operation.

[0033] It should be noted that the lightweight network model CSF can be composed of a feature extractor and a cross-stage fusion part, which can process features of multiple scales at the same time. The feature extractor is stacked with the intra-layer multi-scale blocks (ILBlocks) and is divided into 4 stages according to the resolution of the feature map, with 3, 4, 6, and 4 ILBlocks in each stage respectively. The cross-stage fusion part composed of gOctConv processes the features from each stage of the feature extractor to obtain high-resolution output. gOctConv is used to introduce multi-scale in ILBlock. gOctConv eliminates cross-scale operations so that each input channel corresponds to an output channel with the same resolution.

[0034] In one embodiment, the MobilenetV3 model can be used as the backbone of a neural network model to extract deep and shallow image features of the captured image. The last four layers of features in the neural network model's backbone can be used to perform cross-domain feature fusion using CSF to perform salient object detection on the captured image, thereby obtaining salient object detection results. The salient object detection results are then fused with the last layer of features in the neural network model's backbone to obtain fused feature information. Image parameter prediction is performed based on the fused feature information to obtain target image parameters.

[0035] In one embodiment, taking the target image parameter as the target reflectivity as an example, when training the neural network model, pictures can be collected and the reflectivity of the pictures can be annotated as training samples for the neural network model. When collecting pictures, you can use automatic exposure in the professional mode of the camera to save pictures in DNG and JPG formats. For the same shooting scene, take images with a gray card placed, and take images with the gray card removed, that is, without the gray card placed. For example, when shooting a chair, you can take one image when there is no gray card placed on the chair, and take another image when a gray card is placed on the chair. The reflectivity of an object is calculated using the following formula: lux*r*K=brightess, where lux is the incident light illuminance, r is the object reflectivity, K is a camera-related constant, and brightness is the image brightness. For images with a gray card placed, the average brightness of the gray card portion is obtained. Given that the gray card's reflectivity is 18%, the calculation is: lux*K = brightness / 18. Since K is known, the lux value can be calculated. For images without a gray card placed, the average brightness of the object portion is obtained. Based on the lux calculated above, the object's reflectivity is calculated as: r = brightness / lux*K. This allows for image capture of the scene and annotation of its reflectivity. The captured images and annotated reflectivity can be input into a neural network model for training. The trained neural network model can then be used to predict reflectivity. This method, using the neural network model to predict reflectivity, achieves the reflectivity regression task. Deep learning techniques can be used to jointly learn the salient object detection and reflectivity regression tasks, integrating saliency detection features into the reflectivity regression task for better reflectivity prediction.

[0036] In one embodiment, taking the target image parameter as the target image brightness as an example, when training a neural network model, a picture can be collected and the first image brightness of the picture can be annotated as a training sample for the neural network model. The first image brightness is the image brightness that has a better display effect. When collecting the picture, the camera can be used to automatically expose the picture, and then the exposure can be manually adjusted to the appropriate exposure position to take another picture. The brightness of the picture after the exposure adjustment is recorded as the first image brightness. The neural network model is trained using the automatically exposed picture and the first image brightness of the picture as training samples. For example, the average brightness of a picture is 155, which is obviously overexposed. After manual exposure adjustment, the image brightness with a better effect is 100, so the first image brightness is determined to be 100. The trained neural network model can be used to predict the image brightness that has a better display effect. Optionally, the image brightness with a better display effect means that the difference between the brightness of the target object seen by the human eye and the brightness of the target object in the photo is less than or equal to a preset value.

[0037] In an embodiment of the present application, image feature information of a captured image is obtained, salient object detection is performed on the captured image based on the image feature information to obtain a salient object detection result, and camera shooting parameters are adjusted based on the image feature information and the salient object detection result. Adjusting the camera shooting parameters in conjunction with salient object detection can automatically adjust the camera shooting parameters, eliminating the need for the photographer to repeatedly adjust the camera shooting parameters and improving the efficiency of camera shooting parameter adjustment.

