Image acquisition method, camera, computer equipment and storage medium

Abstract

The invention relates to an image acquisition method, a camera, computer equipment and a storage medium. The method comprises the following steps: in response to a strong light scene, adjusting exposure durations of a plurality of image sensors; obtaining a plurality of spectroscopic images of a target object based on the plurality of adjusted image sensors; and based on the plurality of spectroscopic images, determining a strong light suppression image of the target object. The method can weaken strong light interference and improve the target identification success rate.

Description

Technical Field

[0001] The present application relates to the technical field of image acquisition equipment, and in particular to an image acquisition method, a camera, a computer device and a storage medium. Background Art

[0002] With the development of digital intelligent technology, camera systems have become an important part of traffic roads. For some traffic sections and driving periods, vehicles often turn on high beams to enhance road visibility during driving. However, the strong light of high beams may cause stray light and ghosting for camera systems, making it impossible to effectively capture the outline of the vehicle.

[0003] Traditional technologies often use fill lights and post-processing of images to reduce the interference of strong light. However, there is still a problem of large brightness difference between the local fill light area and the ambient area.

[0004] Therefore, the image acquisition of the current camera system still suffers from the problems of interference from strong light and difficulty in target recognition. Summary of the invention

[0005] Based on this, it is necessary to provide an image acquisition method, camera, computer equipment and storage medium that can weaken strong light interference and improve the success rate of target recognition in response to the above technical problems.

[0006] In a first aspect, the present application provides an image acquisition method, which is applied to a camera, wherein a beam splitter prism and a plurality of image sensors corresponding to the beam splitter prism are provided in the camera, and the image acquisition method comprises: In response to a bright light scene, adjusting exposure durations of the plurality of image sensors; Based on the adjusted plurality of image sensors, a plurality of spectroscopic images of the target object are obtained; Based on the multiple spectral images, a strong light suppression image of the target object is determined.

[0007] In one embodiment, in response to a bright light scene, adjusting the exposure duration of the plurality of image sensors comprises: In response to a strong light scene, obtaining a target object in the strong light scene and a minimum effective exposure time corresponding to the target object; Based on the minimum effective exposure time, the exposure time of the plurality of image sensors is adjusted.

[0008] In one embodiment, obtaining the minimum effective exposure time corresponding to the target object includes: Determining a plurality of exposure durations to be selected based on the target object; Based on the multiple exposure durations to be selected, adjusting the exposure duration of any one of the image sensors in sequence to obtain an exposure image corresponding to each exposure duration to be selected; Based on the multiple exposure images, a minimum effective exposure time of the target object is determined.

[0009] In one embodiment, adjusting the exposure durations of the plurality of image sensors based on the minimum effective exposure duration comprises: Dividing the plurality of image sensors to obtain at least one image sensor of the first category and at least one image sensor of the second category; the number of the image sensors of the first category is equal to the number of the image sensors of the second category; Based on the minimum effective exposure time and the preset exposure time, respectively determine a first exposure time range for the first type of image sensor and a second exposure time range for the second type of image sensor; Based on the first exposure time range, reducing the exposure time of each of the image sensors of the type; Based on the second exposure time range, the exposure time of each of the second type of image sensors is increased.

[0010] In one embodiment, reducing the exposure time of each of the image sensors of the type comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a first exposure time of each of the image sensors of the type is determined, where the first exposure time is less than the preset exposure time.

[0011] In one embodiment, increasing the exposure time of each of the second type image sensors comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a second exposure time of each of the second type of image sensors is determined, where the second exposure time is greater than the preset exposure time.

[0012] In one embodiment, determining the strong light suppression image of the target object based on the multiple spectroscopic images includes: The plurality of spectral images are fused to obtain a strong light suppression image of the target object.

[0013] In a second aspect, the present application provides a camera, the camera comprising an optical focusing component, at least one beam splitter prism, a plurality of image sensors corresponding to the beam splitter prism, and an image processing system, wherein: The optical focusing component is used to collect the optical signals in the target area and guide them to the beam splitter prism; The beam splitter prism is used to split the light signal so that the split light signal is transmitted to the image sensor; The image sensor is connected to the image processing system, and is used to convert the optical signal into an electrical signal based on a set exposure time, and send the electrical signal to the image processing system; The image processing system executes the image acquisition method as described above.

