WO2022160638A1 - 目标对象曝光方法、装置、存储介质、设备及程序 - Google Patents

目标对象曝光方法、装置、存储介质、设备及程序 Download PDF

Info

Publication number
WO2022160638A1
WO2022160638A1 PCT/CN2021/110240 CN2021110240W WO2022160638A1 WO 2022160638 A1 WO2022160638 A1 WO 2022160638A1 CN 2021110240 W CN2021110240 W CN 2021110240W WO 2022160638 A1 WO2022160638 A1 WO 2022160638A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
target object
brightness
recognized
area
Prior art date
Application number
PCT/CN2021/110240
Other languages
English (en)
French (fr)
Inventor
吴强
彭恩厚
李佳
张振宇
Original Assignee
深圳市商汤科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Publication of WO2022160638A1 publication Critical patent/WO2022160638A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/141—Control of illumination
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10141—Special mode during image acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the present disclosure relates to the field of computer technology, and in particular, to a target object exposure method, device, storage medium, device, and program.
  • target recognition technology In the field of image recognition and artificial intelligence, target recognition technology has been applied in all walks of life. For example, in the current field of identity information recognition, face recognition technology occupies a very important position.
  • the target recognition module cannot detect the target that should be detected, resulting in the inability to perform target-based automatic exposure in some scenes, making subsequent applications based on the exposed target unable to proceed.
  • Embodiments of the present disclosure provide a target object exposure method, apparatus, storage medium, device, and program.
  • An embodiment of the present disclosure provides a method for exposing a target object, the method is executed by an electronic device, and the method includes: acquiring an image to be exposed; performing brightness recognition on the image to be exposed, and determining an abnormal brightness area on the image to be exposed performing brightness adjustment on the abnormal brightness area to obtain an image to be identified; in response to identifying a target object in the image to be identified, performing exposure processing on the target object to obtain an exposure image.
  • an image originally obtained in a relatively extreme environment can be improved by adjusting the brightness, avoiding abnormal exposure of the target object in the image in an extreme light environment, and laying a good foundation for the subsequent image application after exposure.
  • performing exposure processing on the target object to obtain an exposed image includes: performing preset object recognition on the to-be-recognized image, where The preset object includes a target object; in the case of identifying the preset object, determine the to-be-identified area where the preset object is located; perform target object recognition on the to-be-identified area; In the case of a target object, exposure processing is performed on the target object to obtain an exposed image. In this way, the target object can be identified in the to-be-recognized image, so that exposure processing can be performed on the target object to obtain an exposure image.
  • the method further includes:
  • the brightness adjustment corresponding to multiple brightnesses is performed on the image to be identified to obtain multiple adjusted images to be identified;
  • Target object recognition is performed in the to-be-recognized area; when the target object is recognized, exposure processing is performed on the target object on the adjusted to-be-recognized image where the target object exists to obtain the exposure image.
  • the preset object can be recognized in the to-be-recognized image, but when the target object is not recognized in the to-be-recognized area where the preset object is located, the target object can be recognized by adjusting the brightness of the to-be-recognized area.
  • the target object is subjected to exposure processing to obtain an exposure image.
  • the method further includes: if the target object is not recognized, determining the brightness of the to-be-recognized image; when the brightness is greater than the first brightness In the case of , the image to be recognized is dimmed according to the first brightness interval value to obtain a dimmed image to be recognized; target object recognition is performed on the to-be-recognized area on the dimmed image to be recognized; In the case of the target object, the dimmed image to be recognized is dimmed according to the first brightness interval value to obtain the current dimmed image to be recognized; In the to-be-recognized area, perform the target object recognition until the target object is recognized; perform exposure processing on the target object on the darkened to-be-recognized image to obtain the exposed image.
  • the first brightness interval value can be used to dim the image to be identified, so that the target in the area to be identified can be identified object, and then expose the target object to obtain the exposure object.
  • the method further includes:
  • the brightness of the image to be recognized is determined; in the case that the brightness is less than the second brightness, the image to be recognized is brightened according to the second brightness interval value to obtain the brightness of the image to be recognized.
  • the second brightness interval value can be used to brighten the image to be identified, so that the target in the area to be identified can be identified object, and then expose the target object to obtain the exposure object.
  • performing exposure processing on the target object to obtain an exposed image includes: performing the preset object recognition on the to-be-recognized image ; Under the condition that the preset object is not identified, the brightness adjustment corresponding to multiple brightnesses is performed on the image to be identified to obtain multiple adjusted images to be identified; the multiple adjusted images to be identified are adjusted Performing the target object recognition; in the case of recognizing the target object, performing exposure processing on the target object to obtain the exposure image.
  • the preset object is not recognized in the to-be-recognized image
  • the corresponding brightness can be adjusted to identify the target object in the brightness-adjusted image, so that the target object can be exposed to obtain the exposed object.
  • the target object includes a human face;
  • the preset object includes a human shape;
  • performing preset object recognition on the to-be-recognized image includes: performing a human-shaped image on the to-be-recognized image through a humanoid recognition network identify;
  • Performing target object recognition on the to-be-recognized area includes: performing face recognition on the to-be-recognized area through the face recognition network.
  • the humanoid recognition network can be used to perform the recognition of the preset object and the recognition of the target object.
  • the abnormal brightness area includes a first abnormal brightness area
  • Adjusting the brightness of the abnormal brightness area to obtain an image to be recognized includes: adjusting the brightness of the first abnormal brightness area based on a first brightness adjustment parameter to obtain the image to be recognized; wherein, in the image to be recognized The brightness of the first abnormal brightness area is lower than the brightness of the first abnormal brightness area on the to-be-exposed image. In this way, the brightness of the first abnormal brightness area in the to-be-exposed image can be adjusted, so that the brightness of the to-be-identified image obtained after the adjustment of the first abnormal brightness area tends to be normal.
  • the abnormal brightness area includes a second abnormal brightness area
  • Adjusting the brightness of the abnormal brightness area to obtain an image to be recognized includes: adjusting the brightness of the second abnormal brightness area based on a second brightness adjustment parameter to obtain the image to be recognized; wherein, the image to be recognized is in the image to be recognized.
  • the brightness of the second abnormal brightness area is higher than the brightness of the second abnormal brightness area on the to-be-exposed image. In this way, the brightness of the second abnormal brightness region in the to-be-exposed image can be adjusted, so that the brightness of the to-be-identified image obtained after the adjustment of the second abnormal brightness region tends to be normal.
  • the method further includes: performing brightness identification on the image to be exposed, and determining a non-abnormal brightness area on the image to be exposed; in response to The target object is determined in the non-abnormal brightness area, and exposure processing is performed on the target object to obtain the exposure image.
  • the target object can be identified in the non-abnormal brightness area in the image to be exposed, and the identified target object can be exposed to obtain an exposed image.
  • the present disclosure provides a target object exposure device, comprising:
  • An image acquisition module configured to acquire an image to be exposed; an area determination module, configured to perform brightness identification on the to-be-exposed image, and determine an abnormal brightness area on the to-be-exposed image; The brightness is adjusted to obtain an image to be recognized; the image exposure module is configured to, in response to identifying a target object in the image to be recognized, perform exposure processing on the target object to obtain an exposed image.
  • the image exposure module includes an identification sub-module, an identification area determination sub-module, and a processing sub-module;
  • a recognition sub-module configured to perform preset object recognition on the to-be-recognized image, where the preset object includes a target object; and a recognition area determination sub-module, configured to determine the preset object when the preset object is identified Preset the to-be-recognized area where the object is located; the identification sub-module is configured to perform target object recognition on the to-be-recognized area; the processing sub-module is configured to identify the target object when the target object is identified Exposure processing is performed to obtain the exposure image.
  • the image exposure module further includes:
  • an adjustment sub-module configured to perform a plurality of brightness adjustments corresponding to the brightness of the to-be-identified image under the condition that the target object is not identified, to obtain a plurality of adjusted to-be-identified images
  • the identification sub-module configured In order to perform target object recognition on the to-be-recognized areas on the plurality of adjusted to-be-recognized images
  • the processing submodule is configured to, when The target object on the to-be-recognized image is subjected to exposure processing to obtain the exposure image.
  • the image exposure module further includes:
  • a brightness determination sub-module configured to determine the brightness of the to-be-identified image when the target object is not identified; a brightness adjustment sub-module configured to determine the brightness of the image to be identified according to the first brightness
  • the brightness interval value dims the to-be-recognized image to obtain the dimmed to-be-recognized image;
  • the recognition sub-module is configured to perform the target object recognition on the to-be-recognized area on the dimmed to-be-recognized image
  • the image exposure sub-module is configured to dim the dimmed image to be recognized according to the first brightness interval value when the target object is not recognized, and obtain the current dimmed image to be recognized image, perform the target object recognition on the to-be-recognized area on the current dimmed image to be recognized until the target object is recognized, and perform the target object recognition on the to-be-recognized image after the dimmed
  • the target object is subjected to exposure processing to obtain the exposure image.
  • the image exposure module further includes:
  • the brightness determination sub-module is configured to determine the brightness of the to-be-identified image when the target object is not identified; the brightness adjustment sub-module is configured to determine the brightness of the image to be identified according to the second brightness when the brightness Brightness interval value brightens the to-be-recognized image to obtain a brightened to-be-recognized image; a recognition sub-module configured to perform the target object recognition on the to-be-recognized area on the brightened to-be-recognized image
  • the image exposure sub-module is configured to brighten the brightened image to be identified according to the second brightness interval value when the target object is not identified, and obtain the current brightened to-be-identified image image, perform the target object recognition on the to-be-recognized area on the current brightened image to be recognized until the target object is recognized, and perform the target object recognition on the area to be recognized on the brightened image to be recognized.
  • the target object is subjected to exposure processing to obtain the exposure image
  • the image exposure module further includes:
