CN109089052B - A method and device for verifying a target object - Google Patents
A method and device for verifying a target object Download PDFInfo
- Publication number
- CN109089052B CN109089052B CN201811216446.2A CN201811216446A CN109089052B CN 109089052 B CN109089052 B CN 109089052B CN 201811216446 A CN201811216446 A CN 201811216446A CN 109089052 B CN109089052 B CN 109089052B
- Authority
- CN
- China
- Prior art keywords
- image information
- image
- value
- target object
- threshold
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
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
- H04N23/70—Circuitry for compensating brightness variation in the scene
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
本发明实施例提出一种目标物体的验证方法及装置。接收第一图像采集装置传输的第一图像信息和第二图像采集装置传输的第二图像信息;分析出第一图像信息的第一质量值;当第一质量值小于预设的第一阈值时,依据第二图像采集装置传输的图像信息计算出目标物体在第一图像采集装置的采集范围内的滞留时间、滞留时间值和目标物体对应滞留时间在当前环境中的所处的预估位置;当滞留时间值不小于预设的曝光时间值时,依据滞留时间值和预估位置对目标物体进行曝光处理,以使生成目标图像信息;依据目标图像信息与预存储的样本图像信息的相似值生成图像验证结果,通过上述步骤获取更优的目标图像信息,从而提升了验证结果的准确性。
Embodiments of the present invention provide a method and device for verifying a target object. Receive the first image information transmitted by the first image acquisition device and the second image information transmitted by the second image acquisition device; analyze the first quality value of the first image information; when the first quality value is less than a preset first threshold calculating, according to the image information transmitted by the second image acquisition device, the residence time of the target object within the acquisition range of the first image acquisition device, the value of the residence time, and the estimated position of the target object corresponding to the residence time in the current environment; When the residence time value is not less than the preset exposure time value, the target object is subjected to exposure processing according to the residence time value and the estimated position, so as to generate target image information; according to the similarity value between the target image information and the pre-stored sample image information An image verification result is generated, and better target image information is obtained through the above steps, thereby improving the accuracy of the verification result.
Description
技术领域technical field
本发明涉及智能识别技术领域,具体而言,涉及一种目标物体的验证方法及装置。The present invention relates to the technical field of intelligent identification, and in particular, to a verification method and device for a target object.
背景技术Background technique
随着社会的发展,智能识别技术原来越普及。常见的有可见光物体识别技术和红外光物体识别技术。随着技术发展,人们逐渐认识到可见光物体识别技术和红外光物体识别技术都存在缺陷。With the development of society, intelligent identification technology has become more and more popular. Common ones are visible light object recognition technology and infrared light object recognition technology. With the development of technology, people gradually realize that both visible light object recognition technology and infrared light object recognition technology have defects.
可见光物体识别技术在光照不足的环境下可能成像质量差或无法成像,严重影响了验证结果。而红外光物体识别技术本身识别的准确率不高,误差较大,也严重影响验证结果。Visible light object recognition technology may have poor imaging quality or fail to image in an environment with insufficient light, which seriously affects the verification results. However, the recognition accuracy of infrared light object recognition technology itself is not high, and the error is large, which also seriously affects the verification results.
发明内容SUMMARY OF THE INVENTION
有改善上述问题,本发明的目的在于提供一种目标物体的验证方法及装置。In order to improve the above-mentioned problems, an object of the present invention is to provide a verification method and device for a target object.
第一方面,本发明实施例提供了一种目标物体的验证方法,所述目标物体的验证方法的步骤包括:In a first aspect, an embodiment of the present invention provides a method for verifying a target object, and the steps of the method for verifying a target object include:
接收第一图像采集装置传输的第一图像信息和第二图像采集装置传输的第二图像信息;其中,所述第二图像采集装置采集的光的波长与所述第一图像采集装置采集的光的波长的差值大于预设的波长差值,所述第一图像采集装置采集的光的波长小于所述第二图像采集装置采集的光的波长;Receive the first image information transmitted by the first image acquisition device and the second image information transmitted by the second image acquisition device; wherein the wavelength of the light acquired by the second image acquisition device is the same as the wavelength of the light acquired by the first image acquisition device The difference of the wavelengths is greater than the preset wavelength difference, and the wavelength of the light collected by the first image collection device is smaller than the wavelength of the light collected by the second image collection device;
分析出所述第一图像信息的第一质量值;其中,所述第一质量值为依据所述第一图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息综合生成;Analyzing the first quality value of the first image information; wherein, the first quality value is comprehensively generated according to the contrast, brightness, clarity of the first image information and the position information of the target object in the image;
当所述第一质量值小于预设的第一阈值时,依据所述第二图像采集装置传输的图像信息计算出所述目标物体在所述第一图像采集装置的采集范围内的滞留时间、滞留时间值和所述目标物体对应所述滞留时间在当前环境中的所处的预估位置;其中,所述滞留时间值为所述滞留时间的总长度;When the first quality value is less than a preset first threshold, calculate the residence time of the target object within the collection range of the first image collection device according to the image information transmitted by the second image collection device, The residence time value and the estimated position of the target object corresponding to the residence time in the current environment; wherein the residence time value is the total length of the residence time;
当所述滞留时间值不小于预设的曝光时间值时,依据所述滞留时间值和所述预估位置对所述目标物体进行曝光处理,以使生成所述目标图像信息;其中,所述预设的曝光时间值为所述第一图像采集装置对所述目标物体进行曝光处理的所需时间;When the residence time value is not less than a preset exposure time value, perform exposure processing on the target object according to the residence time value and the estimated position, so as to generate the target image information; wherein the The preset exposure time value is the time required for the first image acquisition device to perform exposure processing on the target object;
依据所述目标图像信息与预存储的样本图像信息的相似值生成图像验证结果。An image verification result is generated according to the similarity value between the target image information and the pre-stored sample image information.