[0014] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method described above when executed by a processor.

[0016] The above-mentioned image acquisition method, camera, computer equipment and storage medium adjust the exposure time of multiple image sensors in response to strong light scenes; obtain multiple spectral images of the target object based on the adjusted multiple image sensors; determine the strong light suppression image of the target object based on the multiple spectral images, by dynamically adjusting the exposure time of multiple image sensors corresponding to the splitting prism respectively, and fusing the adjusted collected spectral images, which can effectively solve the quality problem of image acquisition in strong light scenes, thereby achieving the effect of weakening strong light interference and improving the success rate of target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A diagram showing an application environment of an image acquisition method in an embodiment; Figure 2 is a schematic flow chart of an image acquisition method in one embodiment; Figure 3 is a structural block diagram of a camera system in one embodiment; Figure 4 is a flow chart of an image acquisition method in another embodiment; Figure 5 is a structural block diagram of a camera in one embodiment; Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] The image acquisition method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 is connected to the image sensor 104 through a network. In response to the strong light scene, the terminal 102 adjusts the exposure time of the multiple image sensors 104; based on the adjusted multiple image sensors 104, multiple spectroscopic images of the target object are obtained; based on the multiple spectroscopic images, the strong light suppression image of the target object is determined. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0020] In one embodiment, Figure 2 As shown, an image acquisition method is provided, which is applied to a camera, wherein a beam splitter prism and a plurality of image sensors corresponding to the beam splitter prism are arranged in the camera, and the method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included: Step S100: In response to a bright light scene, adjusting the exposure durations of the plurality of image sensors.

[0021] The beam splitter is an optical element that can split incident light into multiple directions according to different wavelengths or colors. In this embodiment, a single beam splitter can be used to split the light entering the camera into two beams of relatively weak light intensity, and different image sensors can capture the corresponding light information.

[0022] The image sensor may be a device that converts an optical image into an electronic signal, and may be, for example, a CCD (Charge Coupled Device), a CMOS (Complementary Metal Oxide Semiconductor), or other image sensors. The image sensor is used to capture images of different spectra after being decomposed by a spectroscopic prism.

[0023] A bright light scene can be a situation where there is a high-brightness light source in the environment, which may cause the image captured by an ordinary camera to be overexposed, affecting the image quality and subsequent target recognition. A bright light scene can be a scene type that the image sensor turns on when it detects a high-brightness light source, and is used to start light suppression for bright light scenes.

[0024] The exposure time is the length of time that the image sensor receives light. It is understandable that a longer exposure time allows more light to enter, making the image brighter than a normal exposure time; while a shorter exposure time can reduce the risk of overexposure, making the image darker than a normal exposure time. The exposure time can be adjusted by increasing the exposure time of some image sensors and reducing the exposure time of others, so that the ambient image and the target image in the bright light can be separated.

[0025] It is understandable that when a strong light scene is detected, the system automatically adjusts the exposure time of each image sensor. With multiple image sensors, each sensor can independently adjust the exposure time to better adapt to different light intensities and ensure high-quality images even in strong light conditions.

[0026] Step S200: obtaining a plurality of spectral images of the target object based on the adjusted plurality of image sensors.

[0027] The spectroscopic image may be an image captured by each image sensor according to an adjusted exposure time after light is separated by a spectroscopic prism.

[0028] Step S300: determining a strong light suppression image of the target object based on the plurality of spectral images.

[0029] Among them, the strong light suppression image can be obtained by retaining and fusing the key features in each spectroscopic image through image fusion processing technology, removing or reducing the negative effects of strong light (such as overexposed areas), while retaining or enhancing the useful information in the image, thereby reducing the impact of strong light on image quality, making the image clearer and more detailed in the final output image. Exemplarily, the image fusion processing technology can include multi-scale fusion, contrast adjustment, color correction, etc., to generate an image that can see the outline of the target object while maintaining the overall image quality.