  • the identification sub-module is configured to perform preset object recognition on the to-be-recognized image; the brightness adjustment sub-module is configured to perform multiple brightness-corresponding evaluations on the to-be-recognized image when the preset object is not identified. Brightness adjustment to obtain a plurality of adjusted images to be recognized; a recognition sub-module configured to perform the target object recognition on the plurality of adjusted images to be recognized; an image exposure sub-module configured to recognize the target In the case of the target object, exposure processing is performed on the target object on the adjusted to-be-recognized image in which the target object exists, to obtain the exposure image.
  • the target object includes a human face;
  • the preset object includes a human shape;
  • the recognition sub-module is configured to perform face recognition on the to-be-recognized image through a human-shape recognition network; and is also configured to perform face recognition on the to-be-recognized area through the face recognition network.
  • the abnormal brightness area includes a first abnormal brightness area
  • the brightness adjustment module is configured to adjust the brightness of the first abnormal brightness area based on the first brightness adjustment parameter to obtain the to-be-identified image; wherein the brightness of the first abnormal brightness area in the to-be-identified image is lower than The brightness of the first abnormal brightness area on the to-be-exposed image.
  • the abnormal brightness area includes a second abnormal brightness area
  • the brightness adjustment module is configured to adjust the brightness of the second abnormal brightness area based on the second brightness adjustment parameter to obtain the to-be-identified image; wherein the brightness of the second brightness-abnormal area in the to-be-identified image is higher than The brightness of the second abnormal brightness area on the to-be-exposed image.
  • the area determination module is further configured to perform brightness recognition on the to-be-exposed image to determine a non-abnormal brightness area on the to-be-exposed image; image exposure The module is further configured to, in response to determining the target object in the non-abnormal brightness area, perform exposure processing on the target object to obtain the exposure image.
  • An embodiment of the present disclosure provides an electronic device, including at least one processor, and a memory connected in communication with the at least one processor; wherein, the memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the memory by executing the memory.
  • the stored instructions implement a target object exposure method as in any one of the first aspects.
  • An embodiment of the present disclosure provides a computer-readable storage medium, where at least one instruction or at least one program is stored in the computer-readable storage medium, and at least one instruction or at least one program is loaded and executed by a processor to implement the first aspect Any one of the target object exposure methods.
  • Embodiments of the present disclosure provide a computer program product comprising instructions that, when executed on a computer, cause the computer to perform any one of the target object exposure methods of the first aspect of the present disclosure.
  • An embodiment of the present disclosure provides a computer program, where the computer program includes computer-readable codes, and when the computer-readable codes are executed in an electronic device, the processor of the electronic device executes the above-mentioned goals.
  • Object exposure method when the computer-readable codes are executed in an electronic device, the processor of the electronic device executes the above-mentioned goals.
  • the image to be exposed is obtained, the brightness of the image to be exposed is identified, the abnormal brightness area on the image to be exposed is determined, the brightness of the abnormal brightness area is adjusted, and the image to be identified is obtained, and in response to the image to be identified A target object is identified in the image, and exposure processing is performed on the target object to obtain an exposure image.
  • the embodiments of the present disclosure can improve the abnormal brightness area of an image originally obtained in a relatively extreme environment through brightness adjustment, avoid abnormal exposure of the target object in an extreme environment, and lay a good foundation for subsequent image application after exposure.
  • FIG. 1 shows a schematic diagram of an application environment according to an embodiment of the present disclosure
  • FIG. 2 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure
  • FIG. 3 shows a schematic diagram of a system structure of a target exposure method according to an embodiment of the present disclosure
  • FIG. 4 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure
  • FIG. 5 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure
  • FIG. 6 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure
  • FIG. 7 shows a block diagram of a target object exposure apparatus according to an embodiment of the present disclosure
  • FIG. 8 shows a block diagram of an electronic device according to an embodiment of the present disclosure
  • FIG. 9 shows a block diagram of another electronic device according to an embodiment of the present disclosure.
  • FIG. 1 shows a schematic diagram of an application environment according to an embodiment of the present disclosure. As shown in FIG. 1 , it includes an image providing device 01 and an image processing device 02 . Optionally, the image providing device 01 and the image processing device 02 may be connected through a wireless link, or may be connected through a wired link.
  • the image processing device 02 acquires the image to be exposed from the image providing device 01, performs brightness identification on the image to be exposed, and determines an abnormal brightness area on the image to be exposed.
  • the image processing device 02 adjusts the brightness of the abnormal brightness area to obtain an image to be recognized, and performs exposure processing on the target object to obtain an exposed image when the target object is identified on the image to be recognized and the target object is determined.
  • the image processing device 02 in FIG. 1 may be an image processing system or an image processing platform.
  • the image processing system or the image processing platform may include multiple servers or processing terminals.
  • the first server can obtain the image to be exposed from the image providing device 01, and perform brightness recognition on the image to be exposed, Determine the abnormal brightness area on the image to be exposed, and transmit the image to be exposed with the abnormal brightness area marked to the second server.
  • the identification image is transmitted to the third server.
  • the third server performs target object recognition on the image to be recognized, and when the target object is determined, performs exposure processing on the target object to obtain an exposed image. In this way, by adjusting the brightness of the image to be exposed, the image is at a normal brightness, so that the image processing device can better detect the target object, thereby facilitating subsequent exposure of the target object.
  • the image processing device 02 provided in this embodiment of the present disclosure may be a terminal device, a server, or other types of electronic devices, where the terminal device may be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless Phones, Personal Digital Assistants (PDAs), handheld devices, computing devices, in-vehicle devices, wearable devices, etc.
  • the target object exposure method may be implemented by the processor calling computer-readable instructions stored in the memory.
  • the method for exposing a target object according to an embodiment of the present disclosure will be described below by taking an electronic device as an execution subject as an example.
  • the target object exposure method can be implemented by the processor calling computer readable instructions stored in the memory.
  • the image providing device 01 provided in this embodiment of the present disclosure may be a terminal device, a server, or other types of electronic devices, where the terminal device may include, but is not limited to, a video camera, a video recorder, and the like.
  • FIG. 2 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure. As shown in FIG. 2 , the method includes:
  • the image processing device may obtain the reference picture through the image providing device, or the image providing device may obtain the to-be-exposed image from another device, and then provide it to the image processing device, for example, the image providing device may obtain the image from Provide equipment for obtaining images from equipment such as camera equipment and monitoring equipment.
  • the image providing device described above may be a frame in a video.
  • each frame in the video may be an image to be exposed in the embodiment of the present disclosure, or some frames in the video may be referred to as the image to be exposed in the embodiment of the present disclosure, that is, the image provides
  • the device acquires the video, it can sample the video, determine the image frame obtained by sampling as the image to be exposed, and transmit it to the image processing device.
  • S22 Perform brightness identification on the to-be-exposed image, and determine an abnormal brightness area on the to-be-exposed image.
  • various results can be obtained by identifying the to-be-exposed image, including that the to-be-exposed image is all areas with normal brightness, or the to-be-exposed image includes an abnormal brightness area and a normal brightness area, or the to-be-exposed image includes a brightness abnormal area and a normal brightness area. All are areas of abnormal brightness.
  • the abnormal brightness area may include a backlight area, a low-light area, a strong-light area, or a smooth-light area.
  • the backlight area refers to that the objects in this area of the image are completely photographed against the light, and the objects in this area are not clearly visible or very dim.
  • Low light area refers to the area of the image where things are dim, although not completely against the light.
  • the front light area means that the objects in this area of the image are shot completely along the light, and the light is too strong to be seen clearly.
  • the strong light area refers to the fact that although the objects in this area of the image are not completely photographed with the light, the light is still very strong, causing the objects to be unclear.
  • the image to be exposed since the image to be exposed may be obtained in an abnormal environment, for example, photographed or recorded in the evening or in a dimly lit environment, the image to be exposed may exhibit a phenomenon of backlight or weak light.
  • the image to be exposed is shot or recorded at noon or in an environment with strong light, so the image to be exposed may exhibit strong light or smooth light. All of these phenomena may cause adverse effects on recognition during the process of recognizing the target object. Therefore, in an optional implementation manner, the brightness of the image to be exposed may be identified, and the abnormal brightness area on the image to be exposed may be determined.
  • the abnormal brightness area may include a first abnormal brightness area.
  • the above process of identifying the brightness of the image to be exposed and determining the abnormal brightness area on the image to be exposed may be expressed as performing brightness adjustment on the first abnormal brightness area based on the first brightness adjustment parameter, and obtaining Image to be recognized.
  • the brightness of the first abnormal brightness area in the image to be identified is lower than the brightness of the first abnormal brightness area on the image to be exposed.
  • the above-mentioned first abnormal brightness area may be a smooth light area or a strong light area, and the brightness is relatively bright in the smooth light area or the strong light area.
  • the above-mentioned first brightness adjustment parameter is a dimming parameter.
  • the dimming parameter may include a predetermined first brightness, and the predetermined first brightness is lower than the brightness before dimming, regardless of whether In whichever picture to be exposed is identified as having the first abnormal brightness area, the first abnormal brightness area can be dimmed according to the preset first brightness.
  • the dimming rule does not have a fixed first brightness.
  • the brightness of the first brightness abnormality area can be determined to be adjusted according to the brightness of the first brightness abnormality area.
  • the brightness to be adjusted is then adjusted based on the brightness to be adjusted to the first abnormal brightness area, wherein the brightness to be adjusted is lower than the brightness of the first abnormal brightness area.
  • the abnormal brightness area may include a second abnormal brightness area.
  • the above process of identifying the brightness of the image to be exposed and determining the abnormal brightness area on the image to be exposed may be expressed as performing brightness adjustment on the second abnormal brightness area based on the second brightness adjustment parameter, and obtaining Image to be recognized.
  • the brightness of the second abnormal brightness area in the image to be identified is higher than the brightness of the second abnormal brightness area on the image to be exposed.
  • the above-mentioned second abnormal brightness area may be a backlight area or a low-light area. In the backlight area or the low-light area, the brightness is relatively dim.
