WO2022174539A1 - 自行走设备的摄像曝光方法和装置 - Google Patents

自行走设备的摄像曝光方法和装置 Download PDF

Info

Publication number
WO2022174539A1
WO2022174539A1 PCT/CN2021/100719 CN2021100719W WO2022174539A1 WO 2022174539 A1 WO2022174539 A1 WO 2022174539A1 CN 2021100719 W CN2021100719 W CN 2021100719W WO 2022174539 A1 WO2022174539 A1 WO 2022174539A1
Authority
WO
WIPO (PCT)
Prior art keywords
exposure
brightness
image
self
partition
Prior art date
Application number
PCT/CN2021/100719
Other languages
English (en)
French (fr)
Inventor
吴震
陈佳搏
于炀
Original Assignee
北京石头创新科技有限公司
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 北京石头创新科技有限公司 filed Critical 北京石头创新科技有限公司
Priority to EP21926255.7A priority Critical patent/EP4297395A1/en
Publication of WO2022174539A1 publication Critical patent/WO2022174539A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/71—Circuitry for evaluating the brightness variation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time

Definitions

  • the invention relates to photographic exposure technology, in particular to a photographic exposure method and device for self-propelled equipment.
  • the technical problem to be solved by the present invention is to provide a camera exposure method and device for self-propelled equipment, so that in the case of high reflection along the wall and the ground, the automatic exposure (AE: Automatic Exposure) under the fill light can still meet the requirements of better object recognition requirements.
  • AE Automatic Exposure
  • the present invention provides a camera exposure method for self-propelled equipment.
  • the camera exposure method of the self-propelled equipment includes: detecting the brightness of the region of interest in the collected image according to a preset rule; when it is detected that the brightness information does not meet the preset condition, adjusting the current exposure parameter; according to the exposure parameter Partial exposure is performed during image acquisition, and the exposed area includes at least the region of interest.
  • adjusting the current exposure parameters includes: comparing the brightness information with the target brightness; if the brightness information is compared with the target brightness; If the brightness information is less than the target brightness, the exposure parameter is increased; if the brightness information is greater than the target brightness, the exposure parameter is decreased.
  • the detecting the brightness of the region of interest in the collected image includes: partitioning the region of interest in the collected image, and obtaining the brightness of each partition. value; the brightness information of each partition is obtained by weighting and averaging the brightness value of each partition and the corresponding weight of each partition.
  • partitioning the region of interest in the collected image, and obtaining the brightness value of each partition including: after partitioning the region of interest in the collected image, for For each partition, the partition is divided into a plurality of image blocks, and the average brightness of each image block is obtained respectively; the brightness value of each partition is obtained by weighting the average brightness of each image block and the corresponding weight of each image block.
  • the area of interest in the image includes a reflective surface area and a space area
  • the partitioning of the area of interest in the collected image includes: dividing the area of interest in the image.
  • the area is divided into a reflective surface area and a space area; wherein, the space area is located in the middle of the area of interest, and the reflective surface area is located on the left and right sides and/or below the space area.
  • the weight of the space area is greater than the weight of the reflective surface area.
  • the exposure parameters include exposure time and/or exposure gain.
  • the present invention provides a photographic exposure device for self-propelled equipment.
  • the self-propelled equipment includes an image acquisition device, and the camera exposure device includes: an image brightness detection unit for detecting the brightness of a region of interest in an image collected by the image acquisition device according to a preset rule; exposure parameter adjustment a unit for adjusting the current exposure parameters when it is detected that the brightness information does not meet the preset conditions; a local exposure unit for performing local exposure according to the exposure parameters in the process of collecting images, and the exposed area at least includes the Focus area.
  • the image brightness detection unit includes: a partition brightness value acquisition module for partitioning the region of interest in the collected image, and acquiring the brightness value of each partition;
  • the brightness information calculation module is used for obtaining the brightness information after the brightness value of each partition is weighted and averaged with the weight corresponding to each partition respectively.
  • the exposure parameter adjustment unit includes: a comparison module for comparing the brightness information with the target brightness; an exposure parameter increase module for when the When the brightness information is less than the target brightness, the exposure parameter is increased; the exposure parameter reduction module is used for reducing the exposure parameter when the brightness information is greater than the target brightness.
  • the present invention provides a computing device.
  • the computing device includes one or more processors, and a memory coupled to the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause The one or more processors perform the above-described method.
  • the present invention provides a machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the above method.
  • the camera exposure method and device for self-propelled equipment provided by the embodiments of the present invention enable the self-propelled equipment to work normally in an environment with insufficient light or darkness. So that in the case of high reflection along the wall and the ground, the automatic exposure (AE) under the fill light can still meet the needs of better object recognition.
  • FIG. 1 is a flowchart of a method for photographing exposure of self-propelled equipment according to an embodiment of the present invention
  • FIG. 2 is a flowchart of step S120 in FIG. 1 provided by an example of the present invention.
  • FIG. 3 is a schematic diagram of a region of interest in a collected image provided by an example of the present invention.