[0030] An image acquisition method provided in this embodiment adjusts the exposure time of multiple image sensors in response to a strong light scene; obtains multiple spectral images of a target object based on the adjusted multiple image sensors; and determines a strong light suppression image of the target object based on the multiple spectral images. This method is achieved by dynamically adjusting the exposure time of multiple image sensors corresponding to a spectral prism, and fusing the adjusted collected spectral images. This method can effectively solve the quality problem of image acquisition in strong light scenes, thereby achieving the effect of weakening strong light interference and improving the success rate of target recognition.

[0031] In one embodiment, in response to a bright light scene, adjusting the exposure duration of the plurality of image sensors comprises: In response to a strong light scene, obtaining a target object in the strong light scene and a minimum effective exposure time corresponding to the target object; Based on the minimum effective exposure time, the exposure time of the plurality of image sensors is adjusted.

[0032] The minimum effective exposure time may be the shortest exposure time required to accurately capture the details of the target or to identify the target under given lighting conditions. It is understandable that if the exposure time is too short, the image may be too dark and the target cannot be seen clearly; if the exposure time is too long, details may be lost due to overexposure.

[0033] Furthermore, acquiring the target in the strong light scene may be that after detecting the strong light scene, the system first identifies and locks the target. Further, acquiring the minimum effective exposure time corresponding to the target may be that the minimum effective exposure time of the target is calculated based on the characteristics of the target, such as color, reflectivity, etc., and the current lighting conditions. In another embodiment, the image of the target in different exposure modes can be acquired by adjusting the exposure time, and the shortest exposure time that can identify the target can be determined by the target detection algorithm.

[0034] Based on the minimum effective exposure time, the exposure time of the multiple image sensors is adjusted. After determining the minimum effective exposure time, the exposure parameters of all image sensors are adjusted according to this time, so that each image sensor can work within the optimal exposure time, so that the final strong light suppression image will neither lose the details of the target object due to underexposure nor reduce the image quality due to overexposure, which helps to obtain clearer and more accurate images in strong light scenes, thereby improving the success rate of target recognition.

[0035] An image acquisition method provided in this embodiment achieves refined management of the exposure time of the image sensor by introducing the concept of the minimum effective exposure time of the target object, which not only improves the image quality in strong light scenes, but also enhances the recognition accuracy of the target object, thereby achieving the effect of reducing strong light interference and improving the success rate of target recognition.

[0036] In one embodiment, obtaining the minimum effective exposure time corresponding to the target object includes: Determining a plurality of exposure durations to be selected based on the target object; Based on the multiple exposure durations to be selected, adjusting the exposure duration of any one of the image sensors in sequence to obtain an exposure image corresponding to each exposure duration to be selected; Based on the multiple exposure images, a minimum effective exposure time of the target object is determined.

[0037] The exposure duration to be selected may be a series of optional exposure durations selected within a certain range, for testing and determining the optimal exposure duration. Exemplarily, the optional exposure duration may be determined based on the characteristics of the target object, such as color, reflectivity, surface material, etc., and the lighting conditions at the current moment. The selection of the exposure duration to be selected may be determined based on empirical data, historical records, or real-time calculations.

[0038] The exposure image may be an image captured by an image sensor under a specific exposure time. Exemplarily, the exposure time of any one of the image sensors is adjusted in sequence, and one of the image sensors may be selected and its exposure time may be set to each selected exposure time in sequence, so that a plurality of exposure images may be obtained, each image corresponding to a different exposure time.

[0039] In another embodiment, a selected exposure time may be set for each image sensor, so that an exposure image corresponding to each selected exposure time may be obtained in a short time. Considering that the light intensity of the two light signals after being processed by the spectroscopic prism is reduced, the selected exposure time corresponding to each exposure image may be converted according to the location of the image sensor, and the actual exposure time of each exposure image under the same light intensity may be calculated, and the minimum effective exposure time of the target object may be determined according to the actual exposure time of multiple exposure images.

[0040] When determining the minimum effective exposure time of the target object, the quality of each exposure image can be quantified according to the average brightness of the image, the clarity of the edge of the target object, etc. It is understandable that the minimum effective exposure time will be used for subsequent image acquisition and processing to ensure that high-quality images are obtained in strong light scenes.