  • the above-mentioned second brightness adjustment parameter is a brightness adjustment parameter.
  • the brightness adjustment parameter may include a predetermined second brightness, and the predetermined second brightness is higher than the brightness before the brightness adjustment, no matter which picture to be exposed is identified as having abnormal second brightness.
  • the second brightness abnormal area can be brightened according to the preset second brightness.
  • the dimming rule does not have a fixed second brightness. As long as it is identified that there is a second brightness abnormal area in the image to be exposed, it can be determined according to the brightness of the second brightness abnormal area to be adjusted. The brightness to be adjusted is then adjusted based on the brightness to be adjusted to the second abnormal brightness area, wherein the brightness to be adjusted is higher than the brightness of the second abnormal brightness area.
  • the above-mentioned embodiment determines the area to be adjusted in brightness by detecting the abnormal brightness area, and then adjusts the brightness of the area according to the corresponding brightness adjustment parameter, which lays a good foundation for the subsequent identification of the target object.
  • the image processing device can directly identify the target object on the recognition image, and when it is determined that the image has a target object, directly perform exposure processing on the target object to obtain an exposure image.
  • the target object can be anything, including but not limited to pedestrians, vehicles (cars, trucks, bicycles, etc.), obstacles (trash cans, trees, garbage, traffic lights, etc.), animals (dogs, cats, etc.), Or even a part of something, like a human face, a license plate on a vehicle, etc.
  • the image processing device may firstly pre-recognize the thing containing the target object, and then recognize the target object when the thing containing the target object is recognized.
  • the coarse recognition module of the thing containing the target object can be better recognized, and after the coarse recognition module recognizes it, the refined recognition module is activated to recognize the target thing. It can reduce the workload of the refined recognition module and reduce the computing power of the refined recognition module.
  • an exposure image obtained by exposing a target in a relatively extreme environment can be improved through brightness adjustment, avoiding abnormal exposure of the target object in an extreme light environment, and laying a good foundation for subsequent image application after exposure .
  • FIG. 3 is a schematic diagram of a system structure to which a target exposure method according to an embodiment of the present disclosure can be applied; as shown in FIG. 3 , the system structure includes: an image acquisition device 301 , a network 302 , and a control terminal 303 .
  • the image acquisition device 301 and the control terminal 303 establish a communication connection through the network 302
  • the image acquisition device 301 reports the image to be exposed to the control terminal 303 through the network 302
  • the control terminal 303 responds to the image to be exposed and treats the image to be exposed.
  • Brightness recognition is performed on the exposed image to determine the abnormal brightness area on the image to be exposed; secondly, the brightness of the abnormal brightness area is adjusted to determine the image to be recognized; thirdly, in response to identifying the target object in the image to be recognized, the target The subject is subjected to exposure processing to obtain an exposed image. Finally, the control terminal 303 uploads the exposure image to the network 302 and sends it to the image acquisition device 301 through the network 302 . In this way, it is possible to improve the abnormal brightness area of an image originally obtained in a relatively extreme environment through brightness adjustment, avoid abnormal exposure of the target object in an extreme light environment, and lay a good foundation for subsequent image application after exposure.
  • control terminal 303 may include a visual processing device or a remote server with visual information processing capabilities.
  • the network 302 may employ wired or wireless connections.
  • the image acquisition device 301 can communicate with the visual processing device through a wired connection, such as data communication through a bus; when the control terminal 303 is a remote server, the image acquisition device 301 can Data exchange with remote server through wireless network.
  • the image acquisition device 301 may be a vision processing device with a video capture module, or a host with a camera.
  • the method for exposing the target object in the embodiment of the present disclosure may be performed by the image acquisition device 301 , and the above-mentioned system architecture may not include the network 302 and the control terminal 303 .
  • FIG. 4 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure. As shown in FIG. 4 , the method includes:
  • S401 Perform preset object recognition on the image to be recognized, where the preset object includes a target object; determine whether the preset object is recognized. If the preset object is identified, go to step S402; otherwise, go to step S405.
  • the preset object includes a human shape
  • the image processing device can perform human shape recognition on the image to be recognized by using a human shape recognition network built in the device.
  • the humanoid recognition network may include, but is not limited to, a deep learning network such as a convolutional neural network, a recurrent neural network, or a recurrent neural network.
  • a deep learning network such as a convolutional neural network, a recurrent neural network, or a recurrent neural network.
  • a convolutional neural network a large number of training data sets can be obtained.
  • Each training data set includes training images and human figures marked on the training images.
  • recognition training the parameters of the convolutional neural network are adjusted in the training so that the human figure output by the convolutional neural network matches the marked human figure, and a graph association recognition network is obtained.
  • S402 In the case of identifying the preset object, determine the to-be-identified area where the preset object is located.
  • step S403 Recognize the target object in the area to be recognized; determine whether the target object is recognized. If the target object is identified, go to step S404; otherwise, go to step S405.
  • the target object includes a human face
  • the image processing device can use a face recognition network built in the device to perform face recognition on the area to be recognized.
  • the face recognition network may include, but is not limited to, a deep learning network such as a convolutional neural network, a recurrent neural network, or a recurrent neural network.
  • a deep learning network such as a convolutional neural network, a recurrent neural network, or a recurrent neural network.
  • a convolutional neural network a large number of training data sets can be obtained.
  • Each training data set includes human figures and faces marked on the human figures.
  • the parameters of the convolutional neural network are adjusted in the training so that the face output by the convolutional neural network matches the marked face, and the graph association recognition network is obtained.
  • the training data in the training data set in the embodiment of the present disclosure may be stored in a certain storage area, and the storage area may be a blockchain.
  • blockchain is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the target object is not recognized when the target object is recognized in the area to be recognized in the above step S403, it may be because the above is only based on the first brightness adjustment parameter or the second brightness adjustment parameter this time.
  • the brightness adjustment does not adjust the brightness of the area to be recognized to be more conducive to recognizing the face, so multiple brightness adjustments can also be performed on the image.
  • FIG. 5 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure. As shown in FIG. 5 , the method includes:
  • S501 In the case where the target object is not recognized, perform brightness adjustment corresponding to a plurality of brightnesses of the image to be recognized to obtain a plurality of adjusted images to be recognized.
  • step S501 may be to perform preset object recognition on the image to be recognized, and when a preset object is recognized, determine the to-be-recognized area where the preset object is located, and then can identify the preset object.
  • step S502 Perform target object recognition on the to-be-recognized areas on the multiple adjusted to-be-recognized images; determine whether the target object is recognized in the multiple adjusted to-be-recognized areas, and go to step S503; otherwise, go to step S504.
  • step S503 may be turned to perform exposure processing on the adjusted target object of the to-be-recognized image.
  • S503 In the case that the target object is identified, perform exposure processing on the target object on the adjusted to-be-identified image in which the target object exists, to obtain an exposure image.
  • steps S501 to S504 illustrate a scheme of recognizing multiple adjusted images to be recognized after obtaining multiple adjusted images to be recognized.
  • the brightness adjustment corresponding to multiple brightnesses, and obtaining multiple adjusted images to be recognized may be a waste of hardware resources. In order to reduce the waste of resources, it can be achieved by reducing the number of adjusted images to be recognized.
  • the brightness of the image to be identified may be determined, for example, the brightness is A.
  • the image to be recognized is dimmed according to the first brightness interval value (-1) to obtain a dimmed image to be recognized (the brightness is A-1).
  • the target object recognition is performed on the to-be-recognized area on the image, and in the case where the target object is not recognized, the dimmed image to be recognized is dimmed according to the first brightness interval value to obtain the current dimmed image to be recognized (brightness).
  • target object recognition is performed on the to-be-recognized area on the current dimmed image to be recognized, and so on until the target object is recognized, and the dimmed image to be recognized that can recognize the target object
  • the target object on the image is subjected to exposure processing to obtain an exposure image.
  • the brightness of the image to be identified can be determined, for example, the brightness is B; when the brightness is less than the second brightness, according to the second brightness interval value ( +1) Brighten the image to be identified to obtain the brightened image to be identified (the brightness of the image is B+1). Perform target object recognition on the to-be-recognized area on the brightened to-be-recognized image, and if the target object is not identified, brighten the brightened to-be-recognized image according to the second brightness interval value to obtain the current brightened image.
  • target object recognition is performed on the to-be-recognized area on the current brightened to-be-recognized image, and so on, until the target object is recognized, and the target object can be recognized
  • the target object on the bright image to be identified is subjected to exposure processing to obtain an exposed image.
  • FIG. 6 shows a flowchart of a method for exposing a target object according to an embodiment of the present disclosure. As shown in FIG. 6 , the method includes:
  • step S601 Perform preset object recognition on the image to be recognized, and if the preset object is not recognized, go to step S602.
  • S602 Perform brightness adjustment corresponding to a plurality of brightnesses on the image to be recognized to obtain a plurality of adjusted images to be recognized.
  • the brightness can be directly adjusted to obtain a plurality of adjusted images to be recognized.
  • S603 Perform target object recognition on the plurality of adjusted images to be recognized, and determine whether the target object is recognized.
  • step S604 If the target object is identified, go to step S604; otherwise, go to step S605 to end the process.
  • S604 Perform exposure processing on the target object on the adjusted to-be-identified image in which the target object exists, to obtain an exposure image.
  • the pressure on the algorithm can be reduced, and the target object (such as a human face) will not be directly detected without detecting a preset object (such as a human shape).
  • the reason why the preset object (human shape) cannot be detected is not the brightness, but it may be that most of the human shape is blocked by the object, for example, a person's body is hiding under a big tree , but the face is visible.
  • the human figure is recognized, the overall outline of the person is detected, which may lead to unrecognized results.
  • the target object recognition can be performed directly, and if the target object is recognized, exposure processing is performed on the target object on the to-be-recognized image to obtain an exposed image.
  • the image processing device may identify the brightness of the to-be-exposed image and determine the non-abnormal brightness area on the to-be-exposed image, and in response to determining the target in the non-abnormal brightness area The target object is subjected to exposure processing to obtain an exposure image.
  • FIG. 7 shows a block diagram of a target object exposure apparatus according to an embodiment of the present disclosure.