第二方面,本发明实施例还提供了一种目标物体的验证装置,包括:In a second aspect, an embodiment of the present invention also provides a verification device for a target object, including:
信息接收单元,用于接收第一图像采集装置传输的第一图像信息和第二图像采集装置传输的第二图像信息;其中,所述第二图像采集装置采集的光的波长与所述第一图像采集装置采集的光的波长的差值大于预设的波长差值,所述第一图像采集装置采集的光的波长小于所述第二图像采集装置采集的光的波长;an information receiving unit, configured to receive first image information transmitted by the first image acquisition device and second image information transmitted by the second image acquisition device; wherein the wavelength of the light acquired by the second image acquisition device is the same as the wavelength of the light acquired by the first image acquisition device The difference between the wavelengths of the light collected by the image collection device is greater than a preset wavelength difference, and the wavelength of the light collected by the first image collection device is smaller than the wavelength of the light collected by the second image collection device;
分析单元,用于分析出所述第一图像信息的第一质量值;其中,所述第一质量值为依据所述第一图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息综合生成;An analysis unit, configured to analyze the first quality value of the first image information; wherein, the first quality value is based on the contrast, brightness, clarity of the first image information and the position of the target object in the image information synthesis;
计算单元,用于当所述第一质量值小于预设的第一阈值时,依据所述第二图像采集装置传输的图像信息计算出所述目标物体在所述第一图像采集装置的采集范围内的滞留时间、滞留时间值和所述目标物体对应所述滞留时间在当前环境中的所处的预估位置;其中,所述滞留时间值为所述滞留时间的总长度;a calculation unit, configured to calculate the acquisition range of the target object in the first image acquisition device according to the image information transmitted by the second image acquisition device when the first quality value is less than a preset first threshold The residence time, the residence time value and the estimated position of the target object in the current environment corresponding to the residence time; wherein the residence time value is the total length of the residence time;
目标图像信息生成单元,用于当所述滞留时间值不小于预设的曝光时间值时,依据所述滞留时间值和所述预估位置对所述目标物体进行曝光处理,以使生成所述目标图像信息;其中,所述预设的曝光时间值为所述第一图像采集装置对所述目标物体进行曝光处理的所需时间;A target image information generation unit, configured to perform exposure processing on the target object according to the residence time value and the estimated position when the residence time value is not less than a preset exposure time value, so as to generate the target image information; wherein the preset exposure time value is the time required for the first image acquisition device to perform exposure processing on the target object;
验证结果生成单元,用于依据所述目标图像信息与预存储的样本图像信息的相似值生成图像验证结果。A verification result generating unit, configured to generate an image verification result according to the similarity value between the target image information and the pre-stored sample image information.
本发明实施例提供的目标物体的验证方法及装置的有益效果:接收第一图像采集装置传输的第一图像信息和第二图像采集装置传输的第二图像信息;分析出第一图像信息的第一质量值;当第一质量值小于预设的第一阈值时,依据第二图像采集装置传输的图像信息计算出目标物体在第一图像采集装置的采集范围内的滞留时间、滞留时间值和目标物体对应滞留时间在当前环境中的所处的预估位置;当滞留时间值不小于预设的曝光时间值时,依据滞留时间值和预估位置对目标物体进行曝光处理,以使生成目标图像信息;依据目标图像信息与预存储的样本图像信息的相似值生成图像验证结果,通过上述步骤获取更优的目标图像信息,从而提升了验证结果的准确性。The beneficial effects of the method and device for verifying a target object provided by the embodiments of the present invention include: receiving the first image information transmitted by the first image acquisition device and the second image information transmitted by the second image acquisition device; analyzing the first image information of the first image information a quality value; when the first quality value is smaller than the preset first threshold, calculate the residence time of the target object within the collection range of the first image collection device, the residence time value and the The estimated position of the target object corresponding to the residence time in the current environment; when the residence time value is not less than the preset exposure time value, the target object is exposed according to the residence time value and the estimated position, so that the target object is generated. Image information; an image verification result is generated according to the similarity value between the target image information and the pre-stored sample image information, and better target image information is obtained through the above steps, thereby improving the accuracy of the verification result.