[0041] An image acquisition method provided in this embodiment determines the minimum effective exposure time of a target object from multiple exposure time options by exposing in sequence, which can improve the selection accuracy of exposure time and ensure the image quality and recognition accuracy of the target object in strong light scenes, thereby achieving the effect of reducing strong light interference and improving the success rate of target recognition.

[0042] In one embodiment, adjusting the exposure durations of the plurality of image sensors based on the minimum effective exposure duration comprises: Dividing the plurality of image sensors to obtain at least one image sensor of the first category and at least one image sensor of the second category; the number of the image sensors of the first category is equal to the number of the image sensors of the second category; Based on the minimum effective exposure time and the preset exposure time, respectively determine a first exposure time range for the first type of image sensor and a second exposure time range for the second type of image sensor; Based on the first exposure time range, reducing the exposure time of each of the image sensors of the type; Based on the second exposure time range, the exposure time of each of the second type of image sensors is increased.

[0043] Among them, the first type of image sensor is an image sensor that needs to reduce the exposure time to reduce the interference of strong light; the second type of image sensor is an image sensor that needs to increase the exposure time to increase the capture of dark details.

[0044] Exemplarily, all or part of the image sensors may be divided into two groups, with an equal number of image sensors in each group, to ensure that when adjusting the exposure time, the image instructions under different light intensities can be balanced. When some image sensors are divided into two groups, the remaining image sensors that are not grouped can be exposed and image captured as normal exposure time. The grouping of image sensors may be based on the corresponding dichroic prisms. For example, if the same dichroic prism corresponds to two image sensors, the two image sensors may be divided into one type of image sensor and the second type of image sensor, respectively. The grouping of image sensors may also be based on the location, sensitivity and other characteristics of the sensors, which is not limited in this embodiment.

[0045] Based on the minimum effective exposure time and the preset exposure time, the first exposure time range of the first category image sensor and the second exposure time range of the second category image sensor are respectively determined. The minimum effective exposure time can be used as the lowest threshold, and the first exposure time range of each first category image sensor and the second exposure time range of each second category image sensor are respectively determined according to the preset exposure time.

[0046] It can be understood that the first exposure time range of each type of image sensor can be determined according to the number of optical paths. The more optical paths there are, the weaker the light intensity received by the image sensor may be. For example, the light received by one of the image sensors may pass through three beam splitting prisms, and the light signal is separated three times. Assuming an ideal state and ignoring other losses, after the light signal is separated, the light intensity of one light signal is half of the original light signal. Then, the light intensity of the light signal after separation three times can be one eighth of the original light signal. Therefore, the exposure time range can be set according to the position of the image sensor.

[0047] The first exposure time range is the exposure time range that a type of image sensor should at least be in after the exposure time is reduced; accordingly, based on the first exposure time range, the exposure time of each of the type of image sensors is reduced, and its exposure time can be adjusted to a value within the first exposure time range, thereby reducing the exposure time to reduce the interference of strong light.

[0048] The second exposure time range is the exposure time range that the second type of image sensor should at least be in after the exposure time is increased; accordingly, based on the second exposure time range, the exposure time of each of the second type of image sensors is increased, which can be to adjust its exposure time to a value within the second exposure time range, thereby increasing the exposure time to enhance the capture of dark details.

[0049] An image acquisition method provided in this embodiment achieves more precise image control in strong light scenes by dividing multiple image sensors into two categories and adjusting their exposure times respectively. By reducing the exposure time of one type of image sensor to reduce strong light interference and increasing the exposure time of the second type of image sensor to enhance dark details, the clarity and detail of the image can be improved, and the stability and reliability of image acquisition under complex lighting conditions can be ensured, thereby achieving the effect of reducing strong light interference and improving the success rate of target recognition.

[0050] In one embodiment, reducing the exposure time of each of the image sensors of the type comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a first exposure time of each of the image sensors of the type is determined, where the first exposure time is less than the preset exposure time.