  • FIG. 4 is a schematic structural diagram of a camera exposure device of a self-propelled equipment provided by another embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of the image brightness detection unit in FIG. 4 provided by an example of the present invention.
  • FIG. 6 is a structural block diagram of a computing device for photographic exposure of a self-propelled device according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for photographing and exposing a self-propelled device according to an embodiment of the present invention.
  • the self-propelled device includes a fill light and an image acquisition device such as a camera.
  • the camera exposure method of the self-propelled device in this embodiment is applicable to the self-propelled device with a camera, and the field of view of the camera faces forward.
  • the light direction of the fill light is roughly the same as the direction of the camera's field of view.
  • the supplementary light of the self-propelled equipment may be an infrared light.
  • the self-propelled device is, for example, a small ground robot.
  • the purpose of this embodiment is to provide an automatic exposure (AE) method that meets the light-filling conditions for a small ground robot. In view of the fact that the light emitted by the small robot fill light near the ground is easy to be reflected by the ground and walls, the exposure area and weight selection in AE have been updated.
  • step S110 the brightness of the region of interest in the collected image is detected according to a preset rule.
  • the method of weighted average can be used to detect the brightness of the image collected by the camera.
  • FIG. 2 is a flowchart of step S110 in FIG. 1 provided by an example of the present invention.
  • step S110 may further include the following steps:
  • step S112 the region of interest in the collected image is partitioned, and the brightness value of each partition is acquired.
  • the region of interest in the collected image is partitioned, and for each partition, the partition can be divided into multiple image blocks, and the average brightness of each image block is obtained respectively;
  • the luminance value of each partition is obtained by weighted averaging of the luminance mean value of the block and the weight corresponding to each image block.
  • the brightness value of each partition is obtained by performing a weighted average of the brightness mean value of each image block and the weight corresponding to each image block.
  • the specific process of the weighted average may include: assuming that the number of valid image blocks in a certain partition is N, and the mean luminance values of each image block are I(x1, y1), ..., I(xN, yN), where x1, y1 , ..., xN, yN are the coordinates of each image block, assuming that M(x1, y1), ..., M(xN, yN) are the weight values corresponding to the image blocks x1, y1, ..., xN, yN, respectively, the partition
  • the image brightness value of each image block is obtained separately, and weighted according to the corresponding weight value to determine the final exposure parameter.
  • the numbers in Figure 3 are the weight values corresponding to each image block.
  • the brightness information of each partition is obtained by weighting and averaging the brightness value of each partition and the weight corresponding to each partition respectively.
  • the region of interest in the image may include a reflective surface area and a space area
  • the area of interest when partitioning the area of interest in the captured image, the area of interest may be partitioned according to the reflective surface area and the space area. Further, it can also include dividing the reflective surface area into a floor area and a wall area. Wherein, the space area is located in the middle of the area of interest, and the reflective surface area is located on the left and right sides and/or below the space area. The weight of the space area is greater than the weight of the reflective surface area.
  • the weight value corresponding to the space area is greater than the weight value corresponding to the reflective surface area.
  • the area of interest in the image can be the area below the image and the raised areas on the left and right sides, as shown in Figure 3.
  • the first area 310 is the area on the ground, and its weight is higher; the second area 320 is the ground area, and the weight is lower to prevent reflection; the third area 330 is the left and right wall area, and the weight is lower .
  • Other areas are long-distance areas. The reason why the weight of the first area 310 is selected to be greater than the weight of the second area 320 and the weight of the third area 330 is that the ground and walls reflect light.
  • the preset rule here can be periodic or continuous, that is, it can be detected once every time an image is taken.
  • step S120 when it is detected that the brightness information does not meet the preset condition, the current exposure parameter is adjusted.
  • automatic exposure AE, Automatic Exposure
  • the target brightness of the current scene is Lt
  • compare the brightness detection result L with the target brightness Lt if the brightness detection result L ⁇ Lt, increase the exposure parameter in the next exposure; if the brightness detection result L>Lt, Then reduce the exposure parameter in the next exposure.
  • step S130 local exposure is performed in the process of capturing an image according to the adjusted exposure parameters, and the exposed area includes at least the area of interest.
  • Whether it is in low illumination can be judged according to exposure gain and/or exposure time and image quality.
  • the local area automatic exposure (AE) method can be used to collect the image.
  • AE local area automatic exposure
  • the exposure parameters of the current frame are generally determined by the brightness of the previous frame or several frames of images. Specifically, the region of interest in the image of the previous frame or previous frames can be partitioned, and the brightness value of each partition can be obtained; the brightness value of each partition can be weighted and averaged with the weight corresponding to each partition to obtain the brightness information, The exposure parameter of the current frame is determined according to the brightness information, and local exposure is performed in the process of shooting the video according to the exposure parameter of the current frame.
  • the camera exposure method of the self-propelled device of this embodiment adjusts the weight of the ground, and compared with the method of averaging weights, the influence of reflection on the ground is avoided. For example, if the ground is overexposed, automatic exposure (AE) under fill light will be affected, resulting in insufficient exposure gain and/or time relative to the detection area, which may coincide with or be similar to the first area 310 .