为使本发明的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below, and are described in detail as follows in conjunction with the accompanying drawings.
附图说明Description of drawings
为了更清楚地说明本发明实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本发明的某些实施例,因此不应被看作是对范围的限定,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他相关的附图。In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.
图1示出了本发明实施例提供的服务器分别与第一图像采集装置、第二图像采集装置的交互示意图;FIG. 1 shows a schematic diagram of interaction between a server provided by an embodiment of the present invention and a first image acquisition device and a second image acquisition device respectively;
图2示出了本发明实施例提供的服务器的结构框图;2 shows a structural block diagram of a server provided by an embodiment of the present invention;
图3示出了本发明实施例提供的目标物体的验证方法的流程示意图;3 shows a schematic flowchart of a verification method for a target object provided by an embodiment of the present invention;
图4示出了本发明实施例提供的目标物体的验证方法的步骤S105的子步骤示意图;FIG. 4 shows a schematic diagram of sub-steps of step S105 of the verification method for a target object provided by an embodiment of the present invention;
图5示出了本发明实施例提供的目标物体的验证装置的功能单元示意图。FIG. 5 shows a schematic diagram of functional units of an apparatus for verifying a target object provided by an embodiment of the present invention.
图标:10-服务器;20-第一图像采集装置;30-第二图像采集装置;101-存储器;102-存储控制器;103-处理器;104-外设接口;105-通讯器;200-目标物体的验证装置;201-信息接收单元;202-分析单元;203-计算单元;204-目标图像信息生成单元;205-验证结果生成单元。Icons: 10-server; 20-first image acquisition device; 30-second image acquisition device; 101-memory; 102-storage controller; 103-processor; 104-peripheral interface; 105-communicator; 200- 201-information receiving unit; 202-analyzing unit; 203-calculating unit; 204-target image information generating unit; 205-verifying result generating unit.
具体实施方式Detailed ways
下面将结合本发明实施例中附图,对本发明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发明一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本发明实施例的组件可以以各种不同的配置来布置和设计。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.
因此,以下对在附图中提供的本发明的实施例的详细描述并非旨在限制要求保护的本发明的范围,而是仅仅表示本发明的选定实施例。基于本发明的实施例,本领域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,都属于本发明保护的范围。Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.
需要说明的是,术语“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。It should be noted that relational terms such as the terms "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.
本发明较佳实施例提供的一种目标物体的验证方法,可应用于服务器10。如图1所示,服务器10、第一图像采集装置20、第二图像采集装置30位于无线网络或有线网络中,通过该无线网络或有线网络,服务器10分别与第一图像采集装置20、第二图像采集装置30进行数据交互。A method for verifying a target object provided by a preferred embodiment of the present invention can be applied to the
图2示出了本发明实施例提供的服务器10的结构框图。服务器10包括:存储器101、存储控制器102、一个或多个(图中仅示出一个)处理器103、外设接口104、通讯器105以及目标物体的验证装置200等。这些组件通过一条或多条通讯总线/信号线相互通讯。FIG. 2 shows a structural block diagram of a
目标物体的验证装置200包括至少一个可以软件或固件(firmware)的形式存储于存储器101中或固化在处理器103的操作系统(operating system,OS)中的软件功能模块。The
处理器103种类有多种选择,例如:中央处理器(Central Processing Unit,CPU)、数字信号处理器(Digital Signal Processing,DSP)、可编程逻辑器件(ComplexProgrammable Logic Device,CPLD)、现场可编程阵列(Field-Programmable Gate Array,FPGA)、单片机等。本实施例中采用CPU。There are various types of
存储器101可用于存储软件程序以及模块,如本发明实施例中的图片处理装置及方法所对应的程序指令/模块,目标物体的验证装置200。处理器103通过运行存储在存储器101内的软件程序以及模块,从而执行各种功能应用以及数据处理,如本发明实施例提供的目标物体的验证方法。存储器101还可用于存储处理器103传输的其他数据。The
存储器101可包括高速随机存储器,还可包括非易失性存储器,如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。处理器103以及其他可能的组件对存储器101的访问可在存储控制器102的控制下进行。