[0051] The number of optical paths is the number of optical paths formed after passing through the beam splitter prism, and each optical path may correspond to an image sensor. The preset exposure time may be a preset reference exposure time, which is used to determine the adjustment basis of the exposure time. For example, the reference exposure time may be a normal exposure time in a normal scene.

[0052] The first exposure time may be the final exposure time of a single type I image sensor, and the exposure time is less than the preset exposure time. Based on the number of light paths corresponding to the plurality of image sensors and the preset exposure time, the first exposure time of each type I image sensor is determined, and the adjustment value of the preset exposure time is determined according to the number of light paths and the preset exposure time, so as to determine the final exposure time, i.e., the first exposure time.

[0053] An image acquisition method provided in this embodiment can effectively reduce the interference of strong light on the image and avoid overexposure of the image by reducing the exposure time, ensuring that the details of the target object can still be clearly captured under strong light conditions, thereby achieving the effect of weakening strong light interference and improving the success rate of target recognition.

[0054] In one embodiment, increasing the exposure time of each of the second type image sensors comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a second exposure time of each of the second type of image sensors is determined, where the second exposure time is greater than the preset exposure time.

[0055] The number of optical paths is the number of optical paths formed after passing through the beam splitter prism, and each optical path may correspond to an image sensor. The preset exposure time may be a preset reference exposure time, which is used to determine the adjustment basis of the exposure time. For example, the reference exposure time may be a normal exposure time in a normal scene.

[0056] The second exposure time may be the final exposure time of a single type II image sensor, and the exposure time is greater than the preset exposure time. Based on the number of light paths corresponding to the plurality of image sensors and the preset exposure time, the second exposure time of each type II image sensor is determined, and the adjustment value of the preset exposure time is determined according to the number of light paths and the preset exposure time, so as to determine the final exposure time, i.e., the second exposure time.

[0057] An image acquisition method provided in this embodiment can effectively enhance the capture of dark details by increasing the exposure time, which not only improves the image quality in strong light scenes, but also ensures that the details of the target object are clearly visible, thereby achieving the effect of improving the success rate of target recognition.

[0058] In one embodiment, determining the strong light suppression image of the target object based on the multiple spectroscopic images includes: The plurality of spectral images are fused to obtain a strong light suppression image of the target object.

[0059] The spectroscopic image is an image captured by each image sensor under a specific spectrum after the incident light is split into multiple light paths by a spectroscopic prism.

[0060] To fuse the multiple spectral images, an image fusion algorithm may be selected, such as a weighted average method, a multi-resolution fusion algorithm, a fusion algorithm based on wavelet transform, a fusion algorithm based on deep learning, etc., to achieve fusion of the multiple spectral images and obtain a strong light suppression image.

[0061] Before image fusion, the spectroscopic image can also be preprocessed, such as noise filtering, contrast adjustment, etc., to improve image quality.

[0062] After obtaining the strong light suppression image, the strong light suppression image may be subjected to post-processing such as color correction and sharpening, thereby further improving the visual effect of the image and the recognition accuracy of the target object.

[0063] An image acquisition method provided in this embodiment combines multiple spectroscopic images into a high-quality strong light suppression image through image fusion technology, which can effectively eliminate strong light interference, improve the detail clarity of the target object and the overall quality of the image, thereby achieving the effect of weakening strong light interference and improving the success rate of target recognition.

[0064] In order to more clearly illustrate the technical solution of the present application, the present application also provides a detailed embodiment.

[0065] In one embodiment, an image acquisition method is provided, which is applied to a camera system, such as Figure 3 As shown, the camera system includes a camera system, a prism, an image sensor and an image processing system, wherein: The target object is the monitored object; the camera system can be an optical focusing component such as a lens, which is used to collect information related to the monitored object; the beam splitter prism is used to split the output light of the camera system to obtain two beams of light after splitting, and the light beams are received by two image sensors respectively; the image sensor is used to receive image information of the monitoring system; the image processing system fuses the image information received by multiple image sensors to achieve image information with stray light processing effect.

[0066] like Figure 4 As shown, taking the number of beam splitting prisms as 2, that is, the number of optical paths as 3 as an example, the image acquisition method includes: Step S1, adjusting the camera system according to the actual usage scenario to obtain required scene information.