  • AE automatic exposure
  • the camera exposure method of the self-propelled device adjusts the weight of the edge wall, so as to avoid the influence of overexposure due to the reflection of the wall along the wall. For example, if the wall is overexposed, the AE will be affected under fill light, resulting in insufficient exposure gain and/or time relative to the detection area, which may be coincident with or similar to the first area 310 .
  • the wall area should be raised a part to avoid the wall area being too small.
  • the detection area may be coincident with or similar to the first area 310 , and the distance between the front and rear of the detection area may range from 20 cm to 50 cm.
  • the camera exposure method of the self-propelled device enables AE to meet better object recognition requirements under the fill light in the case of high reflection along the wall and the ground.
  • FIG. 4 is a schematic structural diagram of a photographic exposure device of a self-propelled equipment according to another embodiment of the present invention.
  • the self-propelled device includes a camera.
  • the photographic exposure apparatus 400 of the self-propelled equipment provided in this embodiment includes an image brightness detection unit 410 , an exposure parameter adjustment unit 420 , and a local exposure unit 430 .
  • the image brightness detection unit 410 is configured to detect the brightness of the region of interest in the image captured by the image capturing device according to a preset rule.
  • the operation of the image brightness detection unit 410 may refer to the operation of step S110 described above with reference to FIG. 1 .
  • the exposure parameter adjustment unit 420 is configured to adjust the current exposure parameter when it is detected that the brightness information does not meet the preset condition; the operation of the exposure coefficient adjustment unit 420 may refer to the operation of step S120 described above with reference to FIG. 1 .
  • the partial exposure unit 430 is configured to perform partial exposure in the process of capturing images according to exposure parameters.
  • the operation of the partial exposure unit 430 may refer to the operation of step S130 described above with reference to FIG. 1 .
  • FIG. 5 is a schematic structural diagram of the image brightness detection unit in FIG. 4 according to an example of the present invention.
  • the image brightness detection unit 410 may include a partition brightness value acquisition module 412 and a brightness information calculation module 414 .
  • the partition brightness value obtaining module 412 is configured to partition the region of interest in the collected image, and obtain the brightness value of each partition.
  • the operation of the partition luminance value obtaining module 412 may refer to the operation of step S112 described above with reference to FIG. 2 .
  • the brightness information calculation module 414 is configured to obtain the brightness information by weighting and averaging the brightness values of each partition and the weights corresponding to the respective partitions.
  • the operation of the luminance information calculation module 414 may refer to the operation of step S114 described above with reference to FIG. 2 .
  • the exposure parameter adjustment unit 420 may include a comparison module, an exposure parameter increase module, and an exposure parameter decrease module.
  • the comparison module is used to compare the brightness information with the target brightness.
  • the exposure parameter increasing module is used to increase the exposure parameter when the brightness information is less than the target brightness.
  • the exposure parameter reduction module is used to reduce the exposure parameter when the brightness information is greater than the target brightness.
  • FIG. 6 is a structural block diagram of a computing device for photographic exposure of a self-propelled device according to an embodiment of the present invention.
  • computing device 600 may include at least one processor 610 , memory 620 , memory 630 , communication interface 640 , and internal bus 650 , and at least one processor 610 , memory 620 , memory 630 , and communication interface 640 via bus 650 connected.
  • the at least one processor 610 executes at least one computer-readable instruction (ie, the above-described elements implemented in software) stored or encoded in a computer-readable storage medium (ie, memory 620).
  • computer-executable instructions are stored in the memory 620, which, when executed, cause the at least one processor 610 to: detect the brightness of the region of interest in the captured image according to a preset rule; when the brightness information is detected When the preset conditions are not met, the current exposure parameters are adjusted; local exposure is performed in the process of capturing images according to the exposure parameters, and the exposed areas at least include the area of interest.
  • computing device 600 may include, but is not limited to, personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDA), handheld devices, messaging devices, wearable computing devices, consumer electronics, and the like.
  • PDA personal digital assistants
  • a program product eg, a non-transitory machine-readable medium
  • a non-transitory machine-readable medium may have instructions (ie, the above-described elements implemented in software) that, when executed by a machine, cause the machine to perform various embodiments of the present invention described above in connection with FIGS. 1-5 operations and functions.
  • a system or an apparatus equipped with a readable storage medium may be provided, on which software program codes for realizing the functions of any of the above-described embodiments are stored, and a computer or a computer of the system or apparatus may be provided.
  • the processor reads and executes the instructions stored in the readable storage medium.
  • the program code itself read from the readable medium can implement the functions of any one of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code constitute the present invention a part of.
  • Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (eg, CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tape, non- Volatile memory cards and ROMs.
  • the program code may be downloaded from a server computer or the cloud over a communications network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)