  • the target object exposure apparatus includes:
  • an area determination module 702 configured to perform brightness identification on the to-be-exposed image, and to determine an abnormal brightness area on the to-be-exposed image
  • a brightness adjustment module 703, configured to adjust the brightness of the abnormal brightness area to obtain an image to be identified;
  • the image exposure module 704 is configured to, in response to identifying the target object in the to-be-recognized image, perform exposure processing on the target object to obtain an exposure image.
  • the image exposure module includes an identification sub-module, an identification area determination sub-module, and a processing sub-module;
  • the recognition sub-module is configured to perform preset object recognition on the to-be-recognized image, and the preset object includes a target object;
  • the recognition area sub-determination module is configured to determine the preset object when the preset object is recognized. the to-be-recognized area where the preset object is located;
  • the recognition sub-module is configured to perform target object recognition on the to-be-recognized area;
  • the processing sub-module is configured to, when the target object is recognized, The target object is subjected to exposure processing to obtain the exposure image.
  • the image exposure module further includes an adjustment sub-module
  • the adjustment sub-module is configured to perform brightness adjustment corresponding to a plurality of brightnesses on the to-be-recognized image under the condition that the target object is not recognized, to obtain a plurality of adjusted images to be recognized;
  • the recognition sub-module configured to perform target object recognition on the to-be-recognized areas on the plurality of adjusted images to be recognized;
  • the processing sub-module is configured to, when the target object is recognized The target object on the adjusted to-be-identified image is subjected to exposure processing to obtain the exposure image.
  • the image exposure module further includes a brightness determination submodule and a brightness adjustment submodule:
  • the brightness determination submodule is configured to determine the brightness of the to-be-identified image when the target object is not identified; the brightness adjustment submodule is configured to determine the brightness of the image to be identified when the brightness is greater than the first brightness , dim the to-be-recognized image according to the first brightness interval value to obtain the dimmed to-be-recognized image; the recognition sub-module is configured to perform all the necessary steps on the to-be-recognized area on the dimmed to-be-recognized image.
  • the target object recognition is performed; the image exposure sub-module is configured to dim the dimmed image to be recognized according to the first brightness interval value when the target object is not recognized to obtain the current dimmed image.
  • the target object recognition is performed on the area to be recognized on the current image to be recognized after dimmed until the target object is recognized, and the image to be recognized after dimmed is recognized.
  • the target object above is subjected to exposure processing to obtain an exposure image.
  • the image exposure module further includes:
  • the brightness determination sub-module is configured to determine the brightness of the to-be-identified image when the target object is not identified; the brightness adjustment sub-module is configured to determine the brightness of the image to be identified according to the second brightness when the brightness Brightness interval value brightens the to-be-recognized image to obtain a brightened to-be-recognized image; a recognition sub-module configured to perform the target object recognition on the to-be-recognized area on the brightened to-be-recognized image
  • the image exposure sub-module is configured to brighten the brightened image to be identified according to the second brightness interval value when the target object is not identified, and obtain the current brightened to-be-identified image image, perform the target object recognition on the to-be-recognized area on the current brightened image to be recognized until the target object is recognized, and perform the target object recognition on the area to be recognized on the brightened image to be recognized.
  • the target object is subjected to exposure processing to obtain an exposure image
  • the identification sub-module is configured to perform preset object recognition on the to-be-recognized image; the brightness adjustment sub-module is configured to perform multiple brightness-corresponding evaluations on the to-be-recognized image when the preset object is not identified. Brightness adjustment to obtain a plurality of adjusted images to be recognized; a recognition sub-module configured to perform the target object recognition on the plurality of adjusted images to be recognized; an image exposure sub-module configured to recognize the target In the case of the target object, exposure processing is performed on the target object on the adjusted to-be-recognized image where the target object exists to obtain an exposure image.
  • the target object includes a human face;
  • the preset object includes a human figure;
  • the recognition module is configured to perform face recognition on the to-be-recognized image through a human-shape recognition network; and is also configured to perform face recognition on the to-be-recognized area through the face recognition network.
  • the abnormal brightness area includes a first abnormal brightness area
  • the brightness adjustment module is configured to adjust the brightness of the first abnormal brightness area based on the first brightness adjustment parameter to obtain the to-be-identified image; wherein the brightness of the first abnormal brightness area in the to-be-identified image is lower than The brightness of the first abnormal brightness area on the to-be-exposed image.
  • the abnormal brightness area includes a second abnormal brightness area
  • the brightness adjustment module is configured to adjust the brightness of the second abnormal brightness area based on the second brightness adjustment parameter to obtain the to-be-identified image; wherein the brightness of the second brightness-abnormal area in the to-be-identified image is higher than The brightness of the second abnormal brightness area on the to-be-exposed image.
  • the area determination module is further configured to perform brightness identification on the to-be-exposed image, and to determine a non-abnormal brightness area on the to-be-exposed image; the image exposure module is further configured to respond to The target object is determined in the non-abnormal brightness area, and exposure processing is performed on the target object to obtain the exposure image.
  • the functions or modules included in the apparatuses provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments.
  • An embodiment of the present disclosure further provides a computer-readable storage medium, where at least one instruction or at least one piece of program is stored, and the at least one instruction or at least one piece of program is loaded and executed by a processor to implement the above-mentioned method.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium.
  • An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to perform the above method.
  • the electronic device may be provided as a terminal, server or other form of device.
  • Embodiments of the present disclosure also provide a computer program, the computer program includes computer-readable codes, and when the computer-readable codes are executed in an electronic device, the processor of the electronic device executes any one of the above A target object exposure method of an embodiment.
  • Embodiments of the present disclosure provide another computer program product containing instructions, which, when executed on a computer, cause the computer to execute the target object exposure method of the present disclosure.
  • the computer program product can be realized by means of hardware, software or a combination thereof.
  • the computer program product may be embodied as a computer storage medium, and in other embodiments, the computer program product may be embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.
  • FIG. 8 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc. terminal.
  • an electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814 , and the communication component 816 .
  • the processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 802 can include one or more processors 820 to execute instructions to perform all or some of the steps of the methods described above.
  • processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components.
  • processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operation at electronic device 800 . Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. Memory 804 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic or Optical Disk Magnetic Disk
  • Power supply assembly 806 provides power to various components of electronic device 800 .
  • Power supply components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800 .
  • Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action.
  • the multimedia component 808 includes a front-facing camera and/or a rear-facing camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.
  • Audio component 810 is configured to output and/or input audio signals.
  • audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 800 is in operating modes, such as calling mode, recording mode, and voice recognition mode.
  • the received audio signal may be further stored in memory 804 or transmitted via communication component 816 .
  • audio component 810 also includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.
  • Sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of electronic device 800 .
  • the sensor assembly 814 can detect the on/off state of the electronic device 800, the relative positioning of the components, such as the display and the keypad of the electronic device 800, the sensor assembly 814 can also detect the electronic device 800 or one of the electronic device 800 Changes in the position of components, presence or absence of user contact with the electronic device 800 , orientation or acceleration/deceleration of the electronic device 800 and changes in the temperature of the electronic device 800 .
  • Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices.
  • Electronic device 800 may access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination thereof.
  • the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication.
  • NFC near field communication
  • the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A programmed gate array
  • controller microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • a non-volatile computer-readable storage medium such as a memory 804 comprising computer program instructions executable by the processor 820 of the electronic device 800 to perform the above method is also provided.
  • FIG. 9 shows a block diagram of another electronic device according to an embodiment of the present disclosure.
  • the electronic device 900 may be provided as a server.
  • electronic device 900 includes processing component 922, which further includes one or more processors, and a memory resource represented by memory 932 for storing instructions executable by processing component 922, such as applications.
  • An application program stored in memory 932 may include one or more modules, each corresponding to a set of instructions.
  • the processing component 922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 900 may also include a power supply assembly 926 configured to perform power management of the electronic device 900, a wired or wireless network interface 950 configured to connect the electronic device 900 to a network, and an input output (I/O) interface 958 .
  • Electronic device 800 may operate based on an operating system stored in memory 932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium such as memory 932 comprising computer program instructions executable by processing component 922 of electronic device 900 to perform the above method.
  • the present disclosure may be a system, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disk read only memory
  • DVD digital versatile disk
  • memory sticks floppy disks
  • mechanically coded devices such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • the computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages.
  • Source or object code written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect).
  • LAN local area network
  • WAN wide area network
  • custom electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) can be personalized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present disclosure.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.
  • Embodiments of the present disclosure provide a method, device, storage medium, device, and program for exposing a target object.
  • the method includes: acquiring an image to be exposed; performing brightness recognition on the image to be exposed, and determining an abnormal brightness on the image to be exposed The brightness of the abnormal brightness area is adjusted to obtain an image to be recognized; in response to identifying a target object in the image to be recognized, exposure processing is performed on the target object to obtain an exposed image.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Studio Devices (AREA)
  • Exposure Control For Cameras (AREA)