[0067] Among them, the camera can be independently controlled according to the monitoring scene.

[0068] Step S2, the light signal is split by the prism and then transmitted in three paths, thereby performing light splitting modulation of the image.

[0069] Step S3, performing image exposure processing on two of the optical signals to remove the area with stray light in the scene and improve the image information quality of the area.

[0070] In step S4, the image processing system fuses the three-way image information and removes the interference information of some areas, so as to obtain complete image information of the entire area.

[0071] Among them, step S3 includes: Step S31, the image information of the first optical signal is obtained by the image sensor and corresponding image modulation is performed. The image sensor normally receives the target information, and when acquiring the information, the exposure time T1 of the corresponding target is extracted. The exposure time T1 is the exposure time of the normal image, and in the case of a high-speed scene, it is in an overexposed state.

[0072] Step S32, control the image sensors of the other two of the three paths to acquire images in other ways.

[0073] The second optical signal is received by another image sensor and the image modulation method of reducing the exposure time is used to remove the overexposed part to obtain the image effect; the third optical signal is received by another image sensor and the image modulation method of increasing the exposure time is used to increase the image effect of the target. Further, during the image modulation process, the object contour in the split image can also be recognized and the contour can be enhanced to improve the recognition effect.

[0074] Further, the method of acquiring image P2 for one path is to reduce the exposure time to T2, thereby reducing the halo intensity, and the method of acquiring image P3 for the other path is to increase the exposure time to T3, thereby increasing the brightness and clarity of the target and the environment.

[0075] Before step S32, it also includes acquiring in advance the lowest exposure time T4 required for target recognition, and then determining the exposure time T2 and the exposure time T3. The relationship among the exposure times T1 to T4 satisfies T4 < T2 < T1 < T3, where the exposure time T2 needs to satisfy the condition 0.05T1 ≤ T2 ≤ 0.15T1, and the exposure time T3 needs to satisfy the condition T1 ≤ T3 ≤ 2T1. When the exposure time T1 and the exposure time T4 are known, the values of T2 or T3 for each image sensor can be determined.

[0076] Fuse the image information after modulation of the three groups to obtain an ideal image effect.

[0077] Furthermore, when the number of optical paths is greater than 3, assuming that the number of optical paths is n, and the exposure time of image Pn is Tn, it can be the exposure time T1 of the first path of the captured image after the splitting. If n is an even number, the remaining optical paths other than the first and second beams can be evenly divided into two parts, which are used to reduce the exposure time and increase the exposure time respectively; if n is an odd number, the remaining optical paths except the first beam image acquisition can be evenly divided into two parts, one part of which has a reduced exposure time Tn of Tn=(0.05+0.1 / n) / T1, and the other part of which has an increased exposure time Tn of Tn=(1+1 / n)T1, so that the image Pn captured by each image sensor can be obtained. After the image Pn is obtained, the multiple split images are integrated to improve the imaging quality, so as to remove stray light and clearly identify objects.