外设接口104将各种输入/输出装置耦合至处理器103以及存储器101。在一些实施例中,外设接口104、处理器103以及存储控制器102可以在单个芯片中实现。在其他一些实例中,他们可以分别由独立的芯片实现。
通讯器105接受处理器103的控制,用于与第一图像采集装置20、第二图像采集装置30进行数据交付。The
第一图像采集装置20用于采集目标物体图像信息,并将采集到的目标物体图像信息通过通讯器105发送给处理器103。第一图像采集装置20还用于接收处理器103发送的曝光指令,并执行该曝光指令对应的动作,对指定区域进行曝光处理,从而获取清晰的图像信息。其中,目标物体图像信息可以是人脸图像信息。The first
第二图像采集装置30用于采集目标物体图像信息,并将采集到的目标物体图像信息通过通讯器105发送给处理器103。The second
第一图像采集装置20可以采集可见光图像。第二图像采集装置30可以采集红外光图像。第二图像采集装置30采集的光的波长与第一图像采集装置20采集的光的波长的差值大于预设的波长差值,第一图像采集装置20采集的光的波长小于第二图像采集装置30采集的光的波长。可以通过在第一图像采集装置20的镜头和第二图像采集装置30的镜头前配置不同的滤光片以实现上述限定。The first
本发明实施例提供的应用于服务器10的目标物体的验证方法的具体步骤如图3所示:The specific steps of the verification method for the target object applied to the
步骤S101:接收所述第一图像采集装置传输的第一图像信息和所述第二图像采集装置传输的第二图像信息。Step S101: Receive first image information transmitted by the first image acquisition device and second image information transmitted by the second image acquisition device.
其中,第二图像采集装置30采集的光的波长与第一图像采集装置20采集的光的波长的差值大于预设的波长差值,第一图像采集装置20采集的光的波长小于第二图像采集装置30采集的光的波长。Wherein, the difference between the wavelength of the light collected by the second
具体地,如在应用环境介绍中所描述地,第一图像采集装置20和第二图像采集装置30所采集的目标图像可以是人脸图像,但不限于此,还可以包括其他具有识别特征的物体图像。同时,第一图像采集装置20和第二图像采集装置30分别采集的光的波长不同,第一图像采集装置20采集的光的波长小于第二图像采集装置30采集的光的波长。第一图像采集装置20和第二图像采集装置30可以分别采集可见光和红外光,在此不做限定。Specifically, as described in the introduction to the application environment, the target images captured by the first
步骤S102:分析出所述第一图像信息的第一质量值。Step S102: Analyze the first quality value of the first image information.
其中,第一质量值为依据第一图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息综合生成。Wherein, the first quality value is comprehensively generated according to the contrast, brightness, and definition of the first image information and the position information of the target object in the image.
具体地,可以依据人脸图像质量算法或者图像质量评价算法计算出第一质量值。与第一质量值关联的因数包括图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息。可以理解地,第一质量值的高低分别代表第一图像信息的好坏。Specifically, the first quality value may be calculated according to a face image quality algorithm or an image quality evaluation algorithm. The factors associated with the first quality value include contrast, brightness, sharpness of the image information, and position information of the target object in the image. Understandably, the level of the first quality value represents the quality of the first image information, respectively.
步骤S103:判断所述第一质量值是否小于预设的第一阈值?若是,则执行步骤S105;若否,则执行步骤S104。Step S103: Determine whether the first quality value is less than a preset first threshold? If yes, go to step S105; if not, go to step S104.
具体地,第一阈值依据第一图像采集装置20具体设置。当第一质量值大于或等于第一阈值,说明第一图像采集装置20所采集的图像信息质量满足比对条件,所以执行步骤S104;当第一质量值小于第一阈值,则说明第一图像采集装置20所采集的图像信息质量不满足比对条件,从而需要执行步骤S105,以获取质量满足的图像信息。Specifically, the first threshold is specifically set according to the first
步骤S104:将所述第一图像信息认定为所述目标图像信息。Step S104: Identify the first image information as the target image information.
步骤S105:当所述第一质量值小于预设的第一阈值时,依据所述第二图像采集装置传输的图像信息计算出所述目标物体在所述第一图像采集装置的采集范围内的滞留时间、滞留时间值和所述目标物体对应所述滞留时间在当前环境中的所处的预估位置。Step S105: when the first quality value is less than a preset first threshold, calculate the target object within the acquisition range of the first image acquisition device according to the image information transmitted by the second image acquisition device. The residence time, the residence time value and the estimated position of the target object corresponding to the residence time in the current environment.