Abstract

本公开实施例公开了一种目标对象曝光方法、装置、存储介质、设备及程序，在本公开实施例中，通过获取待曝光图像，对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域，对亮度异常区域进行亮度调节，得到待识别图像；响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。本公开实施例可以通过亮度调节改进原本处在比较极端的环境下得到的图像，避免极端光线环境下对获取的图像中目标对象的曝光异常，为曝光后的后续图像应用打下良好基础。

Description

目标对象曝光方法、装置、存储介质、设备及程序
相关申请的交叉引用
本专利申请要求2021年01月29日提交的中国专利申请号为202110127188.6、申请人为深圳市商汤科技有限公司，申请名称为“目标对象曝光方法、装置、存储介质及设备”的优先权，该申请文件以引用的方式并入本申请中。
技术领域
本公开涉及计算机技术领域，尤其涉及一种目标对象曝光方法、装置、存储介质、设备及程序。
背景技术
在图像识别和人工智能领域中，目标识别技术在各行各业中都得到相应的应用，比如，在现在的身份信息识别领域中，人脸识别技术就占据着很重要的位置。
由于目标识别的重要性使得针对包含有目标的图像优化成为了市场的刚性需求，从而使得越来越多的厂家也在做基于目标的自动曝光策略。然而，在部分极端光线环境中，目标识别模块无法检测到本应该检测到的目标，从而导致部分场景无法进行基于目标的自动曝光，造成基于曝光后的目标的后续应用无法进行下去。
发明内容
本公开实施例提出了一种目标对象曝光方法、装置、存储介质、设备及程序。
本公开实施例提供了一种目标对象曝光方法，所述方法由电子设备执行，其包括：获取待曝光图像；对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度异常区域；对所述亮度异常区域进行亮度调节，得到待识别图像；响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。如此，可以通过亮度调节改进原本处在比较极端的环境下得到的图像，避免极端光线环境下图像中目标对象的曝光异常，为曝光后的后续图像应用打下良好基础。
在一些可能的实施方式中，响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像，包括：对所述待识别图像进行预设对象识别，所述预设对象包含有目标对象；在识别出所述预设对象的情况下，确定出所述预设对象所在的待识别区域；对所述待识别区域进行目标对象识别；在识别出所述目标对象的情况下，对目标对象进行曝光处理，得到曝光图像。如此，能够在对待识别图像中识别出目标对象，从而能够对目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，在所述对所述待识别区域进行目标对象识别之后，所述还包括：
在未识别出所述目标对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；对所述多张调节后的待识别图像上的待识别区域进行目标对象识别；在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。如此，能够在待识别图像中识别出预设对象，但是在预设对象所在的待识别区域中未识别出目标对象的情况下，通过对待识别区域进行亮度调节，识别出目标对象，从而能够对目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，对所述待识别区域进行目标对象识别之后，还包括：在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；在亮度大于第一亮度的情况下，根据第一亮度间隔数值将待识别图像调暗，得到调暗后的待识别图像；对所述调暗后的待识别图像 上的待识别区域进行目标对象识别；在未识别出所述目标对象的情况下，根据第一亮度间隔数值将调暗后的待识别图像调暗，得到当前的调暗后的待识别图像；对所述当前的调暗后的待识别图像上的待识别区域，进行所述目标对象识别，直至识别出所述目标对象；对所述调暗后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。如此，能够在待识别区域中未识别出目标对象的情况下，在待识别图像的亮度比较亮时，采用第一亮度间隔数值将待识别图像调暗，从而可以识别出待识别区域中的目标对象，进而对目标对象进行曝光，得到曝光对象。
在一些可能的实施方式中，在所述对所述待识别区域进行所述目标对象识别之后，所述方法还包括：
在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；在所述亮度小于第二亮度的情况下，根据第二亮度间隔数值将所述待识别图像调亮，得到调亮后的待识别图像；对所述调亮后的待识别图像上的所述待识别区域，进行所述目标对象识别；在未识别出所述目标对象的情况下，根据第二亮度间隔数值将调亮后的待识别图像调亮，得到当前的调亮后的待识别图像；对所述当前的调亮后的待识别图像上的待识别区域进行所述目标对象识别，直至识别出所述目标对象；对所述调亮后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。如此，能够在待识别区域中未识别出目标对象的情况下，在待识别图像的亮度比较暗时，采用第二亮度间隔数值将待识别图像调亮，从而可以识别出待识别区域中的目标对象，进而对目标对象进行曝光，得到曝光对象。
在一些可能的实施方式中，响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像，包括：对所述待识别图像进行所述预设对象识别；在未识别出所述预设对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；对所述多张调节后的待识别图像进行所述目标对象识别；在识别出所述目标对象的情况下，对所述目标对象进行曝光处理，得到所述曝光图像。如此，能够在待识别图像中未识别出预设对象时，可以通过对应的亮度调节，进而在亮度调节后的图像中识别出目标对象，从而可以对目标对象进行曝光，得到曝光对象。
在一些可能的实施方式中，所述目标对象包括人脸；所述预设对象包括人形；对所述待识别图像进行预设对象识别，包括：通过人形识别网络对所述待识别图像进行人形识别；
对所述待识别区域进行目标对象识别，包括：通过所述人脸识别网络对所述待识别区域进行人脸识别。如此，可以采用人形识别网络进行预设对象的识别和目标对象的识别。
在一些可能的实施方式中，所述亮度异常区域包括第一亮度异常区域；
对所述亮度异常区域进行亮度调节，得到待识别图像，包括：基于第一亮度调节参数对所述第一亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第一亮度异常区域的亮度低于所述待曝光图像上的第一亮度异常区域的亮度。如此，能够对待曝光图像中的第一亮度异常区域进行亮度调节，使得第一亮度异常区域在调节后得到的待识别图像中的亮度趋于正常。
在一些可能的实施方式中，所述亮度异常区域包括第二亮度异常区域；
对所述亮度异常区域进行亮度调节，得到待识别图像，包括：基于第二亮度调节参数对所述第二亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第二亮度异常区域的亮度高于所述待曝光图像上的第二亮度异常区域的亮度。如此，能够对待曝光图像中的第二亮度异常区域进行亮度调节，使得第二亮度异常区域在调节后得到的待识别图像中的亮度趋于正常。
在一些可能的实施方式中，在所述获取所述待曝光图像之后，所述方法还包括：对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度非异常区域；响应于在所述亮度非异常区域中确定出所述目标对象，对所述目标对象进行曝光处理，得到所述曝光图像。如此，能够对待曝光图像中的亮度非异常区域进行目标对象识别，并对识别出的目标对象进行曝光，得到曝光图像。
本公开提供了一种目标对象曝光装置，包括：
图像获取模块，配置为获取待曝光图像；区域确定模块，配置为对所述待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域；亮度调节模块，配置为对所述亮度异常区域进行 亮度调节，得到待识别图像；图像曝光模块，配置为响应于在所述对待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，图像曝光模块包括识别子模块，识别区域确定子模块，处理子模块；
识别子模块，配置为对所述待识别图像进行预设对象识别，预设对象包含有目标对象；识别区域确定子模块，配置为在识别出所述预设对象的情况下，确定出所述预设对象所在的待识别区域；所述识别子模块，配置为对所述待识别区域进行目标对象识别；处理子模块，配置为在识别出所述目标对象的情况下，对所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，所述图像曝光模块还包括：
调节子模块，配置为在未识别出所述目标对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；所述识别子模块，配置为对所述多张调节后的待识别图像上的待识别区域进行目标对象识别；所述处理子模块，配置为在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，所述图像曝光模块还包括：
亮度确定子模块，配置为在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；亮度调节子模块，配置为在所述亮度大于第一亮度的情况下，根据第一亮度间隔数值将所述待识别图像调暗，得到调暗后的待识别图像；识别子模块，配置为对所述调暗后的待识别图像上的所述待识别区域进行所述目标对象识别；图像曝光子模块，配置为在未识别出所述目标对象的情况下，根据所述第一亮度间隔数值将所述调暗后的待识别图像调暗，得到当前的调暗后的待识别图像，对所述当前的调暗后的待识别图像上的所述待识别区域进行所述目标对象识别，直至识别出所述目标对象，对所述调暗后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，图像曝光模块还包括：
亮度确定子模块，配置为在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；亮度调节子模块，配置为在所述亮度小于第二亮度的情况下，根据第二亮度间隔数值将所述待识别图像调亮，得到调亮后的待识别图像；识别子模块，配置为对所述调亮后的待识别图像上的所述待识别区域进行所述目标对象识别；图像曝光子模块，配置为在未识别出所述目标对象的情况下，根据所述第二亮度间隔数值将所述调亮后的待识别图像调亮，得到当前的调亮后的待识别图像，对所述当前的调亮后的待识别图像上的所述待识别区域进行所述目标对象识别，直至识别出所述目标对象，对所述调亮后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，所述图像曝光模块还包括：
识别子模块，配置为对所述待识别图像进行预设对象识别；亮度调节子模块，配置为在未识别出所述预设对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；识别子模块，配置为对所述多张调节后的待识别图像进行所述目标对象识别；图像曝光子模块，配置为在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，所述目标对象包括人脸；所述预设对象包括人形；
所述识别子模块，配置为通过人形识别网络对所述待识别图像进行人形识别；还配置为通过所述人脸识别网络对所述待识别区域进行人脸识别。
在一些可能的实施方式中，所述亮度异常区域包括第一亮度异常区域；
所述亮度调节模块，配置为基于第一亮度调节参数对所述第一亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第一亮度异常区域的亮度低于所述待曝光图像上的第一亮度异常区域的亮度。
在一些可能的实施方式中，所述亮度异常区域包括第二亮度异常区域；
所述亮度调节模块，配置为基于第二亮度调节参数对所述第二亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第二亮度异常区域的亮度高于所述待曝光图像上的第二亮度异常区域的亮度。
在一些可能的实施方式中，获取所述待曝光图像之后，所述区域确定模块，还配置为对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度非异常区域；图像曝光模块，还配置为响应于在所述亮度非异常区域中确定出所述目标对象，对所述目标对象进行曝光处理，得到所述曝光图像。
本公开实施例提供了一种电子设备，包括至少一个处理器，以及与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，至少一个处理器通过执行存储器存储的指令实现如第一方面中任意一项的一种目标对象曝光方法。
本公开实施例提供了一种计算机可读存储介质，上述计算机可读存储介质中存储有至少一条指令或至少一段程序，至少一条指令或至少一段程序由处理器加载并执行以实现第一方面中任意一项的一种目标对象曝光方法。