[0078] The present embodiment provides an image acquisition method, which adjusts the exposure time of multiple image sensors in response to a strong light scene; obtains multiple spectroscopic images of a target object based on the adjusted multiple image sensors; and determines a strong light suppression image of the target object based on the multiple spectroscopic images. The method is to dynamically adjust the exposure time of multiple image sensors corresponding to the spectroscopic prism respectively, and fuse the spectroscopic images collected after the adjustment, which can effectively solve the quality problem of image acquisition in a strong light scene, thereby achieving the effect of weakening strong light interference and improving the target recognition success rate; by introducing the concept of the minimum effective exposure time of the target object, the refined management of the exposure time of the image sensor is realized, which not only improves the image quality in the strong light scene, but also enhances the recognition accuracy of the target object, thereby achieving the effect of weakening strong light interference and improving the target recognition success rate; by sequentially exposing, the minimum effective exposure time of the target object is determined from multiple exposure times to be selected, which can improve the selection accuracy of the exposure time, and also ensure the image quality and recognition accuracy of the target object in the strong light scene, thereby achieving the effect of weakening strong light interference and improving the target recognition success rate; By dividing multiple image sensors into two categories and adjusting their exposure times respectively, more precise image control is achieved in strong light scenes. By reducing the exposure time of one type of image sensor to reduce strong light interference and increasing the exposure time of the second type of image sensor to enhance dark details, the clarity and detail performance of the image can be improved, and the stability and reliability of image acquisition under complex lighting conditions can be ensured, so as to achieve the effect of weakening strong light interference and improving the success rate of target recognition; by reducing the exposure time, the interference of strong light on the image can be effectively reduced, the image can be avoided from being overexposed, and the details of the target object can still be clearly captured under strong light conditions, so as to achieve the effect of weakening strong light interference and improving the success rate of target recognition; by increasing the exposure time, the capture of dark details can be effectively enhanced, which not only improves the image quality in strong light scenes, but also ensures that the details of the target object are clearly visible, so as to achieve the effect of improving the success rate of target recognition; through image fusion technology, multiple spectroscopic images are merged into a high-quality strong light suppression image, which can effectively eliminate strong light interference, improve the clarity of the details of the target object and the overall quality of the image, so as to achieve the effect of weakening strong light interference and improving the success rate of target recognition.

[0079] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0080] Based on the same inventive concept, the embodiment of the present application also provides a camera for implementing the above-mentioned image acquisition method. The implementation solution provided by the camera to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more camera embodiments provided below can refer to the limitations of the image acquisition method above, and will not be repeated here.

[0081] In one embodiment, Figure 5 As shown, a camera is provided, the camera comprises an optical focusing component 100, at least one beam splitter prism 200, a plurality of image sensors 300 corresponding to the beam splitter prism 200, and an image processing system 400, wherein: The optical focusing component 100 is used to collect the optical signals in the target area and guide them to the beam splitter prism 200; The beam splitter prism 200 is used to split the optical signal so that the split optical signal is transmitted to the image sensor 300; The image sensor 300 is connected to the image processing system 400, and is used to convert the optical signal into an electrical signal based on a set exposure time, and send the electrical signal to the image processing system 400; The image processing system 400 executes the image acquisition method described in any one of the above embodiments.

[0082] Further, the image processing system 400 is used to adjust the exposure duration of the plurality of image sensors 300 in response to a bright light scene; Based on the adjusted plurality of image sensors 300, a plurality of spectral images of the target object are obtained; Based on the multiple spectral images, a strong light suppression image of the target object is determined.

[0083] In one embodiment, the image processing system 400 is further configured to: In response to a strong light scene, obtaining a target object in the strong light scene and a minimum effective exposure time corresponding to the target object; Based on the minimum effective exposure time, the exposure time of the plurality of image sensors 300 is adjusted.

[0084] In one embodiment, the image processing system 400 is further configured to: Determining a plurality of exposure durations to be selected based on the target object; Based on the multiple exposure durations to be selected, adjusting the exposure duration of any one of the image sensors 300 in sequence to obtain an exposure image corresponding to each exposure duration to be selected; Based on the multiple exposure images, a minimum effective exposure time of the target object is determined.

[0085] In one embodiment, the image processing system 400 is further configured to: Dividing the plurality of image sensors 300 to obtain at least one first-category image sensor 300 and at least one second-category image sensor 300; the number of the first-category image sensor 300 is equal to the number of the second-category image sensor 300; Based on the minimum effective exposure time and the preset exposure time, respectively determine a first exposure time range of the first type of image sensor 300 and a second exposure time range of the second type of image sensor 300; Based on the first exposure time range, reducing the exposure time of each of the image sensors 300 of the type; Based on the second exposure time range, the exposure time of each of the second type image sensors 300 is increased.

[0086] In one embodiment, the image processing system 400 is further configured to: Based on the number of optical paths corresponding to the plurality of image sensors 300 and a preset exposure time, a first exposure time of each of the type of image sensors 300 is determined, where the first exposure time is less than the preset exposure time.