其中,滞留时间为目标物体在第一图像采集装置20的图像采集范围内滞留的时间;滞留时间值为滞留时间的总长度;预估位置为目标物体对应滞留时间所成的位置,可以理解地,在当前环境中,预估位置必然处于第一图像采集装置20的图像采集范围内。Wherein, the residence time is the time that the target object stays in the image acquisition range of the first
具体地,计算出滞留时间、滞留时间值以及预估位置包括以下方式:Specifically, calculating the residence time, the residence time value and the estimated position include the following methods:
如图4所示,第一种的步骤流程如下:As shown in Figure 4, the first step process is as follows:
步骤S1051:依据所述第二图像采集装置传输的图像信息,计算出所述目标物体的当前位置、当前速度以及当前运动方向。Step S1051: Calculate the current position, current speed and current movement direction of the target object according to the image information transmitted by the second image acquisition device.
具体地,处理器103接收第二图像采集装置30连续传输的图像信息,依据第二图像采集装置30连续传输的图像信息中目标物体的位置变化可以计算出目标物体移动的距离、当前运动方向以及当前位置。依据第二图像采集装置30传输对应图像信息的时间,可以计算出对应上述移动的距离目标物体运动的时间,从而可以计算出目标物体的当前速度。Specifically, the
步骤S1052:依据所述当前位置、所述当前速度以及所述当前运动方向生成所述滞留时间值和所述预估位置。Step S1052: Generate the residence time value and the estimated position according to the current position, the current speed and the current movement direction.
具体地,根据目标物体的当前位置、当前速度以及当前运动方向可以预估出目标物体接下来一段时间的运动轨迹,将上述运动轨迹与第一图像采集装置20的图像采集范围对比,得到重合部分。再依据重合部分和当前速度可以计算出目标物体在重合部分待的时间。即重合部分为预估位置;目标物体在重合部分待的时间为滞留时间。Specifically, the movement trajectory of the target object in the next period of time can be estimated according to the current position, current speed and current movement direction of the target object, and the above-mentioned movement trajectory is compared with the image acquisition range of the first
第二种:The second:
将第一图像采集装置20采集图像画面和第二图像采集装置30采集图像画面分别分隔为M*N和W*T个单元格。The image captured by the first
分别取高度上限和高度下限的目标物体做实验。实验内容:当目标物体分别处于W*T个单元格中任一格时,目标物体对应在M*N个单元格中所处的位置,并记录该对应集合。如果以人脸图像为例,高度上限可以设置为2.3米,高度下限可以设置为0.6米,在此不做限定。Take the target objects with the upper and lower height limits respectively for experiments. Experiment content: When the target object is in any one of the W*T cells, the target object corresponds to the position in the M*N cells, and the corresponding set is recorded. Taking a face image as an example, the upper limit of height can be set to 2.3 meters, and the lower limit of height can be set to 0.6 meters, which is not limited here.
通过分析目标物体在第二图像采集装置30采集图像画面中的位置,查询上述对应几何,获取目标物体在第一图像采集装置20采集图像画面中的位置。By analyzing the position of the target object in the image captured by the second
步骤S106:判断所述滞留时间值是小于预设的曝光时间值?若是,则执行步骤S108;若否,则执行步骤S107。Step S106: Determine whether the residence time value is less than a preset exposure time value? If yes, go to step S108; if not, go to step S107.
步骤S107:依据所述滞留时间值和所述预估位置对所述目标物体进行曝光处理,以使生成所述目标图像信息。Step S107: Perform exposure processing on the target object according to the residence time value and the estimated position, so as to generate the target image information.
具体地,处理器103计算出滞留时间值和预估位置,并控制第一图像采集装置20在滞留时间内对预估位置进行曝光处理以获取目标物体清晰的图像信息,即目标图像信息。Specifically, the
步骤S108:分析出所述第二图像信息的第二质量值。Step S108: Analyze the second quality value of the second image information.
其中,第二质量值为依据第二图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息综合生成,同步骤S102。Wherein, the second quality value is comprehensively generated according to the contrast, brightness, and definition of the second image information and the position information of the target object in the image, which is the same as step S102.
步骤S109:判断所述第二质量值是否小于预设的第二阈值?若是,则执行步骤S111;若否,则执行步骤S110。Step S109: Determine whether the second quality value is less than a preset second threshold? If yes, go to step S111; if not, go to step S110.
同理步骤S102。其中,第一阈值与第二阈值不相同。第二阈值依据第二图像采集装置30具体设置。The same is true for step S102. Wherein, the first threshold is different from the second threshold. The second threshold is specifically set according to the second
步骤S110:将所述第二图像信息认定为所述目标图像信息。Step S110: Identify the second image information as the target image information.
步骤S111:判断所述第一质量值是否小于预设的第三阈值?若是,则执行步骤S110;若否,则执行步骤S112。Step S111: Determine whether the first quality value is less than a preset third threshold? If yes, go to step S110; if not, go to step S112.