本公开实施例提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行本公开的第一方面中任一目标对象曝光方法。
本公开实施例提供一种计算机程序，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备的处理器执行用于实现上述所述的目标对象曝光方法。
在本公开实施例中，通过获取待曝光图像，对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域，对亮度异常区域进行亮度调节，得到待识别图像，响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。如此，本公开实施例可以通过亮度调节改进原本处在比较极端的环境下得到的图像的异常亮度区域，避免极端环境下对目标对象的曝光异常，为曝光后的后续图像应用打下良好基础。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案和优点，下面将对实施例或现有技术描述中所需要使用的附图作简单的介绍，显而易见地，下面描述中的附图仅仅是本说明书的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它附图。
图1示出根据本公开实施例的一种应用环境的示意图；
图2示出根据本公开实施例的一种目标对象曝光方法的流程图；
图3示出根据本公开实施例的一种目标曝光方法的系统结构示意图；
图4示出根据本公开实施例的一种目标对象曝光方法的流程图；
图5示出根据本公开实施例的一种目标对象曝光方法的流程图；
图6示出根据本公开实施例的一种目标对象曝光方法的流程图；
图7示出根据本公开实施例的一种目标对象曝光装置的框图；
图8示出根据本公开实施例的一种电子设备的框图；
图9示出根据本公开实施例的另一种电子设备的框图。
具体实施方式
下面将结合本说明书实施例中的附图，对本说明书实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本说明书一部分实施例，而不是全部的实施例。基于本说明书中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包 含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或服务器不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
请参阅图1，图1示出根据本公开实施例的一种应用环境的示意图，如图1所示，包括图像提供设备01和图像处理设备02。可选的，图像提供设备01和图像处理设备02之间可以通过无线链路连接，也可以通过有线链路连接。
在一个可选的实施例中，图像处理设备02从图像提供设备01处获取待曝光图像，对该待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域。图像处理设备02对亮度异常区域进行亮度调节，得到待识别图像，在对待识别图像进行目标对象识别，且确定出目标对象的情况下，对目标对象进行曝光处理，得到曝光图像。
在另一个可选的实施例中，图1中的图像处理设备02可以是一个图像处理系统或者图像处理平台。该图像处理系统或者图像处理平台中可以包括多个服务器或者处理终端。比如，假设图像处理系统中有第一服务器、第二服务器和第三服务器这3个服务器，其中，第一服务器可以从图像提供设备01处获取待曝光图像，对该待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域，并将标出亮度异常区域的待曝光图像传给第二服务器，第二服务器对亮度异常区域进行亮度调节，得到待识别图像，并将亮度调节后的待识别图像传给第三服务器。第三服务器对待识别图像进行目标对象识别，在确定出目标对象的情况下，对目标对象进行曝光处理，得到曝光图像。这样，通过对待曝光图像进行亮度调节，使得图像处于一个正常的亮度下，使得图像处理设备可以更好的检测到目标对象，进而方便后续对该目标对象的曝光。
本公开实施例提供的技术方案可以应用于图像或视频的目标对象曝光、目标识别等应用场景的扩展，本公开实施例对此不做限定。
本公开实施例提供的图像处理设备02可以是终端设备、服务器或其它类型的电子设备，其中，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该目标对象曝光方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。下面以电子设备作为执行主体为例对本公开实施例的目标对象曝光方法进行说明。目标对象曝光方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
本公开实施例提供的图像提供设备01可以是终端设备、服务器或其它类型的电子设备，其中，终端设备可以包括但不限于摄像机，录像机等。
图2示出根据本公开实施例的一种目标对象曝光方法的流程图，如图2所示，方法包括：
S21：获取待曝光图像。
在一些可选的实施方式中，图像处理设备可以通过图像提供设备获取参考图片，或者，图像提供设备可以从其他设备处获取待曝光图像，再提供给图像处理设备，例如，图像提供设备可以从摄像设备、监控设备等设备处获取图像提供设备。在一些实现方式中，上述图像提供设 备可以是视频中的一帧。可选的，视频中的每一帧都可以成为本公开实施例中的待曝光图像，或者，视频中的某些帧可以称为本公开实施例中的待曝光图像，也就是说，图像提供设备获取视频后，可以对该视频进行采样，将采样得到的图像帧确定为待曝光图像，传输给图像处理设备。
S22：对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域。
在本公开实施例中，对待曝光图像进行识别可以得到多种结果，包括该待曝光图像都是亮度正常区域，或者该待曝光图像中包括亮度异常区域和亮度正常区域，或者该待曝光图像中都是亮度异常区域。其中，亮度异常区域可以包括逆光区域，弱光区域，强光区域或者顺光区域。其中，逆光区域是指图像该区域中的事物完全逆着光线拍摄，看不清或者很暗淡。弱光区域是指图像该区域中事物虽然不是完全逆着光线拍摄，但是很暗淡。顺光区域是指图像该区域中的事物完全顺着光线拍摄，光线太强，看不清。强光区域是指图像该区域中的事物虽然不是完全顺着光拍摄，但光线还是很强，导致事物看不清。
S23：对亮度异常区域进行亮度调节，得到待识别图像。
本公开实施例中，由于待曝光图像可能是在异常环境下得到的，比如，在傍晚或者光照比较暗的环境下拍摄或者录制的，因此导致待曝光图像可能呈现逆光或者弱光的现象。又比如，待曝光图像在中午或者光照比较强的环境下拍摄或者录制的，因此导致待曝光图像可能呈现强光或者顺光的现象。而这些现象都可能导致在识别目标对象的过程中对识别造成不良影响，因此，在一种可选的实施方式中，可以对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域。
在一个可能的实施例中，亮度异常区域可以包括第一亮度异常区域。这种情况下，上文中的对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域在本公开实施例中可以表示为基于第一亮度调节参数对第一亮度异常区域进行亮度调节，得到待识别图像。其中，待识别图像中第一亮度异常区域的亮度低于待曝光图像上的第一亮度异常区域的亮度。
可选的，上述的第一亮度异常区域可以是顺光区域或者是强光区域，在顺光区域或者强光区域，亮度都比较亮。上述的第一亮度调节参数是调暗参数，一种可选的实施方式中，调暗参数可以包含有一个预定的第一亮度，这个预定的第一亮度要低于调暗之前的亮度，无论哪张待曝光图片中识别有第一亮度异常区域，都可以根据预设的第一亮度对第一亮度异常区域进行调暗。另一种可选的实施方式中，调暗规则并没有一个固定的第一亮度，只要识别到待曝光图片中有第一亮度异常区域，就可以根据第一亮度异常区域的亮度确定出要调节到的亮度，再基于该要调节到的亮度对第一亮度异常区域进行调节，其中，该要调节到的亮度比第一亮度异常区域的亮度要低。
在一个可能的实施例中，亮度异常区域可以包括第二亮度异常区域。这种情况下，上文中的对待曝光图像进行亮度识别，确定待曝光图像上的亮度异常区域在本公开实施例中可以表示为基于第二亮度调节参数对第二亮度异常区域进行亮度调节，得到待识别图像。其中，待识别图像中第二亮度异常区域的亮度高于待曝光图像上的第二亮度异常区域的亮度。
可选的，上述的第二亮度异常区域可以是逆光区域或者是弱光区域，在逆光区域或者是弱光区域，亮度都比较暗淡。上述的第二亮度调节参数是调亮参数。一种可选的实施方式中，调亮参数可以包含有一个预定的第二亮度，这个预定的第二亮度要高于调亮之前的亮度，无论哪张待曝光图片中识别有第二亮度异常区域，都可以根据预设的第二亮度对第二亮度异常区域进行调亮。另一种可选的实施方式中，调暗规则并没有一个固定的第二亮度，只要识别到待曝光图片中有第二亮度异常区域，就可以根据第二亮度异常区域的亮度确定出要调节到的亮度，再基于该要调节到的亮度对第二亮度异常区域进行调节，其中，该要调节到的亮度比第二亮度异常区域的亮度要高。
上述的实施例通过对亮度异常区域的检测确定出要调节亮度的区域，再根据对应的亮度调节参数对该区域进行亮度调节，为后续对目标对象的识别打下良好基础。
S24：响应于在待识别图像中识别出目标对象，对目标对象进行曝光处理，得到曝光图像。
在一个可能的实施例中，图像处理设备可以直接对识别图像进行目标对象的识别，在确定出该图像中有目标对象的情况下，直接对目标对象进行曝光处理，得到曝光图像。目标对象可以是任何事物，包括但不限于行人，交通工具(汽车，卡车，自行车等等)，障碍物(垃圾桶， 树木，垃圾，交通灯等等)，动物(狗，猫等等)，甚至是某一事物的某个部分，比如人脸，车辆上的车牌等等。
在一个可能的实施例中，图像处理设备可以先对包含目标对象的事物进行预识别，在识别到包含目标对象的事物的情况下，再去识别目标对象，如此，可以先启动针对更大面积更好识别的包含目标对象的事物的粗识别模块，再在粗识别模块识别到后，启动精细化识别模块对目标事物进行识别。可以减少精细化识别模块的工作量，减少精细化识别模块的算力。
根据本公开实施例，能够通过亮度调节改进原本处在比较极端的环境下对目标进行曝光得到的曝光图像，避免极端光线环境下对目标对象的曝光异常，为曝光后的后续图像应用打下良好基础。
图3为可以应用根据本公开实施例的一种目标曝光方法的系统结构示意图；如图3所示，该系统结构中包括：图像获取设备301、网络302、控制终端303。为实现支撑一个示例性应用，图像获取设备301和控制终端303通过网络302建立通信连接，图像获取设备301通过网络302向控制终端303上报待曝光图像，控制终端303响应于待曝光图像，并对待曝光图像进行亮度识别，确定待曝光图像上亮度异常区域；其次，对亮度异常区域进行亮度调节，确定待识别图像；再次，响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。最后，控制终端303将曝光图像上传至网络302，并通过网络302发送给图像获取设备301。从而可以实现通过亮度调节改进原本处在比较极端的环境下得到的图像的异常亮度区域，避免极端光线环境下对目标对象的曝光异常，为曝光后的后续图像应用打下良好基础。
作为示例控制终端303可以包括具有视觉信息处理能力的视觉处理设备或远程服务器。网络302可以采用有线或无线连接方式。其中，当控制终端303为视觉处理设备时，图像采集设备301可以通过有线连接的方式与视觉处理设备通信连接，例如通过总线进行数据通信；当控制终端303为远程服务器时，图像获取设备301可以通过无线网络与远程服务器进行数据交互。
或者，在一些场景中，图像获取设备301可以是带有视频采集模组的视觉处理设备，可以是带有摄像头的主机。这时，本公开实施例的目标对象的曝光方法可以由图像采集设备301执行，上述系统架构可以不包含网络302和控制终端303。
图4示出根据本公开实施例的一种目标对象曝光方法的流程图，如图4所示，方法包括：
S401：对待识别图像进行预设对象识别，预设对象包含有目标对象；确定是否识别出预设对象。若识别出预设对象，转至步骤S402；否则，转至步骤S405。
在一个可选的实施例中，预设对象包括人形，图像处理设备可以利用内置在设备中的人形识别网络对待识别图像进行人形识别。
可选的，人形识别网络可以包括但不限于采用卷积神经网络、循环神经网络或递归神经网络等深度学习网络。以卷积神经网络为例，可以获取大量的训练数据集合，每个训练数据集合中包括训练图像，以及训练图像上标注好的人形，然后，基于大量的训练数据集合对卷积神经网络进行人形识别训练，在训练中调整该卷积神经网络的参数至卷积神经网络输出的人形与标注好的人形相匹配，得到图关联识别网络。
S402：在识别出预设对象的情况下，确定出预设对象所在的待识别区域。
S403：对待识别区域进行目标对象识别；确定是否识别出目标对象。若识别出目标对象，转至步骤S404；否则，转至步骤S405。
基于上述预设对象是人形继续阐述，在一个可选的实施例中，目标对象包括人脸，图像处理设备可以利用内置在设备中的人脸识别网络对待识别区域进行人脸识别。
可选的，人脸识别网络可以包括但不限于采用卷积神经网络、循环神经网络或递归神经网络等深度学习网络。以卷积神经网络为例，可以获取大量的训练数据集合，每个训练数据集合中包括人形，以及人形上标注好的人脸，然后，基于大量的训练数据集合对卷积神经网络进行人脸识别训练，在训练中调整该卷积神经网络的参数至卷积神经网络输出的人脸与标注好的人脸相匹配，得到图关联识别网络。