[0087] In one embodiment, the image processing system 400 is further configured to: Based on the number of optical paths corresponding to the plurality of image sensors 300 and a preset exposure time, a second exposure time of each of the second type image sensors 300 is determined, and the second exposure time is greater than the preset exposure time.

[0088] In one embodiment, the image processing system 400 is further configured to: The plurality of spectral images are fused to obtain a strong light suppression image of the target object.

[0089] Each module in the above-mentioned camera can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0090] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an image acquisition method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0091] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0092] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the image acquisition method of any of the above embodiments is implemented: In response to a bright light scene, adjusting exposure durations of the plurality of image sensors; Based on the adjusted plurality of image sensors, a plurality of spectroscopic images of the target object are obtained; Based on the multiple spectral images, a strong light suppression image of the target object is determined.

[0093] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the image acquisition method of any of the above embodiments is implemented: In response to a bright light scene, adjusting exposure durations of the plurality of image sensors; Based on the adjusted plurality of image sensors, a plurality of spectroscopic images of the target object are obtained; Based on the multiple spectral images, a strong light suppression image of the target object is determined.

[0094] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image acquisition method, characterized in that: Applied to a camera, the camera is provided with a beam splitter prism and a plurality of image sensors corresponding to the beam splitter prism, and the image acquisition method comprises: In response to a bright light scene, adjusting exposure durations of the plurality of image sensors; Based on the adjusted plurality of image sensors, a plurality of spectroscopic images of the target object are obtained; Based on the multiple spectral images, a strong light suppression image of the target object is determined.

2. The image acquisition method according to claim 1, characterized in that: In response to a bright light scene, adjusting the exposure durations of the plurality of image sensors comprises: In response to a strong light scene, obtaining a target object in the strong light scene and a minimum effective exposure time corresponding to the target object; Based on the minimum effective exposure time, the exposure time of the plurality of image sensors is adjusted.

3. The image acquisition method according to claim 2, characterized in that: Obtaining the minimum effective exposure time corresponding to the target object includes: Determining a plurality of exposure durations to be selected based on the target object; Based on the multiple exposure durations to be selected, adjusting the exposure duration of any one of the image sensors in sequence to obtain an exposure image corresponding to each exposure duration to be selected; Based on the multiple exposure images, a minimum effective exposure time of the target object is determined.

4. The image acquisition method according to claim 2, characterized in that: The adjusting the exposure durations of the plurality of image sensors based on the minimum effective exposure duration comprises: Dividing the plurality of image sensors to obtain at least one image sensor of the first category and at least one image sensor of the second category; the number of the image sensors of the first category is equal to the number of the image sensors of the second category; Based on the minimum effective exposure time and the preset exposure time, respectively determine a first exposure time range for the first type of image sensor and a second exposure time range for the second type of image sensor; Based on the first exposure time range, reducing the exposure time of each of the image sensors of the type; Based on the second exposure time range, the exposure time of each of the second type of image sensors is increased.

5. The image acquisition method according to claim 4, characterized in that: The reducing the exposure time of each of the image sensors of the type comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a first exposure time of each of the image sensors of the type is determined, where the first exposure time is less than the preset exposure time.

6. The image acquisition method according to claim 4, characterized in that: The increasing the exposure time of each of the second type image sensors comprises: Based on the number of optical paths corresponding to the plurality of image sensors and a preset exposure time, a second exposure time of each of the second type of image sensors is determined, where the second exposure time is greater than the preset exposure time.

7. The image acquisition method according to claim 1, characterized in that: The determining the strong light suppression image of the target object based on the plurality of spectral images comprises: The plurality of spectral images are fused to obtain a strong light suppression image of the target object.

8. A camera, characterized in that: The camera comprises an optical focusing component, at least one beam splitter prism, a plurality of image sensors corresponding to the beam splitter prism, and an image processing system, wherein: The optical focusing component is used to collect the optical signals in the target area and guide them to the beam splitter prism; The beam splitter prism is used to split the light signal so that the split light signal is transmitted to the image sensor; The image sensor is connected to the image processing system, and is used to convert the optical signal into an electrical signal based on a set exposure time, and send the electrical signal to the image processing system; The image processing system is the image acquisition method according to any one of claims 1 to 7.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images