具体地,第三阈值可以理解为第一图像采集装置20采集到的图像信息质量值的下限。当第一质量值小于第三阈值时,可以看着第一图像采集装置20未采集到有效图像信息。即该步骤可以看着判断第一图像采集装置20是否采集到有效图像信息。Specifically, the third threshold can be understood as the lower limit of the quality value of the image information collected by the first
步骤S112:将所述第一图像信息和所述第二图像信息进行融合处理,以使生成所述目标图像信息。Step S112: Perform fusion processing on the first image information and the second image information, so as to generate the target image information.
具体地,依据图像融合算法将第一图像信息和第二图像信息进行融合处理,以使生成目标图像信息。Specifically, the first image information and the second image information are fused according to an image fusion algorithm, so as to generate target image information.
步骤S113:依据所述目标图像信息与预存储的样本图像信息的相似值生成图像验证结果。Step S113: Generate an image verification result according to the similarity value between the target image information and the pre-stored sample image information.
具体地,将目标图像信息与样本图像信息进行比对,根据目标图像信息和样本图像信息的相似度或重合度生成相似值。Specifically, the target image information is compared with the sample image information, and a similarity value is generated according to the similarity or coincidence between the target image information and the sample image information.
在第一质量值不小于第一阈值或者滞留时间值不小于曝光时间值的条件下,若相似值大于预设的第四阈值,则验证成功;否则,验证失败。Under the condition that the first quality value is not less than the first threshold or the residence time value is not less than the exposure time value, if the similarity value is greater than the preset fourth threshold, the verification succeeds; otherwise, the verification fails.
或在第一质量值小于第一阈值、第一质量值不小于第三阈值且第二质量值小于第二阈值的条件下,若相似值大于预设的第五阈值,则识别成功;否则,识别失败。Or under the condition that the first quality value is less than the first threshold, the first quality value is not less than the third threshold, and the second quality value is less than the second threshold, if the similarity value is greater than the preset fifth threshold, the identification is successful; otherwise, Recognition failed.
或在第一质量值小于第一阈值且第二质量值大于或等于第二阈值的条件下,若相似值大于预设的第六阈值,则识别成功;否则,识别失败。Or under the condition that the first quality value is less than the first threshold and the second quality value is greater than or equal to the second threshold, if the similarity value is greater than the preset sixth threshold, the identification succeeds; otherwise, the identification fails.
或在第一质量值小于第三阈值且第二质量值小于第二阈值的条件下,若相似值大于预设的第七阈值,则识别成功;否则,识别失败。Or under the condition that the first quality value is less than the third threshold and the second quality value is less than the second threshold, if the similarity value is greater than the preset seventh threshold, the identification succeeds; otherwise, the identification fails.
其中,第四阈值、第五阈值、第六阈值以及第七阈值彼此不相同。第四阈值可以是95%-100%;第五阈值可以是85%-95%;第六阈值可以是75%-85%;第七阈值可以是70%-75%。Among them, the fourth threshold, the fifth threshold, the sixth threshold and the seventh threshold are different from each other. The fourth threshold may be 95%-100%; the fifth threshold may be 85%-95%; the sixth threshold may be 75%-85%; and the seventh threshold may be 70%-75%.
请参阅5,图5为本发明较佳实施例提供的一种目标物体的验证装置200。需要说明的是,本实施例所提供的目标物体的验证装置200,其基本原理及产生的技术效果和上述实施例相同,为简要描述,本实施例部分未提及之处,可参考上述实施例中相应内容。Please refer to 5. FIG. 5 is an
目标物体的验证装置200包括:信息接收单元201、分析单元202、计算单元203、目标图像信息生成单元204以及验证结果生成单元205。The
信息接收单元201,用于接收第一图像采集装置20传输的第一图像信息和第二图像采集装置30传输的第二图像信息。具体地,信息接收单元201可以执行步骤S101。The
分析单元202,用于分析出第一图像信息的第一质量值。具体地,分析单元202可以执行步骤S102。The analyzing
计算单元203,用于当第一质量值小于预设的第一阈值时,依据第二图像采集装置30传输的图像信息计算出目标物体在第一图像采集装置20的采集范围内的滞留时间、滞留时间值和目标物体对应滞留时间在当前环境中的所处的预估位置。具体地,计算单元203可以执行步骤S103和步骤S105。The
计算单元203具体用于依据第二图像采集装置30传输的图像信息,计算出目标物体的当前位置、当前速度以及当前运动方向。具体地,计算单元203可以执行步骤S1051。The
计算单元203具体还用用于依据当前位置、当前速度以及当前运动方向生成滞留时间值和预估位置。具体地,计算单元203可以执行步骤S1052。目标图像信息生成单元204,用于当滞留时间值不小于预设的曝光时间值时,依据滞留时间值和预估位置对目标物体进行曝光处理,以使生成目标图像信息。具体地,目标图像信息生成单元204可以执行步骤S106和S107。The
分析单元202还用于当滞留时间值小于曝光时间值时,分析出第二图像信息的第二质量值。具体地,分析单元202还可以执行步骤S108。The analyzing
目标图像信息生成单元204还用于当第二质量值小于预设的第二阈值且第一质量值不小于预设的第三阈值时,将第一图像信息和第二图像信息进行融合处理,以使生成目标图像信息。具体地,目标图像信息生成单元204还可以执行步骤S109、步骤S111和步骤S112。The target image
目标图像信息生成单元204还用于当第一质量值大于或等于第一阈值时,将第一图像信息认定为目标图像信息;The target image
目标图像信息生成单元204还用于当第一质量值小于第一阈值且第二质量值大于或等于第二阈值时,将第二图像信息认定为目标图像信息;The target image
目标图像信息生成单元204还用于当第一质量值小于第三阈值且第二质量值小于第二阈值时,将第二图像信息认定为目标图像信息。The target image
验证结果生成单元205,用于依据目标图像信息与预存储的样本图像信息的相似值生成图像验证结果。具体地,验证结果生成单元205可以执行步骤S113。The verification
验证结果生成单元205包括:The verification
相似值生成模块,用于将目标图像信息和样本图像信息进行比对,以使生成相似值。The similarity value generation module is used to compare the target image information with the sample image information, so as to generate the similarity value.