其中，本公开实施例中的训练数据集合中的训练数据可以存储在某个存储区域，该存储区域可以是一个区块链。其中，区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串 使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层。
S404：在识别出目标对象的情况下，对目标对象进行曝光处理，得到曝光图像。
S405：结束流程。
一种可选的实施方式中，若上述步骤S403中对待识别区域进行目标对象识别时，没有识别出目标对象，则可能是因为上文中仅仅根据第一亮度调节参数或者第二亮度调节参数这一次亮度调节并没有对待识别区域的亮度调节至比较有利于识别出人脸的情况，因此，还可以对图像进行多个亮度调节。
图5示出根据本公开实施例的一种目标对象曝光方法的流程图，如图5所示，方法包括：
S501：在未识别出目标对象的情况下，对待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像。
在一个可选的实施例中，步骤S501可以是在对待识别图像进行预设对象识别，并且在识别出预设对象的情况下，确定出该预设对象所在的待识别区域，进而可以对该待识别区域进行目标对象识别的前提下实施的步骤。
S502：对多张调节后的待识别图像上的待识别区域进行目标对象识别；确定在多张调节后的待识别区域中是否识别出目标对象，转至步骤S503；否则，转至步骤S504。
可选的，在多张调节后的待识别区域中只要存在一个待识别区域中识别出目标对象，可以转至步骤S503，对该调节后的待识别图像的目标对象进行曝光处理。
S503：在识别出目标对象的情况下，对存在目标对象的调节后的待识别图像上的目标对象进行曝光处理，得到曝光图像。
S504：结束流程。
上述步骤S501至步骤S504的实施例示例了一种得到多张调节后的待识别图像后，对多张调节后的待识别图像进行识别的方案，然而实际操作过程中，一次性对待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像可能是对硬件资源的浪费，为了减少资源浪费，可以通过减少得到调节后的待识别图像的数量来实现。
在一个可选的实施方式中，在未识别出目标对象的情况下，可以确定待识别图像的亮度，比如亮度为A。在亮度A大于第一亮度的情况下，根据第一亮度间隔数值(-1)将待识别图像调暗，得到调暗后的待识别图像(亮度为A-1)，对调暗后的待识别图像上的待识别区域进行目标对象识别，在未识别出目标对象的情况下，根据第一亮度间隔数值将调暗后的待识别图像调暗，得到当前的调暗后的待识别图像(亮度为A-2)，对当前的调暗后的待识别图像上的待识别区域进行目标对象识别，以此类推，直至识别出目标对象，对能够识别出目标对象的调暗后的待识别图像上的目标对象进行曝光处理，得到曝光图像。
在另一个可选的实施方式中，在未识别出目标对象的情况下，可以确定待识别图像的亮度，比如亮度为B；在亮度小于第二亮度的情况下，根据第二亮度间隔数值(+1)将待识别图像调亮，得到调亮后的待识别(图像亮度为B+1)。对调亮后的待识别图像上的待识别区域进行目标对象识别，在未识别出目标对象的情况下，根据第二亮度间隔数值将调亮后的待识别图像调亮，得到当前的调亮后的待识别图像(亮度为B+2)，对当前的调亮后的待识别图像上的待识别区域进行目标对象识别，以此类推，直至识别出目标对象，对能够识别出目标对象的调亮后的待识别图像上的目标对象进行曝光处理，得到曝光图像。
图6示出根据本公开实施例的一种目标对象曝光方法的流程图，如图6所示，方法包括：
S601：对待识别图像进行预设对象识别，若未识别出预设对象，转至步骤S602。
S602：对待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像。
本公开实施例中，如果存在没有识别出预设对象的情况，则可能是由于亮度造成的疏忽，因此，可以直接调节亮度，得到多张调节后的待识别图像。
S603：对多张调节后的待识别图像进行目标对象识别，判断是否识别出目标对象。
若识别出目标对象，转至步骤S604；否则，转至步骤S605结束流程。
S604：对存在目标对象的调节后的待识别图像上的目标对象进行曝光处理，得到曝光图像。
如此，可以减轻算法压力，不会在没有检测出预设对象(比如人形)的情况下，直接检测目标对象(比如人脸)。
S605：结束流程。
在另一个可选的实施例中，检测不出预设对象(人形)的原因并不是亮度，而可能是人形的大部分被物体挡住了，比如说某个人的身子躲在一棵大树下，但是人脸是可见的，当对人形进行识别时，由于是对人的整体轮廓进行检测，因此可能导致识别不出来的结果。该种情况下，若未识别出预设对象，可以直接进行目标对象识别，若识别出目标对象，对该待识别图像上的目标对象进行曝光处理，得到曝光图像。
在一个可选的实施例中，在获取待曝光图像之后，图像处理设备在对待曝光图像进行亮度识别，可以确定待曝光图像上的亮度非异常区域，响应于在亮度非异常区域中确定出目标对象，对目标对象进行曝光处理，得到曝光图像。
图7示出根据本公开实施例的一种目标对象曝光装置的框图，如图7所示，所述目标对象曝光装置包括：
图像获取模701，配置为获取待曝光图像；
区域确定模块702，配置为对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度异常区域；
亮度调节模块703，配置为对所述亮度异常区域进行亮度调节，得到待识别图像；
图像曝光模块704，配置为响应于在所述对待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，所述图像曝光模块包括识别子模块，识别区域确定子模块，处理子模块；
所述识别子模块，配置为对所述待识别图像进行预设对象识别，预设对象包含有目标对象；识别区域子确定模块，配置为在识别出所述预设对象的情况下，确定出所述预设对象所在的待识别区域；所述识别子模块，配置为对所述待识别区域进行目标对象识别；处理子模块，配置为在识别出所述目标对象的情况下，对所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，图像曝光模块还包括调节子模块，
所述调节子模块，配置为在未识别出所述目标对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；所述识别子模块，配置为对所述多张调节后的待识别图像上的待识别区域进行目标对象识别；所述处理子模块，配置为在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
在一些可能的实施方式中，所述图像曝光模块还包括亮度确定子模块和亮度调节子模块：
所述亮度确定子模块，配置为在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；所述亮度调节子模块，配置为在所述亮度大于第一亮度的情况下，根据第一亮度间隔数值将所述待识别图像调暗，得到调暗后的待识别图像；识别子模块，配置为对所述调暗后的待识别图像上的所述待识别区域进行所述目标对象识别；图像曝光子模块，配置为在未识别出所述目标对象的情况下，根据所述第一亮度间隔数值将所述调暗后的待识别图像调暗，得到当前的调暗后的待识别图像，对所述当前的调暗后的待识别图像上的所述待识别区域进行所述目标对象识别，直至识别出所述目标对象，对所述调暗后的待识别图像上的所述目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，图像曝光模块还包括：
亮度确定子模块，配置为在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；亮度调节子模块，配置为在所述亮度小于第二亮度的情况下，根据第二亮度间隔数值将所述待识别图像调亮，得到调亮后的待识别图像；识别子模块，配置为对所述调亮后的待识别图像上的所述待识别区域进行所述目标对象识别；图像曝光子模块，配置为在未识别出所述目标对象的情况下，根据所述第二亮度间隔数值将所述调亮后的待识别图像调亮，得到当前的调亮后的待识别图像，对所述当前的调亮后的待识别图像上的所述待识别区域进行所述目标对象识别，直至识别出所述目标对象，对所述调亮后的待识别图像上的所述目标对象进行曝光处理，得到 曝光图像。
在一些可能的实施方式中，
识别子模块，配置为对所述待识别图像进行预设对象识别；亮度调节子模块，配置为在未识别出所述预设对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；识别子模块，配置为对所述多张调节后的待识别图像进行所述目标对象识别；图像曝光子模块，配置为在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到曝光图像。
在一些可能的实施方式中，该目标对象包括人脸；预设对象包括人形；
所述识别模块，配置为通过人形识别网络对所述待识别图像进行人形识别；还配置为通过所述人脸识别网络对所述待识别区域进行人脸识别。
在一些可能的实施方式中，所述亮度异常区域包括第一亮度异常区域；
所述亮度调节模块，配置为基于第一亮度调节参数对所述第一亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第一亮度异常区域的亮度低于所述待曝光图像上的第一亮度异常区域的亮度。
在一些可能的实施方式中，所述亮度异常区域包括第二亮度异常区域；
所述亮度调节模块，配置为基于第二亮度调节参数对所述第二亮度异常区域进行亮度调节，得到所述待识别图像；其中，所述待识别图像中第二亮度异常区域的亮度高于所述待曝光图像上的第二亮度异常区域的亮度。
在一些可能的实施方式中，所述区域确定模块，还配置为对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度非异常区域；所述图像曝光模块，还配置为响应于在所述亮度非异常区域中确定出所述目标对象，对所述目标对象进行曝光处理，得到所述曝光图像。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，所述计算机可读存储介质中存储有至少一条指令或至少一段程序，所述至少一条指令或至少一段程序由处理器加载并执行时实现上述方法。计算机可读存储介质可以是非易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为上述方法。
电子设备可以被提供为终端、服务器或其它形态的设备。
本公开实施例还提供一种计算机程序，所述计算机程序包括计算机可读代码，在所述计算机可读代码在电子设备中运行的情况下，所述电子设备的处理器执行如上所述任一实施例的目标对象曝光方法。
本公开实施例提供另一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行本公开的目标对象曝光方法。
其中，该计算机程序产品可以通过硬件、软件或其结合的方式实现。在一些实施例中，所述计算机程序产品可以体现为计算机存储介质，在另一些实施例中，计算机程序产品可以体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
图8示出根据本公开实施例的一种电子设备的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图8，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例 包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图9示出根据本公开实施例的另一种电子设备的框图。例如，电子设备900可以被提供为一服务器。参照图9，电子设备900包括处理组件922，其进一步包括一个或多个处理器，以及由存储器932所代表的存储器资源，用于存储可由处理组件922的执行的指令，例如应用程序。存储器932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件922被配置为执行指令，以执行上述方法。
电子设备900还可以包括一个电源组件926被配置为执行电子设备900的电源管理，一个有线或无线网络接口950被配置为将电子设备900连接到网络，和一个输入输出(I/O)接口958。电子设备800可以操作基于存储在存储器932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器932，上述计算机程序指令可由电子设备900的处理组件922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是但不限于电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实 现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。
工业实用性
本公开实施例提供一种目标对象曝光方法、装置、存储介质、设备及程序，该方法包括：获取待曝光图像；对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度异常区域；对所述亮度异常区域进行亮度调节，得到待识别图像；响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。

Claims (14)

  1. 一种目标对象曝光方法，所述方法由电子设备执行，所述方法包括：
    获取待曝光图像；
    对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度异常区域；
    对所述亮度异常区域进行亮度调节，得到待识别图像；
    响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。
  2. 根据权利要求1所述的方法，其中，所述响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像，包括：
    对所述待识别图像进行预设对象识别，所述预设对象包含有所述目标对象；
    在识别出所述预设对象的情况下，确定出所述预设对象所在的待识别区域；
    对所述待识别区域进行所述目标对象识别；
    在识别出所述目标对象的情况下，对所述目标对象进行曝光处理，得到所述曝光图像。
  3. 根据权利要求2所述的方法，其中，所述对所述待识别区域进行所述目标对象识别之后，所述方法还包括：
    在未识别出所述目标对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；
    对所述多张调节后的待识别图像上的所述待识别区域，进行所述目标对象识别；
    在识别出所述目标对象的情况下，对存在所述目标对象的调节后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
  4. 根据权利要求2所述的方法，其中，在所述对所述待识别区域进行所述目标对象识别之后，所述方法还包括：
    在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；
    在所述亮度大于第一亮度的情况下，根据第一亮度间隔数值将所述待识别图像调暗，得到调暗后的待识别图像；
    对所述调暗后的待识别图像上的所述待识别区域，进行所述目标对象识别；
    在未识别出所述目标对象的情况下，根据所述第一亮度间隔数值将所述调暗后的待识别图像调暗，得到当前的调暗后的待识别图像；
    对所述当前的调暗后的待识别图像上的所述待识别区域，进行所述目标对象识别，直至识别出所述目标对象；
    对所述调暗后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
  5. 根据权利要求2所述的方法，其中，在所述对所述待识别区域进行所述目标对象识别之后，所述方法还包括：
    在未识别出所述目标对象的情况下，确定所述待识别图像的亮度；
    在所述亮度小于第二亮度的情况下，根据第二亮度间隔数值将所述待识别图像调亮，得到调亮后的待识别图像；
    对所述调亮后的待识别图像上的所述待识别区域，进行所述目标对象识别；
    在未识别出所述目标对象的情况下，根据所述第二亮度间隔数值将所述调亮后的待识别图像调亮，得到当前的调亮后的待识别图像；
    对所述当前的调亮后的待识别图像上的所述待识别区域，进行所述目标对象识别，直至识别出所述目标对象；
    对所述调亮后的待识别图像上的所述目标对象进行曝光处理，得到所述曝光图像。
  6. 根据权利要求1所述的方法，其中，所述响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像，包括：
    对所述待识别图像进行预设对象识别；
    在未识别出所述预设对象的情况下，对所述待识别图像进行多个亮度对应的亮度调节，得到多张调节后的待识别图像；
    对所述多张调节后的待识别图像进行所述目标对象识别；
    在识别出所述目标对象的情况下，对所述目标对象进行曝光处理，得到所述曝光图像。
  7. 根据权利要求2至6任一所述的方法，其中,所述目标对象包括人脸；所述预设对象包括人形；
    所述对所述待识别图像进行预设对象识别，包括：
    通过人形识别网络对所述待识别图像进行所述人形识别；
    所述对所述待识别区域进行所述目标对象识别，包括：
    通过所述人脸识别网络对所述待识别区域进行所述人脸识别。
  8. 根据权利要求1至7任一项所述的方法，其中，所述亮度异常区域包括第一亮度异常区域；所述对所述亮度异常区域进行亮度调节，得到待识别图像，包括：
    基于第一亮度调节参数对所述第一亮度异常区域进行亮度调节，得到待识别图像；
    其中，所述待识别图像中所述第一亮度异常区域的亮度低于所述待曝光图像上的第一亮度异常区域的亮度。
  9. 根据权利要求1至8任一项所述的方法，其中，所述亮度异常区域包括第二亮度异常区域；所述对所述亮度异常区域进行亮度调节，得到待识别图像，包括：
    基于第二亮度调节参数对所述第二亮度异常区域进行亮度调节，得到待识别图像；
    其中，所述待识别图像中所述第二亮度异常区域的亮度高于所述待曝光图像上的第二亮度异常区域的亮度。
  10. 根据权利要求1所述的方法，其中，在所述获取待曝光图像之后，所述方法还包括：
    对所述待曝光图像进行所述亮度识别，确定所述待曝光图像上的亮度非异常区域；
    响应于在所述亮度非异常区域中确定出所述目标对象，对所述目标对象进行曝光处理，得到所述曝光图像。
  11. 一种目标对象曝光装置，包括：
    图像获取模块，配置为获取待曝光图像；
    区域确定模块，配置为对所述待曝光图像进行亮度识别，确定所述待曝光图像上的亮度异常区域；
    亮度调节模块，配置为对所述亮度异常区域进行亮度调节，得到待识别图像；
    图像曝光模块，配置为响应于在所述待识别图像中识别出目标对象，对所述目标对象进行曝光处理，得到曝光图像。
  12. 一种计算机可读存储介质，所述计算机可读存储介质中存储有至少一条指令或至少一段程序，所述至少一条指令或至少一段程序由处理器加载并执行以实现如权利要求1至10中任一项所述的一种目标对象曝光方法。
  13. 一种电子设备，包括至少一个处理器，以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述至少一个处理器通过执行所述存储器存储的指令实现如权利要求1至10中任一项所述的一种目标对象曝光方法。
  14. 一种计算机程序，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备的处理器执行用于实现权利要求1至10任一项所述的目标对象曝光方法。
PCT/CN2021/110240 2021-01-29 2021-08-03 目标对象曝光方法、装置、存储介质、设备及程序 WO2022160638A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110127188.6 2021-01-29
CN202110127188.6A CN112819714A (zh) 2021-01-29 2021-01-29 目标对象曝光方法、装置、存储介质及设备

Publications (1)

Publication Number Publication Date
WO2022160638A1 true WO2022160638A1 (zh) 2022-08-04

Family

ID=75860240

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/110240 WO2022160638A1 (zh) 2021-01-29 2021-08-03 目标对象曝光方法、装置、存储介质、设备及程序

Country Status (3)

Country Link
CN (1) CN112819714A (zh)
TW (1) TW202230277A (zh)
WO (1) WO2022160638A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220156485A1 (en) * 2020-11-14 2022-05-19 Facense Ltd. Robust photosensor-based facial expression detector

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112819714A (zh) * 2021-01-29 2021-05-18 深圳市商汤科技有限公司 目标对象曝光方法、装置、存储介质及设备
CN115278099A (zh) * 2022-06-29 2022-11-01 广东小天才科技有限公司 一种补光灯控制方法、终端设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106682620A (zh) * 2016-12-28 2017-05-17 北京旷视科技有限公司 人脸图像采集方法及装置
CN107277356A (zh) * 2017-07-10 2017-10-20 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置
WO2019024717A1 (zh) * 2017-07-29 2019-02-07 Oppo广东移动通信有限公司 防伪处理方法及相关产品
CN112819714A (zh) * 2021-01-29 2021-05-18 深圳市商汤科技有限公司 目标对象曝光方法、装置、存储介质及设备

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5742722B2 (ja) * 2009-11-05 2015-07-01 日本電気株式会社 画像目標識別装置、画像目標識別方法、画像目標識別プログラム
CN108377345B (zh) * 2018-04-11 2020-04-03 浙江大华技术股份有限公司 一种曝光参数值确定方法、装置、多目摄像机及存储介质
CN108319940A (zh) * 2018-04-12 2018-07-24 Oppo广东移动通信有限公司 人脸识别处理方法、装置、设备及存储介质
CN109829859B (zh) * 2018-12-05 2024-05-24 平安科技（深圳）有限公司 图像处理方法及终端设备
CN111698432A (zh) * 2019-03-12 2020-09-22 北京猎户星空科技有限公司 一种参数控制方法、装置、设备及介质
CN111340016A (zh) * 2020-02-25 2020-06-26 浙江大华技术股份有限公司 图像曝光方法和装置、存储介质及电子装置
CN111444884A (zh) * 2020-04-22 2020-07-24 万翼科技有限公司 图像中的构件识别方法、设备及计算机可读存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106682620A (zh) * 2016-12-28 2017-05-17 北京旷视科技有限公司 人脸图像采集方法及装置
CN107277356A (zh) * 2017-07-10 2017-10-20 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置
WO2019024717A1 (zh) * 2017-07-29 2019-02-07 Oppo广东移动通信有限公司 防伪处理方法及相关产品
CN112819714A (zh) * 2021-01-29 2021-05-18 深圳市商汤科技有限公司 目标对象曝光方法、装置、存储介质及设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220156485A1 (en) * 2020-11-14 2022-05-19 Facense Ltd. Robust photosensor-based facial expression detector
US11604511B2 (en) * 2020-11-14 2023-03-14 Facense Ltd. Robust photosensor-based facial expression detector
US20230185374A1 (en) * 2020-11-14 2023-06-15 Facense Ltd. Using a camera to compensate for sensor-shift in a photosensor-based facial expression detector
US11983317B2 (en) * 2020-11-14 2024-05-14 Facense Ltd. Using a camera to compensate for sensor-shift in a photosensor-based facial expression detector

Also Published As

Publication number Publication date
CN112819714A (zh) 2021-05-18
TW202230277A (zh) 2022-08-01

Similar Documents

Publication Publication Date Title
CN107205125B (zh) 一种图像处理方法、装置、终端及计算机可读存储介质
WO2022160638A1 (zh) 目标对象曝光方法、装置、存储介质、设备及程序
WO2021017561A1 (zh) 人脸识别方法及装置、电子设备和存储介质
CN111462268B (zh) 图像重建方法及装置、电子设备和存储介质
KR101712529B1 (ko) 플래시 제어 방법, 장치, 단말기, 프로그램 및 컴퓨터가 판독가능한 기록매체
CN108764069B (zh) 活体检测方法及装置
US20220076006A1 (en) Method and device for image processing, electronic device and storage medium
CN110796988B (zh) 背光调节方法及装置
EP3306441A1 (en) Temperature control method and apparatus
CN108234873A (zh) 一种获取图像的方法和装置
CN109165738B (zh) 神经网络模型的优化方法及装置、电子设备和存储介质
CN112714205B (zh) 环境光照强度确定方法、装置及存储介质
EP3379524A1 (en) View angle switching method and apparatus
CN112016344A (zh) 信号指示灯的状态检测方法及装置、驾驶控制方法及装置
EP3629318B1 (en) Method and apparatus for compensating operating parameter of display circuit
CN113191198B (zh) 指纹识别方法、装置、移动终端及存储介质
CN108597456B (zh) 背光亮度调节方法及装置
CN109255839B (zh) 场景调整方法及装置
CN115839764A (zh) 光强的确定方法及装置、电子设备、存储介质
CN114187874B (zh) 亮度调节方法、装置及存储介质
CN112702514B (zh) 图像获取方法、装置、设备及存储介质
CN115601316A (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN113727034A (zh) 补光控制方法、电子设备和存储介质
CN113099101B (zh) 摄像参数调节方法、装置及电子设备
CN106170042A (zh) 补光方法及装置、电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21922234

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM1205A DATED 15.11.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21922234

Country of ref document: EP

Kind code of ref document: A1