Abstract

一种自行走设备的摄像曝光方法和装置。该自行走设备的摄像曝光方法包括：根据预设规则对采集到的图像中关注区域的亮度进行检测；当检测到亮度信息不满足预设条件时，调整当前曝光参数；根据曝光参数在采集图像的过程中进行局部曝光。该自行走设备的摄像曝光装置包括：图像亮度检测单元，用于根据预设规则对图像采集装置采集到的图像中的关注区域的亮度进行检测；曝光参数调整单元，用于当检测到亮度信息不满足预设条件时，调整当前曝光参数；局部曝光单元，用于根据曝光参数在采集图像的过程中进行局部曝光。上述方法和装置使得自行走设备在光照不足或黑暗的环境也可正常工作；在沿墙、地面反光过曝的情况下，也可满足较好的物体识别需求。

Description

自行走设备的摄像曝光方法和装置
相关申请的交叉引用
本申请要求于2021年2月18日递交的中国专利申请第202110187659.2号的优先权，在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
技术领域
本发明涉及摄像曝光技术，尤其涉及一种自行走设备的摄像曝光方法和装置。
背景技术
现有的自行走设备例如扫地机在单独配置摄像头的情况下，在光照不足或者黑暗的环境下无法正常工作，进而影响用户体验。
发明内容
本发明要解决的技术问题是提供一种自行走设备的摄像曝光方法和装置，使得在沿墙、地面高反的情况下，补光灯下自动曝光(AE:Automatic Exposure)尚可满足较好的物体识别需求。
一方面，本发明提出一种自行走设备的摄像曝光方法。所述自行走设备的摄像曝光方法包括：根据预设规则对采集到的图像中关注区域的亮度进行检测；当检测到亮度信息不满足预设条件时，调整当前曝光参数；根据所述曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
可选地，对于所述自行走设备的摄像曝光方法，所述当检测到亮度信息不满足预设条件时，调整当前曝光参数，包括：将所述亮度信息与目标亮度作比较；如果所述亮度信息小于所述目标亮度，则增加曝光参数；如果所述亮度信息大于所述目标亮度，则减少曝光参数。
可选地，对于所述自行走设备的摄像曝光方法，所述对采集到的图像中的关注区域的亮度进行检测，包括：对采集到的图像中的关注区域进行分区，获取各个分区的亮度值；将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。
可选地，对于所述自行走设备的摄像曝光方法，对采集到的图像中的关注区域进行分区，获取各个分区的亮度值，包括：将采集到的图像中的关注区域进行分区之后，针对每一个分区，将该分区分为多个图像块，分别获取各个图像块的亮度平均值；将各个图像块的亮度均值与各个图像块对应的权值进行加权平均后得到各个分区的亮度值。
可选地，对于所述自行走设备的摄像曝光方法，所述图像中的关注区域包括反光面区域和空间区域，所述对采集到的图像中的关注区域进行分区，包括：将所述关注区域分为反光面区域和空间区域；其中，空间区域位于所述关注区域的中间位置，所述反光面区域 位于所述空间区域的左右两边和/或下方。
可选地，对于所述自行走设备的摄像曝光方法，所述空间区域的权值大于所述反光面区域的权值。
可选地，对于所述自行走设备的摄像曝光方法，所述曝光参数包括曝光时间和/或曝光增益。
另一方面，本发明提出一种自行走设备的摄像曝光装置。所述自行走设备包括图像采集装置，所述摄像曝光装置包括：图像亮度检测单元，用于根据预设规则对所述图像采集装置采集到的图像中的关注区域的亮度进行检测；曝光参数调整单元，用于当检测到亮度信息不满足预设条件时，调整当前曝光参数；局部曝光单元，用于根据所述曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
可选地，对于所述自行走设备的摄像曝光装置，所述图像亮度检测单元包括：分区亮度值获取模块，用于对采集到的图像中的关注区域进行分区，获取各个分区的亮度值；亮度信息计算模块，用于将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。
可选地，对于所述的自行走设备的摄像曝光装置，所述曝光参数调整单元包括：比较模块，用于将所述亮度信息与目标亮度作比较；曝光参数增加模块，用于当所述亮度信息小于所述目标亮度时，增加曝光参数；曝光参数减少模块，用于当所述亮度信息大于所述目标亮度时，减少曝光参数。
又一方面，本发明提出一种计算设备。所述计算设备包括：一个或多个处理器，以及与所述一个或多个处理器耦合的存储器，所述存储器存储指令，当所述指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行上述方法。
再一方面，本发明提出一种机器可读存储介质，所述机器可读存储介质存储有可执行指令，所述指令当被执行时使得所述机器执行上述方法。
与现有技术相比，本发明技术方案主要的优点如下：
本发明的实施例提供的自行走设备的摄像曝光方法和装置使自行走设备在光照不足或者黑暗的环境也可以正常工作。使得在沿墙、地面高反的情况下，补光灯下自动曝光(AE)尚可满足较好的物体识别需求。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本发明的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1为本发明一个实施例提供的自行走设备的摄像曝光方法的流程图；
图2为本发明一个示例提供的图1中步骤S120的流程图；
图3为本发明一个示例提供的采集到的图像中关注区域的示意图；
图4为本发明另一个实施例提供的自行走设备的摄像曝光装置的结构示意图；
图5为本发明一个示例提供的图4中图像亮度检测单元的结构示意图；
图6为根据本发明的实施例的用于自行走设备的摄像曝光的计算设备的结构框图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整地传达给本领域的技术人员。
图1为本发明一个实施例提供的自行走设备的摄像曝光方法的流程图。
在该实施例中，自行走设备包括补光灯和图像采集装置比如摄像头。本实施例的自行走设备的摄像曝光方法适用于带摄像头的自行走设备，摄像头视场朝前。补光灯的光线方向大致与摄像头的视场方向一致。自行走设备的补光灯可以为红外线灯。自行走设备例如为地面小机器人。本实施例旨在给出一种符合地面小机器人补光条件的自动曝光(AE)方法。针对近地面小机器人补光灯发出的光线易于被地面、墙面反射的特点，更新了AE中的曝光区域与权重选择。
如图1所示，在步骤S110，根据预设规则对采集到的图像中关注区域的亮度进行检测。对摄像头采集到的图像进行亮度检测可以采用加权平均的方法。图2为本发明一个示例提供的图1中步骤S110的流程图。
具体来说，步骤S110可以进一步包括以下步骤：
步骤S112，对采集到的图像中的关注区域进行分区，获取各个分区的亮度值。作为一种可选实施方式，对采集到的图像中的关注区域进行分区，并可以针对每一个分区，将该分区分为多个图像块，分别获取各个图像块的亮度平均值；将各个图像块的亮度均值与各个图像块对应的权值进行加权平均后得到各个分区的亮度值。
将分区进一步划分为多个图像块后，各个图像块的亮度均值与各个图像块对应的权值进行加权平均后得到各个分区的亮度值。加权平均的具体过程可以包括：假设某个分区的有效图像块的数量为N，各个图像块的亮度均值分别为I(x1,y1)、…、I(xN,yN)，其中，x1,y1、…、xN,yN分别为各图像块的坐标，假设M(x1,y1)、…、M(xN,yN)分别是图像块x1,y1、…、xN,yN对应的权重数值，该分区的亮度值为L＝[M(x1,y1)*I(x1,y1)+…+M(xN,yN)*I(xN,yN)]/N。自动曝光后，分别获取每一个图像块的图像亮度值，按照相应的权重数值进行加权，确定最后的曝光参数，权重数值越高则对最终曝光参数确定影响越大。图3中的数字为各个图像块对应的权重数值。
步骤S114，将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。因为图像中的关注区域可以包括反光面区域和空间区域，所以对采集到的图像中的关注区域进行分区时，可以将关注区域按照反光面区域和空间区域进行分区。进一步地，还 可以包括将反光面区域分区为地面区域和墙面区域。其中，空间区域位于关注区域的中间位置，反光面区域位于空间区域的左右两边和/或下方。空间区域的权值大于反光面区域的权值。
作为一种可选实施方式，空间区域对应的权重数值大于反光面区域对应的权重数值。考虑沿墙影响，避免过曝，图像中的关注区域可以为图像下方区域和左右两侧的高起区域，如图3所示。图3中，第一区域310为地面上区域，其权值较高；第二区域320为地面区域，为防止反光，权值较低；第三区域330为左右墙面区域，权值较低。其他区域为远距离区域。选择第一区域310的权值既大于第二区域320的权值又大于第三区域330的权值的原因是地面与墙面反光。
这里的预设规则可以是周期性的，或者持续的，即可以每拍一张图像检测一次。
在步骤S120，当检测到亮度信息不满足预设条件时，调整当前曝光参数。一般，自动曝光(AE，Automatic Exposure)是将曝光时间和曝光增益中至少一个参数作为曝光参数。
具体来说，假设当前场景的目标亮度为Lt，将亮度检测结果L与目标亮度Lt作比较；如果亮度检测结果L<Lt，则在下一次曝光中增加曝光参数；如果亮度检测结果L>Lt，则在下一次曝光中减少曝光参数。
在步骤S130，根据调整后的曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
可以根据曝光增益和/或曝光时间和图像质量，判断是否处于低照度，在判断出处于低照度的情况下，比如图片黑时，可以采用局部区域自动曝光(AE)方式采集图像。采用局部区域曝光即以局部区域为曝光参考区域，局部区域的大小可以按照预设选取，例如选取图3中带数字的区域。
对于视频，一般以前一帧或前几帧图像的亮度确定当前帧的曝光参数。具体来说，可以对前一帧或前几帧的图像中的关注区域进行分区，获取各个分区的亮度值；将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息，根据亮度信息确定当前帧的曝光参数，根据当前帧的曝光参数在拍摄视频的过程中进行局部曝光。
由上述实施例可见，该实施例的自行走设备的摄像曝光方法调整了地面的权重，相比平均权重的做法，避免了地面反光影响。举例而言，如果地面过曝，则补光下自动曝光(AE)将被影响，导致曝光增益和/或时间相对于检测区域不足，检测区域可以与第一区域310重合或近似。
本发明上述实施例的自行走设备的摄像曝光方法调整了边缘墙壁的权重，避免了沿墙时墙壁反光过曝影响。举例而言，如果墙面过曝，则补光下AE将被影响，导致曝光增益和/或时间相对于检测区域不足，检测区域可以与第一区域310重合或近似。
由于三部分同时参与自动曝光(AE)，为平衡墙面区域、地面区域大小，墙面区域对应高起一部分，避免墙面区域过小。
检测区域可以与第一区域310重合或近似，检测区域的前后距离范围可以为20～50cm。
本发明实施例的自行走设备的摄像曝光方法使得在沿墙、地面高反的情况下，补光灯下AE尚可满足较好的物体识别需求。
图4为本发明另一个实施例提供的自行走设备的摄像曝光装置的结构示意图。在该实施例中，自行走设备包括摄像头。如图4所示，该实施例提供的自行走设备的摄像曝光装置400包括图像亮度检测单元410、曝光参数调整单元420、以及局部曝光单元430。
图像亮度检测单元410用于根据预设规则对图像采集装置采集到的图像中的关注区域的亮度进行检测。图像亮度检测单元410的操作可以参照上面参考图1描述的步骤S110的操作。
曝光参数调整单元420用于当检测到亮度信息不满足预设条件时，调整当前曝光参数；曝光系数调整单元420的操作可以参照上面参考图1描述的步骤S120的操作。
局部曝光单元430用于根据曝光参数在采集图像的过程中进行局部曝光。局部曝光单元430的操作可以参照上面参考图1描述的步骤S130的操作。
图5为本发明一个示例提供的图4中图像亮度检测单元的结构示意图。如图5所示，图像亮度检测单元410可以包括分区亮度值获取模块412和亮度信息计算模块414。
分区亮度值获取模块412用于对采集到的图像中的关注区域进行分区，获取各个分区的亮度值。分区亮度值获取模块412的操作可以参照上面参考图2描述的步骤S112的操作。
亮度信息计算模块414用于将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。亮度信息计算模块414的操作可以参照上面参考图2描述的步骤S114的操作。
进一步来说，曝光参数调整单元420可以包括比较模块、曝光参数增加模块、以及曝光参数减少模块。其中，比较模块用于将亮度信息与目标亮度作比较。曝光参数增加模块用于当亮度信息小于目标亮度时，增加曝光参数。曝光参数减少模块用于当亮度信息大于目标亮度时，减少曝光参数。
图6为根据本发明的实施例的用于自行走设备的摄像曝光的计算设备的结构框图。
如图6所示，计算设备600可以包括至少一个处理器610、存储器620、内存630、通信接口640以及内部总线650，并且至少一个处理器610、存储器620、内存630和通信接口640经由总线650连接在一起。该至少一个处理器610执行在计算机可读存储介质(即，存储器620)中存储或编码的至少一个计算机可读指令(即，上述以软件形式实现的元素)。
在一个实施例中，在存储器620中存储有计算机可执行指令，其当执行时使得至少一个处理器610：根据预设规则对采集到的图像中关注区域的亮度进行检测；当检测到亮度信息不满足预设条件时，调整当前曝光参数；根据所述曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
应该理解的是，在存储器620中存储的计算机可执行指令当执行时使得至少一个处理器610进行本公开的各个实施例中以上结合图1-5描述的各种操作和功能。
在本公开中，计算设备600可以包括但不限于：个人计算机、服务器计算机、工作站、桌面型计算机、膝上型计算机、笔记本计算机、移动计算设备、智能电话、平板计算机、蜂窝电话、个人数字助理(PDA)、手持装置、消息收发设备、可佩戴计算设备、消费电子设备等等。
根据一个实施例，提供了一种例如非暂时性机器可读介质的程序产品。非暂时性机器可读介质可以具有指令(即，上述以软件形式实现的元素)，该指令当被机器执行时，使得机器执行本发明的各个实施例中以上结合图1-5描述的各种操作和功能。
具体地，可以提供配有可读存储介质的系统或者装置，在该可读存储介质上存储着实现上述实施例中任一实施例的功能的软件程序代码，且使该系统或者装置的计算机或处理器读出并执行存储在该可读存储介质中的指令。
在这种情况下，从可读介质读取的程序代码本身可实现上述实施例中任何一项实施例的功能，因此机器可读代码和存储机器可读代码的可读存储介质构成了本发明的一部分。
可读存储介质的实施例包括软盘、硬盘、磁光盘、光盘(如CD-ROM、CD-R、CD-RW、DVD-ROM、DVD-RAM、DVD-RW、DVD-RW)、磁带、非易失性存储卡和ROM。可选择地，可以由通信网络从服务器计算机上或云上下载程序代码。
以上所述仅为本发明的实施例，并非因此限制本发明的权利要求保护范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明权利要求的保护范围内。

Claims (12)

  1. 一种自行走设备的摄像曝光方法，其特征在于，包括：
    根据预设规则对采集到的图像中关注区域的亮度进行检测；
    当检测到亮度信息不满足预设条件时，调整当前曝光参数；
    根据所述曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
  2. 如权利要求1所述的自行走设备的摄像曝光方法，其特征在于，所述当检测到亮度信息不满足预设条件时，调整当前曝光参数，包括：
    将所述亮度信息与目标亮度作比较；
    如果所述亮度信息小于所述目标亮度，则增加曝光参数；
    如果所述亮度信息大于所述目标亮度，则减少曝光参数。
  3. 如权利要求1所述的自行走设备的摄像曝光方法，其特征在于，所述对采集到的图像中的关注区域的亮度进行检测，包括：
    对采集到的图像中的关注区域进行分区，获取各个分区的亮度值；
    将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。
  4. 如权利要求3所述的自行走设备的摄像曝光方法，其特征在于，对采集到的图像中的关注区域进行分区，获取各个分区的亮度值，包括：
    将采集到的图像中的关注区域进行分区，并针对每一个分区，将该分区分为多个图像块，分别获取各个图像块的亮度平均值；
    将各个图像块的亮度均值与各个图像块对应的权值进行加权平均后得到各个分区的亮度值。
  5. 如权利要求3所述的自行走设备的摄像曝光方法，其特征在于，所述图像中的关注区域包括反光面区域和空间区域，
    所述对采集到的图像中的关注区域进行分区，包括：将所述关注区域分为反光面区域和空间区域；其中，空间区域位于所述关注区域的中间位置，所述反光面区域位于所述空间区域的左右两边和/或下方。
  6. 如权利要求5所述的自行走设备的摄像曝光方法，其特征在于，所述空间区域的权值大于所述反光面区域的权值。
  7. 如权利要求1所述的自行走设备的摄像曝光方法，其特征在于，所述曝光参数包括曝光时间和/或曝光增益。
  8. 一种自行走设备的摄像曝光装置，其特征在于，所述自行走设备包括图像采集装置，所述摄像曝光装置包括：
    图像亮度检测单元，用于根据预设规则对所述图像采集装置采集到的图像中的关注区域的亮度进行检测；
    曝光参数调整单元，用于当检测到亮度信息不满足预设条件时，调整当前曝光参数；
    局部曝光单元，用于根据所述曝光参数在采集图像的过程中进行局部曝光，曝光的区域中至少包括所述关注区域。
  9. 如权利要求8所述的自行走设备的摄像曝光装置，其特征在于，所述图像亮度检测单元包括：
    分区亮度值获取模块，用于对采集到的图像中的关注区域进行分区，获取各个分区的亮度值；
    亮度信息计算模块，用于将各个分区的亮度值分别与各个分区对应的权值加权平均后得到亮度信息。
  10. 如权利要求8所述的自行走设备的摄像曝光装置，其特征在于，所述曝光参数调整单元包括：
    比较模块，用于将所述亮度信息与目标亮度作比较；
    曝光参数增加模块，用于当所述亮度信息小于所述目标亮度时，增加曝光参数；
    曝光参数减少模块，用于当所述亮度信息大于所述目标亮度时，减少曝光参数。
  11. 一种计算设备，其特征在于，包括：
    一个或多个处理器，以及
    与所述一个或多个处理器耦合的存储器，所述存储器存储指令，当所述指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行如权利要求1到7中任一项所述的方法。
  12. 一种机器可读存储介质，其特征在于，所述机器可读存储介质存储有可执行指令，所述指令当被执行时使得所述机器执行如权利要求1到7中任一项所述的方法。
PCT/CN2021/100719 2021-02-18 2021-06-17 自行走设备的摄像曝光方法和装置 WO2022174539A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP21926255.7A EP4297395A1 (en) 2021-02-18 2021-06-17 Photographing exposure method and apparatus for self-walking device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110187659.2A CN112995525B (zh) 2021-02-18 2021-02-18 自行走设备的摄像曝光方法和装置
CN202110187659.2 2021-02-18

Publications (1)

Publication Number Publication Date
WO2022174539A1 true WO2022174539A1 (zh) 2022-08-25

Family

ID=76393715

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/100719 WO2022174539A1 (zh) 2021-02-18 2021-06-17 自行走设备的摄像曝光方法和装置

Country Status (3)

Country Link
EP (1) EP4297395A1 (zh)
CN (2) CN115022552B (zh)
WO (1) WO2022174539A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114757833B (zh) * 2022-06-15 2022-09-27 北京中瑞方兴科技有限公司 一种车辆侧面图像拼接方法及系统
CN117651212A (zh) * 2024-01-29 2024-03-05 荣耀终端有限公司 一种曝光参数的调节方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109194884A (zh) * 2018-10-29 2019-01-11 广州华多网络科技有限公司 测光处理方法、装置、存储介质和设备
CN109922275A (zh) * 2019-03-28 2019-06-21 苏州科达科技股份有限公司 曝光参数的自适应调整方法、装置及一种拍摄设备
US20190199902A1 (en) * 2017-12-22 2019-06-27 X Development Llc Systems and Methods for Sampling Images
US20210016449A1 (en) * 2017-06-02 2021-01-21 Pixart Imaging Inc. Mobile robot performing multiple detections using image frames of same optical sensor
CN112351214A (zh) * 2020-09-22 2021-02-09 智博汽车科技(上海)有限公司 辅助人脸图像采集的方法、装置、可读存储介质及车辆

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791475B (zh) * 2017-01-23 2019-08-27 上海兴芯微电子科技有限公司 曝光调整方法及所适用的车载摄像装置
CN107137026A (zh) * 2017-06-26 2017-09-08 深圳普思英察科技有限公司 一种扫地机器人及其摄像头补光系统、方法
CN107278490A (zh) * 2017-07-12 2017-10-24 合肥轻风飏电气科技有限责任公司 一种智能割草机及其控制方法
CN108521863B (zh) * 2017-08-29 2020-10-16 深圳市大疆创新科技有限公司 曝光的方法、装置、计算机系统和可移动设备
JP2019149621A (ja) * 2018-02-26 2019-09-05 ソニー株式会社 情報処理装置、情報処理方法、およびプログラム
CN111343387B (zh) * 2019-03-06 2022-01-21 杭州海康慧影科技有限公司 一种摄像设备的自动曝光方法及装置
WO2021007690A1 (zh) * 2019-07-12 2021-01-21 深圳市大疆创新科技有限公司 曝光控制方法、装置与可移动平台
CN112073645B (zh) * 2020-09-04 2022-04-08 深圳创维－Rgb电子有限公司 曝光控制方法、装置、终端设备及存储介质
CN112312036A (zh) * 2020-10-30 2021-02-02 天津天地伟业智能安全防范科技有限公司 一种拍照领域的自动曝光方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210016449A1 (en) * 2017-06-02 2021-01-21 Pixart Imaging Inc. Mobile robot performing multiple detections using image frames of same optical sensor
US20190199902A1 (en) * 2017-12-22 2019-06-27 X Development Llc Systems and Methods for Sampling Images
CN109194884A (zh) * 2018-10-29 2019-01-11 广州华多网络科技有限公司 测光处理方法、装置、存储介质和设备
CN109922275A (zh) * 2019-03-28 2019-06-21 苏州科达科技股份有限公司 曝光参数的自适应调整方法、装置及一种拍摄设备
CN112351214A (zh) * 2020-09-22 2021-02-09 智博汽车科技(上海)有限公司 辅助人脸图像采集的方法、装置、可读存储介质及车辆

Also Published As

Publication number Publication date
EP4297395A1 (en) 2023-12-27
CN115022552B (zh) 2024-04-16
CN112995525B (zh) 2022-07-15
CN112995525A (zh) 2021-06-18
CN115022552A (zh) 2022-09-06

Similar Documents

Publication Publication Date Title
US10997696B2 (en) Image processing method, apparatus and device
CN110691193B (zh) 摄像头切换方法、装置、存储介质及电子设备
KR101352349B1 (ko) 노출 제어장치 및 촬상 장치
EP2494498B1 (en) Method and apparatus for image detection with undesired object removal
WO2019148978A1 (zh) 图像处理方法、装置、存储介质及电子设备
WO2019037088A1 (zh) 一种曝光的控制方法、装置以及无人机
US8994857B2 (en) Camera flash mitigation
CN111028189A (zh) 图像处理方法、装置、存储介质及电子设备
US20070195171A1 (en) Face importance level determining apparatus and method, and image pickup apparatus
WO2022174539A1 (zh) 自行走设备的摄像曝光方法和装置
CN111726521B (zh) 终端的拍照方法、拍照装置和终端
WO2015184978A1 (zh) 摄像机控制方法、装置及摄像机
WO2019105254A1 (zh) 背景虚化处理方法、装置及设备
CN110708463B (zh) 对焦方法、装置、存储介质及电子设备
CN106791451B (zh) 一种智能终端的拍照方法
US11871123B2 (en) High dynamic range image synthesis method and electronic device
WO2021109409A1 (zh) 图像拍摄方法、装置、设备及存储介质
CN112565604A (zh) 视频录制方法、装置及电子设备
JP2017162179A (ja) 情報処理装置、情報処理方法、及びプログラム
US11570373B2 (en) Information processing apparatus, image capturing apparatus, method, and storage medium
JP2005196252A (ja) 目標物領域検出装置、撮影装置、目標物領域検出方法、およびコンピュータプログラム
JP2019129469A (ja) 画像処理装置
WO2021168749A1 (en) Dynamic adjustment of a region of interest for image capture
CN114500870B (zh) 图像处理方法、装置及电子设备
CN114500870A (zh) 图像处理方法、装置及电子设备

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: 21926255

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2021926255

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021926255

Country of ref document: EP

Effective date: 20230918