验证模块,用于在滞留时间值不小于曝光时间值的条件下,若相似值大于预设的第四阈值,则验证成功;否则,验证失败。The verification module is used for verifying successfully if the similarity value is greater than the preset fourth threshold value under the condition that the residence time value is not less than the exposure time value; otherwise, the verification fails.
验证模块还用于在第一质量值小于第一阈值、第一质量值不小于第三阈值且第二质量值小于第二阈值的条件下,若相似值大于预设的第五阈值,则识别成功;否则,识别失败。The verification module is further configured to identify if the similarity value is greater than the preset fifth threshold under the condition that the first quality value is less than the first threshold, the first quality value is not less than the third threshold and the second quality value is less than the second threshold success; otherwise, recognition failed.
综上所述,本发明实施例提供目标物体的验证方法及装置中:首先,接收第一图像采集装置传输的第一图像信息和第二图像采集装置传输的第二图像信息;分析出第一图像信息的第一质量值;当第一质量值小于预设的第一阈值时,依据第二图像采集装置传输的图像信息计算出目标物体在第一图像采集装置的采集范围内的滞留时间、滞留时间值和目标物体对应滞留时间在当前环境中的所处的预估位置;当滞留时间值不小于预设的曝光时间值时,依据滞留时间值和预估位置对目标物体进行曝光处理,以使生成目标图像信息;依据目标图像信息与预存储的样本图像信息的相似值生成图像验证结果,通过上述步骤获取更优的目标图像信息,从而提升了验证结果的准确性;其次,当滞留时间值小于曝光时间值时,分析出第二图像信息的第二质量值;其中,第二质量值为依据第二图像信息的对比度、明亮度、清晰度以及图像中目标物体的位置信息综合生成;当第二质量值小于预设的第二阈值且第一质量值不小于预设的第三阈值时,将第一图像信息和第二图像信息进行融合处理,以使生成目标图像信息,当前环境下采光不足是通过上述步骤可以获取更优地目标图像信息,提升了验证结果的准确性,并提升了验证装置的适应性。To sum up, the embodiments of the present invention provide a method and device for verifying a target object: first, receive the first image information transmitted by the first image acquisition device and the second image information transmitted by the second image acquisition device; The first quality value of the image information; when the first quality value is less than the preset first threshold, calculate the residence time of the target object within the collection range of the first image collection device according to the image information transmitted by the second image collection device, The residence time value and the estimated position of the target object corresponding to the residence time in the current environment; when the residence time value is not less than the preset exposure time value, the target object is exposed according to the residence time value and the estimated position. In order to generate the target image information; generate the image verification result according to the similarity value between the target image information and the pre-stored sample image information, and obtain better target image information through the above steps, thereby improving the accuracy of the verification result; When the time value is less than the exposure time value, the second quality value of the second image information is analyzed; wherein, the second quality value is comprehensively generated according to the contrast, brightness, clarity of the second image information and the position information of the target object in the image ; When the second quality value is less than the preset second threshold value and the first quality value is not less than the preset third threshold value, the first image information and the second image information are fused to make the generation target image information, current In the case of insufficient lighting in the environment, better target image information can be obtained through the above steps, the accuracy of the verification result is improved, and the adaptability of the verification device is improved.
在本申请所提供的几个实施例中,应该理解到,所揭露的装置和方法,也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,附图中的流程图和框图显示了根据本发明的多个实施例的装置、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、程序段或代码的一部分,所述模块、程序段或代码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。也应当注意,在有些作为替换的实现方式中,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。In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block 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. It is also noted that 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.