[0038] Optionally, adjusting camera shooting parameters based on the image feature information and the salient object detection result includes:

[0039] Acquiring target image parameters based on the image feature information and the salient target detection result;

[0040] Adjust camera shooting parameters according to the target image parameters.

[0041] The target image parameters may include target image brightness, target reflectivity, target hue, target depth of field, etc. For example, the target image parameters may be any one or more of target image brightness, target reflectivity, target hue, and target depth of field.

[0042] In one embodiment, the significant target detection result can be fused with the target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information; image parameters are predicted on the fused feature information based on the third sub-network model to obtain target image parameters.

[0043] In one embodiment, taking the target image parameter as target image brightness as an example, the camera exposure parameters can be adjusted based on the predicted target image brightness so that the overall average brightness of the image is the same as the predicted target image brightness. In this way, exposure control can be assisted by directly predicting the image brightness with better results.

[0044] In this embodiment, target image parameters are obtained based on the image feature information and the salient target detection result; camera shooting parameters are adjusted according to the target image parameters, so that image parameters can be predicted in combination with salient target detection, and the camera shooting parameters are adjusted according to the image parameters, which can improve the efficiency of camera shooting parameter adjustment.

[0045] Optionally, adjusting camera shooting parameters based on the image feature information and the salient object detection result includes:

[0046] Fusing the salient target detection result with target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information;

[0047] Adjust camera shooting parameters based on the fused feature information.

[0048] Specifically, the captured image can be subjected to feature extraction based on the first sub-network model to obtain image feature information. The image feature information can then be subjected to salient target detection based on the second sub-network model to obtain salient target detection results. The salient target detection results can then be fused with the target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information. Parameters of the fused feature information can then be predicted based on the third sub-network model to obtain target image parameters or target shooting parameters. Camera shooting parameters can then be adjusted based on the target image parameters or target shooting parameters. In this way, by integrating salient target detection results into the image parameter prediction task through deep learning technology, effective camera shooting parameters can be obtained.

[0049] In addition, the first sub-network model can adopt a convolutional neural network, and / or a fully connected neural network, and / or a recurrent neural network, etc., and this embodiment does not limit the model structure of the first sub-network model. For example, the first sub-network model can be a MobilenetV3 model. The second sub-network model can adopt a convolutional neural network, and / or a fully connected neural network, and / or a recurrent neural network, etc., and this embodiment does not limit the model structure of the second sub-network model. For example, the second sub-network model can be a CSF model. The third sub-network model can adopt a convolutional neural network, and / or a fully connected neural network, and / or a recurrent neural network, etc., and this embodiment does not limit the model structure of the third sub-network model. For example, the third sub-network model can include a convolutional layer (Conv), an average pooling layer (avgpool), and a fully connected layer connected in sequence.

[0050] In one embodiment, Figure 2As shown, the MobilenetV3 model is used as the backbone of the neural network model to extract both deep and shallow image features. Cross-domain feature fusion (CSF) is used to leverage the features of the last four layers of the backbone. CSF uses gOctConv to take features of different scales from the last convolution of each stage in the last four layers of the backbone as input and performs cross-stage convolution to output features of varying scales. To extract multi-scale features at a granular level, each scale of the feature is processed by a set of parallel convolutions with different expansion rates. The features are then sent to another gOctConv 1×1 convolution to generate higher-resolution features, followed by another standard 1×1 convolution (Conv) to output the salient object detection results (sod_result) of the saliency map. The salient object detection results are interpolated and concatenated with the target feature information. After convolution, they are input into the conv2d layer.

[0051] It should be noted that when training the neural network model, in order to reduce the workload of labeling training samples, the teacher model (teacher_model) csnet can be used to perform salient target detection on the sample image, and the detection result can be used as the salient target detection result of the sample image, so that there is no need to label the salient target detection result of the sample image.

[0052] In one embodiment, the third sub-network model may include a convolutional layer, an average pooling layer, and a fully connected layer. For example, the convolutional layer, the average pooling layer, and the fully connected layer are sequentially connected, and the fused feature information is input to the convolutional layer, and the fully connected layer outputs the target image parameters.

[0053] In this implementation, the salient object detection results are fused with target feature information to generate fused feature information, which is all or part of the image feature information. Camera capture parameters are then adjusted based on this fused feature information. In this way, integrating the salient object detection results into the image parameter prediction task can yield optimal camera capture parameters.

[0054] Optionally, fusing the salient target detection result with target feature information to obtain fused feature information includes:

[0055] Splicing the salient target detection result with the target feature information to obtain splicing information;

[0056] The splicing information and the target feature information are subjected to residual connection processing to obtain fused feature information.

[0057] The spliced ​​information may be information obtained by splicing the salient object detection result and the target feature information. The salient object detection result and the target feature information may be spliced ​​in the channel dimension to obtain the spliced ​​information. The performing of residual connection processing on the spliced ​​information and the target feature information may include splicing and fusing the spliced ​​information through a convolutional layer to obtain fused features, and then adding the fused features to the target feature information to perform residual connection processing to obtain the fused feature information.

[0058] In one embodiment, the output of the last layer of the backbone of the neural network model, that is, the output feature_out of the last layer of the feature of mobilnetv3, can be spliced ​​with the significant target detection result sod_result in the channel dimension. After splicing, feature fusion is performed through a layer of 1X1 convolution to obtain the fused feature feature_add_sod. The fused feature feature_add_sod is added to the output feature_out of the last layer, thereby realizing residual connection processing and obtaining fused feature information.

[0059] In this embodiment, the salient target detection result and the target feature information are spliced ​​to obtain spliced ​​information, and the spliced ​​information and the target feature information are residually connected to obtain fused feature information, which can better fuse multi-layer image features and salient target detection results.

[0060] Optionally, obtaining image feature information of the captured image includes:

[0061] performing feature extraction on the captured image based on the first sub-network model to obtain image feature information of the captured image;

[0062] The first sub-network model includes a plurality of network layers connected in sequence, and the image feature information includes feature information output by at least one network layer in the plurality of network layers;

[0063] The target feature information includes feature information output by part of or all of the at least one network layer.

[0064] The image feature information may include feature information output by at least two sequentially connected network layers among the multiple network layers. The at least one network layer may include the last network layer of the first sub-network model. The target feature information may include feature information output by the last network layer of the first sub-network model.

[0065] In one embodiment, the first subnetwork model may be a MobilenetV3 model. The MobilenetV3 model may include multiple bneck layers, and the image feature information may include feature information output by the last four bneck layers. The target feature information may be feature information output by the last bneck layer.

[0066] In this embodiment, the first sub-network model includes multiple network layers connected in sequence, the image feature information includes feature information output by at least one network layer among the multiple network layers; the target feature information includes feature information output by some or all network layers among the at least one network layer. In this way, by fusing multi-layer image features with salient target detection results, image parameters can be better predicted.

[0067] Optionally, the target image parameters include target reflectivity, the camera shooting parameters include exposure parameters, and adjusting the camera shooting parameters according to the target image parameters includes:

[0068] determining a brightness adjustment parameter according to a difference between the target reflectivity and a preset reflectivity;

[0069] The exposure parameter is adjusted according to the brightness adjustment parameter.

[0070] Among them, the preset reflectivity can be 18%, or can be 17%, or can be other values, which is not limited in this embodiment. The brightness adjustment parameter can be related to the difference between the target reflectivity and the preset reflectivity. For example, the brightness adjustment parameter can be the difference between the target reflectivity and the preset reflectivity, or the brightness adjustment parameter can be the product of the difference between the target reflectivity and the preset reflectivity and a first preset coefficient, and the first preset coefficient can be 0.1, or 1.1, or 2, etc., which is not limited in this embodiment. When the difference between the target reflectivity and the preset reflectivity is greater than 0, the brightness adjustment parameter indicates to increase the image brightness, and when the difference between the target reflectivity and the preset reflectivity is less than 0, the brightness adjustment parameter indicates to reduce the image brightness;.

[0071] In addition, the brightness adjustment parameter may be related to the ratio of the difference between the target reflectivity and the preset reflectivity to the preset reflectivity. For example, the brightness adjustment parameter may be the ratio of the difference between the target reflectivity and the preset reflectivity to the preset reflectivity, or the brightness adjustment parameter may be the product of the ratio of the difference between the target reflectivity and the preset reflectivity to the preset reflectivity and a second preset coefficient, and the second preset coefficient may be 0.9, or 1.1, or 1.3, etc., which is not limited in this embodiment. The brightness adjustment parameter may be used to characterize the percentage of brightness to be increased or decreased. When the brightness adjustment parameter is greater than 0, the brightness adjustment parameter is the percentage of brightness to be increased. When the brightness adjustment parameter is less than 0, the brightness adjustment parameter is the percentage of brightness to be decreased; etc., which is not limited in this embodiment.

[0072] In one embodiment, the difference between the target reflectivity and a preset reflectivity can be calculated, the ratio of the difference to the preset reflectivity can be calculated, and the proportion of the salient target in the captured image obtained through salient target detection can be calculated. The brightness adjustment parameter can be determined based on the ratio of the difference to the preset reflectivity and the proportion of the salient target in the captured image. For example, a target product can be determined, where the target product is the ratio of the difference to the preset reflectivity multiplied by the proportion of the salient target in the captured image; wherein the brightness adjustment parameter can be related to the target product. For example, the brightness adjustment parameter can be the target product; or it can be the product of the target product and a third preset coefficient; and so on. The third preset coefficient can be 0.9, or 1.1, or 1.3, and so on, which is not limited in this embodiment.

[0073] For example, assuming the target reflectivity is 30%, the target reflectivity is compared with 18%. If 30 is higher than 18, the image brightness is increased. The brightness adjustment parameter can be: (30-18) / 18=12 / 18=66%, which means the image brightness can be increased by 66%. In actual applications, the image adjustment parameter can be adjusted according to actual use results, and this embodiment does not limit this.

[0074] Furthermore, after determining the brightness adjustment parameter, the exposure parameter can be adjusted based on the brightness adjustment parameter so that the image brightness satisfies the brightness adjustment parameter. For example, if the image brightness of a captured image is a, and the brightness adjustment parameter indicates increasing the image brightness by 66%, the exposure parameter can be adjusted to increase the image brightness by 66%. Adjusting the exposure parameter can include adjusting the ISO sensitivity (ISO) and / or shutter speed, etc.

[0075] It's important to note that with the rapid advancement of mobile phone camera performance and rising aesthetic standards for captured images, people increasingly desire images that closely resemble what the human eye sees, i.e., achieve a high degree of realism. A significant factor influencing the realism of captured images is exposure control, which primarily adjusts image brightness. In the related art, people typically use automatic exposure settings when taking photos, meaning the camera automatically controls exposure. Automatic camera exposure control involves two main steps: metering and exposure adjustment. Metering measures the intensity of light reflected from an object, and then adjusts exposure based on the resulting image brightness to ensure the image brightness approximates the actual object's brightness. An object's reflectivity measures its ability to reflect light and is related to its properties, such as its material and surface roughness. When adjusting exposure, the related art uses the "18% gray" principle, which assumes an average reflectivity of 18% across the entire image. This is because 18% gray represents the majority of what the human eye sees. Using this as a guideline for exposure, cameras typically achieve generally accurate exposure results. However, due to the "18% gray" assumption, when shooting scenes with high reflectivity, such as snowy scenes or white desks, the image may be underexposed, resulting in an overall grayish tint. Conversely, when shooting scenes with low reflectivity, such as black desks or black cars, the image may be overexposed, resulting in an overall brighter image. This embodiment predicts the scene's reflectivity to determine whether the scene is bright or dark, thereby assisting with exposure control adjustments and improving image quality.

[0076] In this embodiment, a brightness adjustment parameter is determined based on the difference between the target reflectivity and the preset reflectivity, and the exposure parameter is adjusted based on the brightness adjustment parameter. In this way, the reflectivity can be predicted in combination with the saliency detection result, and the exposure parameter can be adjusted based on the predicted reflectivity. The exposure parameter of the camera can be automatically adjusted, thereby eliminating the need for the photographer to repeatedly adjust the exposure parameter of the camera. This can improve the efficiency of the camera exposure parameter adjustment and the exposure control effect of the camera.

[0077] It should be noted that the camera shooting parameter adjustment method provided in the embodiments of the present application can be executed by a camera shooting parameter adjustment device, or a control module in the camera shooting parameter adjustment device that is used to execute the method for loading the camera shooting parameter adjustment method. In the embodiments of the present application, the camera shooting parameter adjustment device provided in the embodiments of the present application is described by taking the camera shooting parameter adjustment device executing the method for loading the camera shooting parameter adjustment method as an example.

[0078] See also Figure 3 , Figure 3 is a structural diagram of a camera shooting parameter adjustment device provided in an embodiment of the present application, such as Figure 3As shown, the device 300 includes:

[0079] An acquisition module 301 is configured to acquire image feature information of a captured image, and perform salient object detection on the captured image based on the image feature information to obtain a salient object detection result.

[0080] The adjustment module 302 is configured to adjust camera shooting parameters based on the image feature information and the salient object detection result.

[0081] Optional, such as Figure 4 As shown, the adjustment module 302 includes:

[0082] An acquiring unit 3021 is configured to acquire target image parameters based on the image feature information and the salient object detection result;

[0083] The first adjusting unit 3022 is configured to adjust camera shooting parameters according to the target image parameters.

[0084] Optional, such as Figure 5 As shown, the adjustment module 302 includes:

[0085] a fusion unit 3023 configured to fuse the salient object detection result with the target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information;

[0086] The second adjusting unit 3024 is configured to adjust camera shooting parameters based on the fused feature information.

[0087] Optionally, the fusion unit 3023 is specifically configured to:

[0088] Splicing the salient target detection result with the target feature information to obtain splicing information;

[0089] The splicing information and the target feature information are subjected to residual connection processing to obtain fused feature information.

[0090] Optionally, the acquisition module 301 is specifically configured to:

[0091] performing feature extraction on the captured image based on the first sub-network model to obtain image feature information of the captured image;

[0092] performing salient object detection on the captured image based on the image feature information to obtain a salient object detection result;

[0093] The first sub-network model includes a plurality of network layers connected in sequence, and the image feature information includes feature information output by at least one network layer in the plurality of network layers;

[0094] The target feature information includes feature information output by part of or all of the at least one network layer.

[0095] Optionally, the target image parameter includes target reflectivity, the camera shooting parameter includes exposure parameter, and the first adjustment unit 3022 is specifically configured to:

[0096] determining a brightness adjustment parameter according to a difference between the target reflectivity and a preset reflectivity;

[0097] The exposure parameter is adjusted according to the brightness adjustment parameter.

[0098] In an embodiment of the present application, an acquisition module is configured to acquire image feature information of a captured image and perform salient object detection on the captured image based on the image feature information to obtain a salient object detection result. An adjustment module is configured to adjust camera shooting parameters based on the image feature information and the salient object detection result. In this manner, by combining salient object detection with the adjustment of camera shooting parameters, the camera shooting parameters can be automatically adjusted, eliminating the need for the photographer to repeatedly adjust the camera shooting parameters and improving the efficiency of camera shooting parameter adjustment.

[0099] The camera shooting parameter adjustment device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc., and the embodiment of the present application does not specifically limit it.

[0100] The camera shooting parameter adjustment device in the embodiment of the present application can be a device having an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0101] The camera shooting parameter adjustment device provided in the embodiment of the present application can achieve Figure 1To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0102] Optional, such as Figure 6 As shown, an embodiment of the present application also provides an electronic device 400, including a processor 401, a memory 402, and a program or instruction stored in the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, each process of the above-mentioned camera shooting parameter adjustment method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0103] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0104] Figure 7 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present application.

[0105] The electronic device 500 includes but is not limited to components such as a radio frequency unit 501 , a network module 502 , an audio output unit 503 , an input unit 504 , a sensor 505 , a display unit 506 , a user input unit 507 , an interface unit 508 , a memory 509 , and a processor 510 .

[0106] Those skilled in the art will understand that the electronic device 500 may also include a power source (such as a battery) to power each component, and the power source may be logically connected to the processor 510 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be repeated here.

[0107] The processor 510 is configured to: obtain image feature information of a captured image, perform salient object detection on the captured image based on the image feature information, and obtain a salient object detection result;

[0108] The processor 510 is further configured to adjust camera shooting parameters based on the image feature information and the salient object detection result.

[0109] Optionally, the processor 510 is configured to adjust camera shooting parameters based on the image feature information and the salient object detection result, including:

[0110] Acquiring target image parameters based on the image feature information and the salient target detection result;

[0111] Adjust camera shooting parameters according to the target image parameters.

[0112] Optionally, the processor 510 is configured to adjust camera shooting parameters based on the image feature information and the salient object detection result, including:

[0113] Fusing the salient target detection result with target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information;

[0114] Adjust camera shooting parameters based on the fused feature information.

[0115] Optionally, the processor 510 is configured to perform the fusion processing of the salient object detection result with the target feature information to obtain fused feature information, including:

[0116] Splicing the salient target detection result with the target feature information to obtain splicing information;

[0117] The splicing information and the target feature information are subjected to residual connection processing to obtain fused feature information.

[0118] Optionally, the processor 510 is configured to execute the step of obtaining image feature information of the captured image, including:

[0119] performing feature extraction on the captured image based on the first sub-network model to obtain image feature information of the captured image;

[0120] The first sub-network model includes a plurality of network layers connected in sequence, and the image feature information includes feature information output by at least one network layer in the plurality of network layers;

[0121] The target feature information includes feature information output by part of or all of the at least one network layer.

[0122] Optionally, the target image parameter includes a target reflectivity, and the camera shooting parameter includes an exposure parameter. The processor 510 is configured to adjust the camera shooting parameter according to the target image parameter, including:

[0123] determining a brightness adjustment parameter according to a difference between the target reflectivity and a preset reflectivity;

[0124] The exposure parameter is adjusted according to the brightness adjustment parameter.

[0125] In an embodiment of the present application, processor 510 is configured to: obtain image feature information of a captured image; perform salient object detection on the captured image based on the image feature information to obtain a salient object detection result; and further configured to: adjust camera shooting parameters based on the image feature information and the salient object detection result. In this way, by combining salient object detection with the adjustment of camera shooting parameters, the camera shooting parameters can be automatically adjusted, eliminating the need for the photographer to repeatedly adjust the camera shooting parameters and improving the efficiency of camera shooting parameter adjustment.

[0126] It should be understood that in the embodiment of the present application, the input unit 504 may include a graphics processing unit (GPU) 5041 and a microphone 5042. The graphics processor 5041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 506 may include a display panel 5061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 507 includes a touch panel 5071 and other input devices 5072. The touch panel 5071 is also called a touch screen. The touch panel 5071 may include two parts: a touch detection device and a touch controller. Other input devices 5072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, power keys, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here. The memory 509 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 510 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and applications, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 510.

[0127] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned camera shooting parameter adjustment method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0128] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0129] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned camera shooting parameter adjustment method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0130] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0131] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0132] 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 the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, 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, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0133] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A camera shooting parameter adjustment method, characterized in that: The method comprises: Acquiring image feature information of a captured image, and performing salient object detection on the captured image based on the image feature information to obtain a salient object detection result; Adjusting camera shooting parameters based on the image feature information and the salient object detection result; The adjusting camera shooting parameters based on the image feature information and the salient object detection result includes: Fusing the salient target detection result with target feature information to obtain fused feature information, where the target feature information is all or part of the image feature information; Adjusting camera shooting parameters based on the fused feature information; The fusing the salient target detection result with the target feature information to obtain fused feature information includes: Splicing the salient target detection result with the target feature information to obtain splicing information; The splicing information and the target feature information are subjected to residual connection processing to obtain fused feature information.

2. The method according to claim 1, characterized in that The adjusting camera shooting parameters based on the image feature information and the salient object detection result includes: Acquiring target image parameters based on the image feature information and the salient target detection result; Adjust camera shooting parameters according to the target image parameters.

3. The method according to claim 1, characterized in that The acquiring of image feature information of the captured image includes: performing feature extraction on the captured image based on the first sub-network model to obtain image feature information of the captured image; The first sub-network model includes a plurality of network layers connected in sequence, and the image feature information includes feature information output by at least one network layer in the plurality of network layers; The target feature information includes feature information output by part of or all of the at least one network layer.

4. The method according to claim 2, characterized in that The target image parameters include target reflectivity, the camera shooting parameters include exposure parameters, and adjusting the camera shooting parameters according to the target image parameters includes: determining a brightness adjustment parameter according to a difference between the target reflectivity and a preset reflectivity; The exposure parameter is adjusted according to the brightness adjustment parameter.

5. A camera shooting parameter adjustment device, characterized in that: The device comprises: an acquisition module, configured to acquire image feature information of a captured image, and perform salient object detection on the captured image based on the image feature information to obtain a salient object detection result; An adjustment module, configured to adjust camera shooting parameters based on the image feature information and the salient object detection result; The adjustment module includes: a fusion unit, configured to fuse the salient target detection result with target feature information to obtain fused feature information, wherein the target feature information is all or part of the image feature information; A second adjustment unit, configured to adjust camera shooting parameters based on the fusion feature information; The fusion unit is specifically used for: Splicing the salient target detection result with the target feature information to obtain splicing information; The splicing information and the target feature information are subjected to residual connection processing to obtain fused feature information.

6. The device according to claim 5, characterized in that The adjustment module includes: an acquiring unit, configured to acquire target image parameters based on the image feature information and the salient target detection result; The first adjustment unit is configured to adjust camera shooting parameters according to the target image parameters.

7. The device according to claim 5, characterized in that The acquisition module is specifically used for: performing feature extraction on the captured image based on the first sub-network model to obtain image feature information of the captured image; performing salient object detection on the captured image based on the image feature information to obtain a salient object detection result; The first sub-network model includes a plurality of network layers connected in sequence, and the image feature information includes feature information output by at least one network layer in the plurality of network layers; The target feature information includes feature information output by part of or all of the at least one network layer.

8. The device according to claim 6, characterized in that The target image parameter includes a target reflectivity, the camera shooting parameter includes an exposure parameter, and the first adjustment unit is specifically configured to: determining a brightness adjustment parameter according to a difference between the target reflectivity and a preset reflectivity; The exposure parameter is adjusted according to the brightness adjustment parameter.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the camera shooting parameter adjustment method according to any one of claims 1 to 4.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the camera shooting parameter adjustment method according to any one of claims 1 to 4 are implemented.

Images