另外,在本发明各个实施例中的各功能模块可以集成在一起形成一个独立的部分,也可以是各个模块单独存在,也可以两个或两个以上模块集成形成一个独立的部分。In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .
以上所述仅为本发明的优选实施例而已,并不用于限制本发明,对于本领域的技术人员来说,本发明可以有各种更改和变化。凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811216446.2A CN109089052B (en) | 2018-10-18 | 2018-10-18 | A method and device for verifying a target object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811216446.2A CN109089052B (en) | 2018-10-18 | 2018-10-18 | A method and device for verifying a target object |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109089052A CN109089052A (en) | 2018-12-25 |
CN109089052B true CN109089052B (en) | 2020-09-01 |
Family
ID=64843790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811216446.2A Active CN109089052B (en) | 2018-10-18 | 2018-10-18 | A method and device for verifying a target object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109089052B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112950907A (en) * | 2021-02-02 | 2021-06-11 | 浙江大华技术股份有限公司 | Early warning method, device, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127775A (en) * | 2016-06-28 | 2016-11-16 | 乐视控股(北京)有限公司 | Measurement for Digital Image Definition and device |
CN107292285A (en) * | 2017-07-14 | 2017-10-24 | 广东欧珀移动通信有限公司 | Living iris detection method and Related product |
CN107423714A (en) * | 2017-07-28 | 2017-12-01 | 中控智慧科技股份有限公司 | Image acquisition equipment and method |
CN107577987A (en) * | 2017-08-01 | 2018-01-12 | 广州广电卓识智能科技有限公司 | Method, system and device for identity authentication |
CN108549874A (en) * | 2018-04-19 | 2018-09-18 | 广州广电运通金融电子股份有限公司 | A kind of object detection method, equipment and computer readable storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9173570B2 (en) * | 2012-04-12 | 2015-11-03 | Thomas Nathan Millikan | Viewing and processing multispectral images |
-
2018
- 2018-10-18 CN CN201811216446.2A patent/CN109089052B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127775A (en) * | 2016-06-28 | 2016-11-16 | 乐视控股(北京)有限公司 | Measurement for Digital Image Definition and device |
CN107292285A (en) * | 2017-07-14 | 2017-10-24 | 广东欧珀移动通信有限公司 | Living iris detection method and Related product |
CN107423714A (en) * | 2017-07-28 | 2017-12-01 | 中控智慧科技股份有限公司 | Image acquisition equipment and method |
CN107577987A (en) * | 2017-08-01 | 2018-01-12 | 广州广电卓识智能科技有限公司 | Method, system and device for identity authentication |
CN108549874A (en) * | 2018-04-19 | 2018-09-18 | 广州广电运通金融电子股份有限公司 | A kind of object detection method, equipment and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109089052A (en) | 2018-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109784391B (en) | Multi-model-based sample labeling method and device | |
CN108764133B (en) | Image recognition method, device and system | |
US9042647B2 (en) | Adaptive character segmentation method and system for automated license plate recognition | |
CN110413815B (en) | Portrait clustering cleaning method and device | |
CN106662970B (en) | Method and device for setting interruption threshold of fingerprint identifier and terminal equipment | |
CN105260371B (en) | A kind of feature selection approach and device | |
CN111291749B (en) | Gesture recognition method and device and robot | |
CN111414868A (en) | Determination method, motion detection method and device for time sequence action segment | |
CN111340502B (en) | Abnormal behavior identification method, device, terminal equipment and storage medium | |
CN114708304B (en) | Cross-camera multi-target tracking method, device, equipment and medium | |
KR102581154B1 (en) | Method and Apparatus for Object Detection Using Model Ensemble | |
CN109086186B (en) | Log detection method and device | |
CN115019364A (en) | Identity authentication method, device, electronic device and medium based on face recognition | |
CN112214402B (en) | Method, device and storage medium for selecting a code verification algorithm | |
CN109089052B (en) | A method and device for verifying a target object | |
CN114596638A (en) | Face liveness detection method, device and storage medium | |
JP2025529888A (en) | Distance detection method, device, equipment, and computer program | |
CN114299424B (en) | Target classification method, device, electronic device and storage medium | |
CN111242105A (en) | User identification method, device and equipment | |
CN107749838B (en) | A method and device for detecting network hijacking | |
CN110659517A (en) | Data verification method, apparatus, computer equipment and storage medium | |
CN113705489B (en) | Fine-grained aircraft recognition method in remote sensing images based on prior regional knowledge | |
CN109614844A (en) | A kind of link verification method, device and equipment | |
CN114332934A (en) | Model training method, object re-recognition method, device and storage medium | |
CN109814712B (en) | Gesture recognition system based on virtual interaction device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |