WO2019218362A1 - Object detection method, object detection device, and device having storage function - Google Patents

Object detection method, object detection device, and device having storage function Download PDF

Info

Publication number
WO2019218362A1
WO2019218362A1 PCT/CN2018/087551 CN2018087551W WO2019218362A1 WO 2019218362 A1 WO2019218362 A1 WO 2019218362A1 CN 2018087551 W CN2018087551 W CN 2018087551W WO 2019218362 A1 WO2019218362 A1 WO 2019218362A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
data
information data
points
distribution function
Prior art date
Application number
PCT/CN2018/087551
Other languages
French (fr)
Chinese (zh)
Inventor
阳光
Original Assignee
深圳配天智能技术研究院有限公司
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 深圳配天智能技术研究院有限公司 filed Critical 深圳配天智能技术研究院有限公司
Priority to PCT/CN2018/087551 priority Critical patent/WO2019218362A1/en
Publication of WO2019218362A1 publication Critical patent/WO2019218362A1/en

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using infra-red, visible or ultra-violet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands

Abstract

Disclosed is an object detection method, an object detection device, and a device having a storage function. The method comprises: acquiring information data of a bidirectional reflectance distribution function of a target object; and performing object detection on the target object by using the information data of the bidirectional reflectance distribution function of the target object and image information data of the target object. The present invention achieves an increase in the dimensions of object detection, thereby improving the accuracy of object detection.

Description

物体识别方法、物体识别装置及具有存储功能的装置 Object recognition method, object recognition device, and device having storage function

【技术领域】[Technical Field]

本发明涉及计算机视觉技术领域,特别是涉及一种物体识别方法、物体识别装置及具有存储功能的装置。The present invention relates to the field of computer vision technology, and in particular, to an object recognition method, an object recognition device, and a device having a storage function.

【背景技术】 【Background technique】

物体识别是计算机视觉技术的重要应用之一,物体识别的应用能够为人们的工作、生活带来翻天覆地的变化。Object recognition is one of the important applications of computer vision technology. The application of object recognition can bring about earth-shaking changes in people's work and life.

目前,物体识别的方法主要是基于图像匹配,对目标物体图像的灰度分布建立模板或抽取训练特征建立模型等,然后在目标物体图像中逐像素、逐区块查找匹配;或者在进行物体识别时利用学习算法等,从而达到识别目的。At present, the object recognition method is mainly based on image matching, establishing a template for the grayscale distribution of the target object image or extracting a training feature to establish a model, and then searching for matching pixel by pixel and block by block in the target object image; or performing object recognition. Use learning algorithms, etc., to achieve the purpose of identification.

然而,本申请发明人在长期的研发过程中发现,现有技术中的方法中对物体的识别的信息量较少,在进行物体识别时,很多场景仍不能很好得区分。However, the inventor of the present application found in the long-term development process that the amount of information for recognizing an object in the prior art method is small, and many scenes are still not well distinguished when performing object recognition.

【发明内容】 [Summary of the Invention]

本发明主要解决的技术问题是提供一种物体识别方法、物体识别装置及具有存储功能的装置,能够增加物体识别维度,进而提高物体识别的准确度。The technical problem to be solved by the present invention is to provide an object recognition method, an object recognition device, and a device having a storage function, which can increase the object recognition dimension and thereby improve the accuracy of object recognition.

为解决上述技术问题,本发明采用的一个技术方案是:提供一种物体识别方法,所述方法包括:获取目标物体的双向反射分布函数的信息数据;利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别。In order to solve the above technical problem, a technical solution adopted by the present invention is to provide an object recognition method, the method comprising: acquiring information data of a bidirectional reflection distribution function of a target object; and utilizing a bidirectional reflection distribution function of the target object The information data and the image information data of the target object identify the target object.

为解决上述技术问题,本发明采用的另一个技术方案是:提供一种物体识别装置,所述物体识别装置包括:处理器及存储器,所述处理器耦接所述存储器;所述存储器中存储中计算机操作指令及数据,所述处理器执行所述计算机操作指令,用于:获取目标物体的双向反射分布函数的信息数据;利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide an object recognizing device, the object recognizing device comprising: a processor and a memory, the processor is coupled to the memory; and the memory is stored a computer operating instruction and data, the processor executing the computer operation instruction, configured to: acquire information data of a bidirectional reflection distribution function of the target object; use information data of the bidirectional reflection distribution function of the target object, and the target The image information data of the object identifies the target object.

为解决上述技术问题,本发明采用的又一个技术方案是:提供一种具有存储功能的装置,所述具有存储功能的装置中存储有程序数据,所述程序数据被处理器执行时能够实现上述物体识别方法。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a device having a storage function, wherein the device having the storage function stores program data, and the program data can be implemented by the processor. Object recognition method.

本发明的有益效果是:区别于现有技术的情况,本发明物体识别方法包括:获取目标物体的双向反射分布函数的信息数据;利用目标物体的双向反射分布函数的信息数据和目标物体的图像信息数据,对目标物体进行识别。通过上述方式,本发明在进行图像识别时,利用所识别的目标物体的双向反射分布函数的信息数据结合图像信息数据,增加物体识别维度,进而能够提高物体识别的准确度。The invention has the beneficial effects that, different from the prior art, the object recognition method of the present invention comprises: acquiring information data of a bidirectional reflection distribution function of the target object; using information data of the bidirectional reflection distribution function of the target object and an image of the target object Information data to identify the target object. In the above manner, when performing image recognition, the present invention uses the information data of the bidirectional reflection distribution function of the identified target object in combination with the image information data to increase the object recognition dimension, thereby improving the accuracy of object recognition.

【附图说明】 [Description of the Drawings]

图1是本发明物体识别方法一实施方式的流程示意图;1 is a schematic flow chart of an embodiment of an object recognition method according to the present invention;

图2是本发明物体识别方法另一实施方式的流程示意图;2 is a schematic flow chart of another embodiment of an object identification method according to the present invention;

图3是图1中步骤S102的流程示意图;3 is a schematic flow chart of step S102 in FIG. 1;

图4是本发明物体识别方法一实施方式的示例示意图;4 is a schematic diagram showing an example of an embodiment of an object recognition method according to the present invention;

图5是图3中步骤S202的流程示意图;FIG. 5 is a schematic flowchart of step S202 in FIG. 3;

图6是图5中步骤S301的流程示意图;Figure 6 is a schematic flow chart of step S301 in Figure 5;

图7是本发明物体识别方法一实施方式的示例示意图;7 is a schematic diagram showing an example of an embodiment of an object recognition method according to the present invention;

图8是图3中步骤S201的流程示意图;FIG. 8 is a schematic flowchart of step S201 in FIG. 3;

图9是图1中步骤S104的流程示意图;9 is a schematic flow chart of step S104 in FIG. 1;

图10是本发明物体识别装置一实施方式的结构示意图;10 is a schematic structural view of an embodiment of an object recognition device of the present invention;

图11是本发明物体识别装置另一实施方式的结构示意图;11 is a schematic structural view of another embodiment of the object recognition device of the present invention;

图12是本发明具有存储功能的装置一实施方式的结构示意图。Figure 12 is a block diagram showing an embodiment of an apparatus having a storage function according to the present invention.

【具体实施方式】【Detailed ways】

请参阅图1,图1是本发明物体识别方法一实施方式的流程示意图。该方法包括:Please refer to FIG. 1. FIG. 1 is a schematic flow chart of an embodiment of an object recognition method according to the present invention. The method includes:

步骤S102:获取目标物体的双向反射分布函数的信息数据;Step S102: Acquire information data of a bidirectional reflection distribution function of the target object;

双向反射分布函数(Bidirectional Reflectance Distribution Function,BRDF)描述了光线如何在物体表面进行反射,具体反映光线在物体上的反射率分布的信息,可以用来描述物体的材质属性。每种材质对应的反射率分布是不一致的,因此,可以通过物体的BRDF信息数据来获取物体的材质或类别,进而能够辅助对物体进行识别。Bidirectional Reflectance Distribution Function, BRDF) describes how light is reflected on the surface of the object, specifically reflecting the reflectance distribution of the light on the object, which can be used to describe the material properties of the object. The reflectance distribution of each material is inconsistent. Therefore, the material or category of the object can be obtained by the BRDF information data of the object, thereby assisting in identifying the object.

具体地,获取目标物体的BRDF的信息数据的方法可以通过辐射传输、几何光学、或者计算机模拟等进行获取,此处不做具体限定,只要能够得出目标物体的BRDF的信息数据即可。Specifically, the method of acquiring the information data of the BRDF of the target object may be acquired by radiation transmission, geometric optics, or computer simulation, etc., and is not specifically limited herein, as long as the information data of the BRDF of the target object can be obtained.

在一个应用场景中,请参阅图2,步骤S102之前还包括:步骤S101:获取目标物体的图像信息数据。那么此时,可以通过分析目标物体的图像信息数据获取目标物体的BRDF的信息数据。In an application scenario, referring to FIG. 2, before step S102, the method further includes: step S101: acquiring image information data of the target object. Then, at this time, the information data of the BRDF of the target object can be acquired by analyzing the image information data of the target object.

进一步地,本实施方式中,目标物体的BRDF的信息数据是能够用来直接反映或者通过计算等方式得到目标物体的BRDF的相关信息数据,例如可以是目标物体的入射光的反射率的分布信息等。Further, in the present embodiment, the information data of the BRDF of the target object is related information data of the BRDF that can be directly reflected or obtained by calculation or the like, and may be, for example, distribution information of the reflectance of the incident light of the target object. Wait.

步骤S104:利用目标物体的双向反射分布函数的信息数据和目标物体的图像信息数据,对目标物体进行识别。Step S104: Identify the target object by using the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object.

其中,目标物体的图像信息数据是指能够通过包含有目标物体的图像获取到的信息,例如灰度分布、色彩、亮度等信息数据。通过目标物体的图像信息数据能够对该目标物体的边缘、空间分布状态等进行计算和检测,以对目标物体进行初步识别。Here, the image information data of the target object refers to information that can be acquired by the image including the target object, such as information data such as gradation distribution, color, and brightness. The edge information, the spatial distribution state, and the like of the target object can be calculated and detected by the image information data of the target object to perform preliminary recognition on the target object.

然而,单纯的通过上述的图像信息数据对目标物体进行识别时,会出现如图像中物体间的灰度分布差异较小,或者信息量过少而造成识别时样本间存在交叠,从而使得在很多场景下的识别效果并不好。因此,本实施方式中进一步获取目标物体的BRDF的信息数据,将BRDF的信息数据与上述目标物体的图像信息数据结合在一起,增加物体识别维度,进而提高物体识别的准确度。However, when the target object is simply identified by the image information data described above, there may be a small difference in the gray scale distribution between the objects in the image, or the amount of information is too small to cause overlap between the samples when the recognition occurs, thereby causing The recognition effect in many scenes is not good. Therefore, in the embodiment, the information data of the BRDF of the target object is further acquired, and the information data of the BRDF and the image information data of the target object are combined to increase the object recognition dimension, thereby improving the accuracy of the object recognition.

其中,请参阅图3,上述实施方式中,步骤S102包括:子步骤S201和子步骤S202。Referring to FIG. 3, in the above embodiment, step S102 includes: sub-step S201 and sub-step S202.

子步骤S201:多视角采集目标物体的多个点的多个反射率数据;Sub-step S201: collecting multiple reflectance data of a plurality of points of the target object by multiple viewing angles;

需要指出的是,此处的“点”可以指目标物体表面的具有一定面积的微小的面元。It should be noted that the "dot" herein may refer to a small surface element having a certain area on the surface of the target object.

本实施方式中,可以通过分析目标物体的图像,从中得到目标物体的多个点的多个反射率数据。其中,上述目标物体的多个点的多个反射率数据是指采集的多个点中每个点均对应多个反射率数据,具体是每个点对应多个视角的多个反射率数据。其中,目标物体的多个点可以包括目标物体的每个点,或者目标物体的一部分点,例如可以是均匀分布且占一定比例的点,具体采集的点的数量可根据需求设置。另外,每个视角中采集的点数、分布情况可以一致,或者每个视角中采集的均不相同,此处不做具体限定。In the present embodiment, a plurality of reflectance data of a plurality of points of the target object can be obtained by analyzing an image of the target object. The plurality of reflectance data of the plurality of points of the target object refers to a plurality of reflectance data corresponding to each of the plurality of points collected, and specifically, a plurality of reflectance data corresponding to the plurality of viewing angles at each point. The plurality of points of the target object may include each point of the target object, or a part of the point of the target object, for example, may be a uniformly distributed and proportioned point, and the number of specifically collected points may be set according to requirements. In addition, the number of points and the distribution of the points collected in each view may be the same, or the points collected in each view are different, and are not specifically limited herein.

具体地,可以通过多个不同视角的摄像头获取多视角的目标物体的图像,从而分析得出多个点的多个反射率数据,或者也可以设置可旋转或可移动的摄像头,从而利用一个摄像头便能得出目标物体的多个视角的图像。Specifically, an image of a multi-view target object may be acquired by a plurality of cameras of different viewing angles, thereby analyzing a plurality of reflectance data of a plurality of points, or a rotatable or movable camera may be set to utilize a camera. An image of multiple perspectives of the target object can be derived.

子步骤S202:通过目标物体的多个点的多个反射率数据得到目标物体的双向反射分布函数的信息数据。Sub-step S202: obtaining information data of a bidirectional reflection distribution function of the target object by a plurality of reflectance data of a plurality of points of the target object.

容易理解地,根据目标物体的多个点的多个反射率数据能够得出对应的多个点的BRDF的信息数据。本实施方式中,多视角采集目标物体的多个点的多个反射率数据能够得出每个点所对应的更为准确的BRDF的信息数据,从而得到更为准确的目标物体的BRDF的信息数据。It is easy to understand that the information data of the BRDF of the corresponding plurality of points can be obtained from the plurality of reflectance data of the plurality of points of the target object. In this embodiment, multiple reflectivity data of multiple points of the target object can be obtained, and more accurate information of the BRDF corresponding to each point can be obtained, thereby obtaining more accurate information of the BRDF of the target object. data.

其中,反射率数据是指能够直接或者间接得出目标物体的反射率的相关数据,例如可以是反射率,或者入射光的强度、波长、仰角、方位角、出射光的强度、仰角、方位角等。每个点的多个视角的反射率数据则对应于该点的BRDF的信息数据。Wherein, the reflectance data refers to data that can directly or indirectly obtain the reflectance of the target object, and may be, for example, reflectance, or intensity, wavelength, elevation angle, azimuth angle, intensity of emitted light, elevation angle, and azimuth angle of the incident light. Wait. The reflectance data of a plurality of viewing angles of each point corresponds to the information data of the BRDF of the point.

在一个应用场景中,请参阅图4,在获取图4中目标物体α的BRDF的信息数据时,采集了5幅不同视角但均包含目标物体α的图像(图4中仅显示其中一幅)。在具体采集时,可采集图4所示的图像中目标物体α上部分点的反射率数据,具体为图4中的虚线之间的交点的反射率数据,或者在对图像进行边缘检测得出目标物体α的边缘轮廓线后,还可以包括虚线与边缘轮廓线的交点的反射率数据。在获取每个点对应的5个不同视角的反射率数据后,整合分析得出目标物体α的BRDF的信息数据。In an application scenario, referring to FIG. 4, when acquiring the information data of the BRDF of the target object α in FIG. 4, five images with different viewing angles but each containing the target object α are collected (only one of them is shown in FIG. 4). . At the specific acquisition, the reflectance data of the partial points on the target object α in the image shown in FIG. 4 may be acquired, specifically the reflectance data of the intersection point between the broken lines in FIG. 4, or the edge detection of the image is obtained. After the edge contour of the target object α, the reflectance data of the intersection of the dotted line and the edge contour may also be included. After obtaining the reflectance data of five different viewing angles corresponding to each point, the integrated analysis results in the information data of the BRDF of the target object α.

进一步地,请参阅图5,步骤S202包括:子步骤S301和子步骤S302;Further, referring to FIG. 5, step S202 includes: sub-step S301 and sub-step S302;

子步骤S301:利用多视角采集的目标物体的多个点的多个反射率数据得到多个点中每个点的双向反射分布函数的信息数据;Sub-step S301: obtaining, by using a plurality of reflectance data of a plurality of points of the target object acquired by the multi-view, information data of a bidirectional reflection distribution function of each of the plurality of points;

容易理解地,在获取目标物体的BRDF的信息数据时,可以先获取目标物体中有代表性的多个点的BRDF,那么需要从多视角采集的目标物体的多个点的多个反射率数据中得到对应于每个点的多个反射率数据,从而可以得出每个点的BRDF的信息数据。It is easy to understand that when acquiring the information data of the BRDF of the target object, the BRDF of the representative plurality of points in the target object may be acquired first, and then multiple reflectance data of the plurality of points of the target object collected from the multiple perspectives are required. A plurality of reflectance data corresponding to each point are obtained, so that the information data of the BRDF of each point can be obtained.

更进一步地,请参阅图6,子步骤S301包括:子步骤S401和子步骤S402;Further, referring to FIG. 6, sub-step S301 includes: sub-step S401 and sub-step S402;

子步骤S401:获取采集的与目标物体的每个点在同一区域的其它点的反射率数据;Sub-step S401: acquiring reflectance data of other points collected in the same area as each point of the target object;

子步骤S402:利用每个点的反射率数据以及与每个点在同一区域的其它点的反射率数据,得到每个点的双向反射分布函数的信息数据;Sub-step S402: obtaining the information data of the bidirectional reflection distribution function of each point by using the reflectance data of each point and the reflectance data of other points in the same area of each point;

其中,该多个点中的每个点及与该每个点在同一区域的其他点的BRDF的信息数据一致。The information of the BRDF of each of the plurality of points and the other points of the same area in the same area are consistent with each other.

需要指出的是,本实施方式中,在获取目标物体的某一个点的BRDF的信息数据时,首先需要获取该点对应的多个视角的反射率数据,然而,在一些应用场景中,在采集目标物体的图像数据时,仅采集很少量的视角的图像信息数据,这样使得在利用反射率数据获取对应的BRDF的信息数据时,所得到的结果的准确度不够高,因此,需要通过一定的手段获取对应于更多视角的反射率数据。It should be noted that, in the present embodiment, when acquiring the information data of the BRDF at a certain point of the target object, it is first necessary to acquire the reflectance data of the plurality of views corresponding to the point. However, in some application scenarios, the data is collected. When the image data of the target object is acquired, only a small amount of image information data of the viewing angle is acquired, so that when the information data of the corresponding BRDF is acquired by using the reflectance data, the accuracy of the obtained result is not high enough, and therefore, it is necessary to pass certain Means to obtain reflectance data corresponding to more viewing angles.

本实施方式中,从拍摄的或者直接获取的目标物体的图像中获取目标物体的3D图像信息数据。根据目标物体的3D图像信息数据能够得出目标物体的3D分布情况,并根据目标物体的3D分布情况可以对目标物体进行区域划分,例如可以将平滑的、没有边缘的表面划定为同一个区域,并认定该区域的BRDF一致。在此认定的基础上,由于同一区域中的某一点的采集视角与区别于该点的其它点的采集视角不同,那么,其它点对应的反射率数据可以用来作为上述某一点的其它角度对应的反射率数据,通过这种手段能够大大得丰富每个点的反射率数据,尤其是在所获取的图像数据的视角较少的情况下,从而能够大大提高图像识别的准确率。In the present embodiment, the 3D image information data of the target object is acquired from the image of the captured or directly acquired target object. According to the 3D image information data of the target object, the 3D distribution of the target object can be obtained, and the target object can be divided according to the 3D distribution of the target object. For example, the smooth, non-edge surface can be defined as the same area. And determined that the BRDF of the region is consistent. On the basis of this determination, since the acquisition angle of view of a certain point in the same area is different from the collection angle of view of other points different from the point, the reflectance data corresponding to other points may be used as the other angle corresponding to the above point. The reflectance data can greatly enrich the reflectance data of each point by using this method, especially in the case where the angle of view of the acquired image data is small, thereby greatly improving the accuracy of image recognition.

例如在一个应用场景中,请参阅图7,在获取图7中目标物体β的BRDF的信息数据时,仅采集了2张不同视角的图像(其中图7为其中一张),因此,所获取的A点的反射率数据仅有两个角度的数据,若采用这两个反射率数据,由于数据过少,因此所得到的BRDF的信息数据将不够准确。而与A点在同一区域中的其它B点、C点、D点、E点的采集视角与A点不同,因此对应的反射率数据的角度也不同,因此可以将B点、C点、D点、E点等对应的反射率数据作为A点的其它角度的反射率数据,从而能够大大丰富A点的反射率数据,丰富后的A点的反射率数据中具有多个角度对应的反射率数据,因此,根据这些数据能够得出较为准确的BRDF的信息数据。For example, in an application scenario, referring to FIG. 7, when acquiring the information data of the BRDF of the target object β in FIG. 7, only two images of different viewing angles are acquired (in which FIG. 7 is one of them), and thus, the acquired The reflectance data of point A has only two angles of data. If these two reflectance data are used, the information of the obtained BRDF will not be accurate because the data is too small. The other B points, C points, D points, and E points in the same area as point A are different from point A. Therefore, the angles of the corresponding reflectance data are different, so point B, point C, and D can be used. The reflectance data corresponding to the point, the E point, and the like is used as the reflectance data of the other angles of the A point, so that the reflectance data of the point A can be greatly enriched, and the reflectance of the plurality of angles in the reflectance data of the rich point A is rich. Data, therefore, based on these data, more accurate information on BRDF can be obtained.

子步骤S302:根据每个点的双向反射分布函数的信息数据得到目标物体的双向反射分布函数的信息数据。Sub-step S302: Obtain information data of the bidirectional reflection distribution function of the target object according to the information data of the bidirectional reflection distribution function of each point.

在目标物体所选取的多个点中每个点的BRDF的信息数据都获取之后,可进一步获得对应于该目标物体的BRDF的信息数据。After the information data of the BRDF of each of the plurality of points selected by the target object is acquired, the information data of the BRDF corresponding to the target object can be further obtained.

其中,请参阅图8,在一实施方式中,上述实施方式中步骤S201包括:子步骤S501和子步骤S502;Referring to FIG. 8, in an embodiment, step S201 in the above embodiment includes: sub-step S501 and sub-step S502;

子步骤S501:分别在环境光源和主动光源的照射下,多视角采集目标物体的多个点的第一数据;Sub-step S501: collecting first data of a plurality of points of the target object by multiple angles of view under illumination of the ambient light source and the active light source, respectively;

子步骤S502:通过目标物体的多个点的第一数据得到目标物体的多个点的多个反射率数据。Sub-step S502: obtaining a plurality of reflectance data of a plurality of points of the target object by the first data of the plurality of points of the target object.

其中,环境光源是指目标物体所处的环境当中的自然光源,例如可以是太阳光,或者太阳光与灯光等所组成的混合光源等。环境光源的光强、波长、对目标物体的入射方位、与目标物体的位置关系等相关信息均为未知,无法利用目标物体在环境光源下的图像来分析目标物体的BRDF的数据信息。The ambient light source refers to a natural light source in the environment in which the target object is located, for example, it may be sunlight, or a mixed light source composed of sunlight and light. The information about the light intensity, wavelength, incident orientation of the target object, and positional relationship with the target object is unknown. It is impossible to analyze the BRDF data of the target object using the image of the target object under the ambient light source.

主动光源是指专门设置的,光强、波长、与目标物体的位置关系等信息均为已知的光源,主动光源下拍摄的目标物体的图像可以用来分析该目标物体的BRDF的数据信息。The active light source is specifically set, and the information such as the light intensity, the wavelength, and the positional relationship with the target object are known light sources, and the image of the target object photographed under the active light source can be used to analyze the BRDF data information of the target object.

本实施方式中,具体可以分别获取目标物体在环境光源和主动光源的照射下的图像数据,然后分析得出目标物体单纯在主动光源的照射下的图像数据,进而可以利用该单纯在主动光源照射下的图像数据,从而用来得出目标物体的多个点的第一数据。In the embodiment, the image data of the target object under the illumination of the ambient light source and the active light source may be respectively acquired, and then the image data of the target object under the illumination of the active light source may be analyzed, and then the active light source may be irradiated. The underlying image data is used to derive first data for a plurality of points of the target object.

其中,第一数据是指与反射率相关的数据,例如可以是入射光的强度、波长、仰角、方位角、出射光的强度、仰角、方位角等。通过目标物体的多个点的第一数据能够直接或者间接得得出目标物体的多个点的多个反射率数据。The first data refers to data related to reflectance, and may be, for example, intensity, wavelength, elevation angle, azimuth angle, intensity of emitted light, elevation angle, azimuth angle, and the like of incident light. The plurality of reflectance data of the plurality of points of the target object can be directly or indirectly obtained by the first data of the plurality of points of the target object.

其中,请参阅图9,在一实施方式中,步骤S104包括:子步骤S601和子步骤S602;Referring to FIG. 9, in an embodiment, step S104 includes: sub-step S601 and sub-step S602;

子步骤S601:利用目标物体的双向反射分布函数的信息数据和物体材质或类别对应的双向反射分布函数的模型数据,确定目标物体的材质或类别;Sub-step S601: determining the material or category of the target object by using the information data of the bidirectional reflection distribution function of the target object and the model data of the bidirectional reflection distribution function corresponding to the object material or category;

需要指出的是,BRDF可以用来描述物体的材质属性,不同材质对应的反射率分布是不一致的,因此,可以根据分析得到的目标物体的BRDF的信息数据得到该目标物体对应的材质或类别。具体地,本实施方式中,预先建立物体材质或类别对应的BRDF的模型数据,在分析得到目标物体的BRDF的信息数据后,经过对比匹配,得到与预先建立的模型数据的相似度最高的BRDF的模型数据,从而得到对应的材质或类别。It should be pointed out that BRDF can be used to describe the material properties of objects. The reflectivity distributions of different materials are inconsistent. Therefore, the material or category corresponding to the target object can be obtained according to the information of the BRDF of the target object. Specifically, in the present embodiment, the model data of the BRDF corresponding to the object material or category is established in advance, and after the information data of the BRDF of the target object is analyzed, the BRDF with the highest similarity with the pre-established model data is obtained through comparison matching. The model data to get the corresponding material or category.

在一个应用场景中,物体材质或类别对应的BRDF的模型数据为与目标物体的材质或类别相似的物体材质或类别对应的BRDF的模型数据,这样能够使得在确定目标物体的材质或类别时能够更加有针对性得进行匹配,从而加快物体识别的速度,提高物体识别的效率。In an application scenario, the model data of the BRDF corresponding to the object material or category is the model data of the BRDF corresponding to the object material or category similar to the material or category of the target object, so that the material or category of the target object can be determined. Matching is more targeted, thus speeding up object recognition and improving the efficiency of object recognition.

子步骤S602:根据目标物体的材质或类别和目标物体的图像信息数据,进而对目标物体进行识别。Sub-step S602: The target object is further identified according to the material or category of the target object and the image information data of the target object.

在得到目标物体的材质或类别后,将其与目标物体的图像信息数据综合在一起分析,从而能够对目标物体进行更加准确的识别。After obtaining the material or category of the target object, it is combined with the image information data of the target object to analyze the target object, so that the target object can be more accurately identified.

另外,由于目标物体的BRDF的信息数据是与角度相关的数据,在分析并得出物体的材质或类别后,可以将该材质或类别对应的BRDF的模型数据作为获取的目标物体的BRDF的信息数据,并将根据模型数据对应的角度赋予目标物体,作为获取的目标物体的图像信息数据的一部分对目标物体进行识别,从而能够减少自行分析识别时的误差,进一步提高物体识别的准确率。In addition, since the information data of the BRDF of the target object is angle-related data, after analyzing and obtaining the material or category of the object, the model data of the BRDF corresponding to the material or category may be used as the BRDF information of the acquired target object. The data is given to the target object according to the angle corresponding to the model data, and the target object is identified as part of the image information data of the acquired target object, thereby reducing errors in self-analysis and recognition, and further improving the accuracy of object recognition.

请参阅图10,图10是本发明物体识别装置一实施方式的结构示意图,该物体识别装置包括:处理器11及存储器12,处理器11耦接存储器12。Referring to FIG. 10, FIG. 10 is a schematic structural diagram of an object recognition apparatus according to an embodiment of the present invention. The object recognition apparatus includes a processor 11 and a memory 12, and the processor 11 is coupled to the memory 12.

其中,存储器12中存储中计算机操作指令及数据,处理器11执行计算机操作指令,用于:获取目标物体的双向反射分布函数的信息数据;利用目标物体的双向反射分布函数的信息数据和目标物体的图像信息数据,对目标物体进行识别。The memory 12 stores therein computer operation instructions and data, and the processor 11 executes computer operation instructions for: acquiring information data of a bidirectional reflection distribution function of the target object; using information data of the bidirectional reflection distribution function of the target object and the target object The image information data identifies the target object.

通过上述方式,本发明物体识别装置在进行图像识别时,利用所识别的目标物体的双向反射分布函数的信息数据结合图像信息数据,增加物体识别维度,进而能够提高物体识别的准确度。In the above manner, when the image recognition device of the present invention performs image recognition, the information data of the bidirectional reflection distribution function of the identified target object is combined with the image information data to increase the object recognition dimension, thereby improving the accuracy of the object recognition.

其中,在一实施方式中,处理器11获取目标物体的双向反射分布函数的信息数据,包括:多视角采集目标物体的多个点的多个反射率数据;通过目标物体的多个点的多个反射率数据得到目标物体的双向反射分布函数的信息数据。In an embodiment, the processor 11 acquires information data of a bidirectional reflection distribution function of the target object, including: collecting multiple reflectance data of a plurality of points of the target object by multiple viewing angles; and multiple points passing through the target object The reflectance data obtains information data of the bidirectional reflection distribution function of the target object.

其中,在一实施方式中,处理器11通过目标物体的多个点的多个反射率数据得到目标物体的双向反射分布函数的信息数据,包括:利用多视角采集的目标物体的多个点的多个反射率数据得到多个点中每个点的双向反射分布函数的信息数据;根据每个点的双向反射分布函数的信息数据得到目标物体的双向反射分布函数的信息数据。In an embodiment, the processor 11 obtains information data of a bidirectional reflection distribution function of the target object by using multiple reflectance data of a plurality of points of the target object, including: using a plurality of points of the target object acquired by using multiple angles of view The plurality of reflectance data obtains information data of the bidirectional reflection distribution function of each of the plurality of points; and the information data of the bidirectional reflection distribution function of the target object is obtained according to the information data of the bidirectional reflection distribution function of each point.

其中,在一实施方式中,处理器11利用多视角采集的目标物体的多个点的多个反射率数据得到每个点的双向反射分布函数的信息数据,包括:获取采集的与目标物体的每个点在同一区域的其它点的反射率数据;利用每个点的反射率数据以及与每个点在同一区域的其它点的反射率数据,得到每个点的双向反射分布函数的信息数据;其中,该每个点,及与该每个点在同一区域的其他点的双向反射分布函数的信息数据一致。In an embodiment, the processor 11 obtains information data of the bidirectional reflection distribution function of each point by using multiple reflectance data of a plurality of points of the target object acquired by the multi-view, including: acquiring the acquired target object The reflectance data of each point at other points in the same area; using the reflectance data of each point and the reflectance data of other points in the same area of each point, the information data of the bidirectional reflection distribution function of each point is obtained. Wherein, each of the points, and the information data of the bidirectional reflection distribution function of the other points in the same area of each point are identical.

其中,在一实施方式中,处理器11多视角下采集目标物体的多个点的多个反射率数据,包括:分别在环境光源和主动光源的照射下,多视角采集目标物体的多个点的第一数据,第一数据是指与反射率相关的数据;通过目标物体的多个点的第一数据得到目标物体的多个点的多个反射率数据。In an embodiment, the processor 11 collects multiple reflectance data of a plurality of points of the target object in multiple views, including: collecting multiple points of the target object by multiple angles under illumination of the ambient light source and the active light source, respectively. The first data, the first data refers to data related to the reflectivity; the plurality of reflectance data of the plurality of points of the target object are obtained by the first data of the plurality of points of the target object.

其中,请参阅图11,在一实施方式中,物体识别装置还包括:通信电路13;处理器11利用目标物体的双向反射分布函数的信息数据和目标物体的图像信息数据,对目标物体进行识别之前,通信电路13用于,获取目标物体的图像信息数据。Referring to FIG. 11, in an embodiment, the object recognition apparatus further includes: a communication circuit 13; the processor 11 uses the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object to identify the target object. Previously, the communication circuit 13 was used to acquire image information data of the target object.

其中,在一实施方式中,通信电路13获取目标物体的图像信息数据,包括:获取目标物体的3D图像信息数据。In an embodiment, the acquiring, by the communication circuit 13, image information data of the target object includes: acquiring 3D image information data of the target object.

其中,在一实施方式中,处理器11利用目标物体的双向反射分布函数的信息数据和目标物体的图像信息数据,对目标物体进行识别,包括:利用目标物体的双向反射分布函数的信息数据和物体材质或类别对应的双向反射分布函数的模型数据,确定目标物体的材质或类别;根据目标物体的材质或类别和目标物体的图像信息数据,进而对目标物体进行识别。In an embodiment, the processor 11 uses the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object to identify the target object, including: using the information data of the bidirectional reflection distribution function of the target object and The model data of the bidirectional reflection distribution function corresponding to the object material or category determines the material or category of the target object; and the target object is identified according to the material or category of the target object and the image information data of the target object.

其中,在一实施方式中,物体材质或类别对应的双向反射分布函数的模型数据为与目标物体的材质或类别相似的物体材质或类别对应的双向反射分布函数的模型数据。In one embodiment, the model data of the bidirectional reflection distribution function corresponding to the object material or category is model data of a bidirectional reflection distribution function corresponding to the object material or category similar to the material or category of the target object.

请参阅图12,图12是本发明具有存储功能的装置一实施方式的结构示意图。该具有存储功能的装置上存储有程序数据21,该程序数据21被处理器执行时实现上述本发明物体识别方法实施方式中的步骤,相关内容的详细说明请参见上述方法部分,在此不再赘述。Please refer to FIG. 12. FIG. 12 is a schematic structural diagram of an embodiment of a device having a storage function according to the present invention. The device having the storage function stores the program data 21, and the program data 21 is executed by the processor to implement the steps in the embodiment of the object identification method of the present invention. For details of the related content, please refer to the method section above. Narration.

其中,该具有存储功能的装置可以为服务器、软盘驱动器、硬盘驱动器、CD-ROM读取器、磁光盘读取器、CPU(针对RAM)等中的至少一种。The device having the storage function may be at least one of a server, a floppy disk drive, a hard disk drive, a CD-ROM reader, a magneto-optical disk reader, a CPU (for a RAM), and the like.

以上仅为本发明的实施方式,并非因此限制本发明的专利范围,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的专利保护范围内。The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformation made by the specification and the drawings of the present invention may be directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims (19)

  1. 一种物体识别方法,其特征在于,所述方法包括:An object recognition method, characterized in that the method comprises:
    获取目标物体的双向反射分布函数的信息数据;Obtaining information data of a bidirectional reflection distribution function of the target object;
    利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别。The target object is identified by using information data of a bidirectional reflection distribution function of the target object and image information data of the target object.
  2. 根据权利要求1所述的方法,其特征在于,所述获取目标物体的双向反射分布函数的信息数据,包括:The method according to claim 1, wherein the acquiring information data of the bidirectional reflection distribution function of the target object comprises:
    多视角采集所述目标物体的多个点的多个反射率数据;Collecting multiple reflectance data of a plurality of points of the target object by multiple viewing angles;
    通过所述目标物体的多个点的多个反射率数据得到所述目标物体的双向反射分布函数的信息数据。Information data of a bidirectional reflection distribution function of the target object is obtained by a plurality of reflectance data of a plurality of points of the target object.
  3. 根据权利要求2所述的方法,其特征在于,所述通过所述目标物体的多个点的多个反射率数据得到所述目标物体的双向反射分布函数的信息数据,包括:The method according to claim 2, wherein the obtaining the information data of the bidirectional reflection distribution function of the target object by using the plurality of reflectance data of the plurality of points of the target object comprises:
    利用多视角采集的所述目标物体的多个点的多个反射率数据得到所述多个点中每个点的所述双向反射分布函数的信息数据;Obtaining information data of the bidirectional reflection distribution function of each of the plurality of points by using a plurality of reflectance data of a plurality of points of the target object acquired by multiple viewing angles;
    根据所述每个点的所述双向反射分布函数的信息数据得到所述目标物体的双向反射分布函数的信息数据。Information data of a bidirectional reflection distribution function of the target object is obtained according to the information data of the bidirectional reflection distribution function of each point.
  4. 根据权利要求3所述的方法,其特征在于,所述利用多视角采集的所述目标物体的多个点的多个反射率数据得到所述每个点的所述双向反射分布函数的信息数据,包括:The method according to claim 3, wherein the plurality of reflectance data of the plurality of points of the target object acquired by the multi-view are used to obtain information data of the bidirectional reflection distribution function of each point ,include:
    获取采集的与所述目标物体的所述每个点在同一区域的其它点的所述反射率数据;Obtaining the reflectance data of the collected other points in the same area as the each point of the target object;
    利用所述每个点的所述反射率数据以及与所述每个点在所述同一区域的其它点的所述反射率数据,得到所述每个点的所述双向反射分布函数的信息数据;Using the reflectance data of each point and the reflectance data of the other points of the same area of each point, the information data of the bidirectional reflection distribution function of each point is obtained. ;
    其中,所述每个点,及与所述每个点在所述同一区域的其他点的所述双向反射分布函数的信息数据一致。Wherein each of the points and the information data of the bidirectional reflection distribution function of the other points of the same area of the same area are consistent.
  5. 根据权利要求2所述的方法,其特征在于,所述多视角下采集所述目标物体的多个点的多个反射率数据,包括:The method according to claim 2, wherein the capturing multiple plurality of reflectance data of the plurality of points of the target object in the multiple viewing angles comprises:
    分别在环境光源和主动光源的照射下,多视角采集所述目标物体的多个点的第一数据,所述第一数据是指与所述反射率相关的数据;Collecting, by the ambient light source and the active light source, first data of a plurality of points of the target object by using multiple angles of view, where the first data refers to data related to the reflectivity;
    通过所述目标物体的多个点的第一数据得到所述目标物体的多个点的多个反射率数据。A plurality of reflectance data of a plurality of points of the target object are obtained by first data of a plurality of points of the target object.
  6. 根据权利要求1所述的方法,其特征在于,所述利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别之前,包括:The method according to claim 1, wherein the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object are used to identify the target object, including:
    获取所述目标物体的图像信息数据。Obtaining image information data of the target object.
  7. 根据权利要求6所述的方法,其特征在于,所述获取所述目标物体的图像信息数据,包括:The method according to claim 6, wherein the acquiring the image information data of the target object comprises:
    获取所述目标物体的3D图像信息数据。Obtaining 3D image information data of the target object.
  8. 根据权利要求1所述的方法,其特征在于,所述利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别,包括:The method according to claim 1, wherein the identifying the target object by using the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object comprises:
    利用所述目标物体的双向反射分布函数的信息数据和物体材质或类别对应的双向反射分布函数的模型数据,确定所述目标物体的材质或类别;Determining a material or a category of the target object by using information data of a bidirectional reflection distribution function of the target object and model data of a bidirectional reflection distribution function corresponding to the object material or category;
    根据所述目标物体的材质或类别和所述目标物体的图像信息数据,进而对所述目标物体进行识别。The target object is further identified according to the material or category of the target object and the image information data of the target object.
  9. 根据权利要求8所述的方法,其特征在于,所述物体材质或类别对应的双向反射分布函数的模型数据为与所述目标物体的材质或类别相似的物体材质或类别对应的双向反射分布函数的模型数据。The method according to claim 8, wherein the model data of the bidirectional reflection distribution function corresponding to the object material or category is a bidirectional reflection distribution function corresponding to the material or category of the object or the category of the target object. Model data.
  10. 一种物体识别装置,其特征在于,所述物体识别装置包括:处理器及存储器,所述处理器耦接所述存储器;An object recognition device, comprising: a processor and a memory, wherein the processor is coupled to the memory;
    所述存储器中存储中计算机操作指令及数据,所述处理器执行所述计算机操作指令,用于:The computer stores the computer operation instructions and data, and the processor executes the computer operation instructions for:
    获取目标物体的双向反射分布函数的信息数据;Obtaining information data of a bidirectional reflection distribution function of the target object;
    利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别。The target object is identified by using information data of a bidirectional reflection distribution function of the target object and image information data of the target object.
  11. 根据权利要求10所述的物体识别装置,其特征在于,所述处理器获取目标物体的双向反射分布函数的信息数据,包括:The object recognition apparatus according to claim 10, wherein the processor acquires information data of a bidirectional reflection distribution function of the target object, including:
    多视角采集所述目标物体的多个点的多个反射率数据;Collecting multiple reflectance data of a plurality of points of the target object by multiple viewing angles;
    通过所述目标物体的多个点的多个反射率数据得到所述目标物体的双向反射分布函数的信息数据。Information data of a bidirectional reflection distribution function of the target object is obtained by a plurality of reflectance data of a plurality of points of the target object.
  12. 根据权利要求11所述的物体识别装置,其特征在于,所述处理器通过所述目标物体的多个点的多个反射率数据得到所述目标物体的双向反射分布函数的信息数据,包括:The object recognition apparatus according to claim 11, wherein the processor obtains information data of a bidirectional reflection distribution function of the target object by using a plurality of reflectance data of a plurality of points of the target object, including:
    利用多视角采集的所述目标物体的多个点的多个反射率数据得到所述多个点中每个点的所述双向反射分布函数的信息数据;Obtaining information data of the bidirectional reflection distribution function of each of the plurality of points by using a plurality of reflectance data of a plurality of points of the target object acquired by multiple viewing angles;
    根据所述每个点的所述双向反射分布函数的信息数据得到所述目标物体的双向反射分布函数的信息数据。Information data of a bidirectional reflection distribution function of the target object is obtained according to the information data of the bidirectional reflection distribution function of each point.
  13. 根据权利要求12所述的物体识别装置,其特征在于,所述处理器利用多视角采集的所述目标物体的多个点的多个反射率数据得到所述每个点的所述双向反射分布函数的信息数据,包括:The object recognition apparatus according to claim 12, wherein said processor obtains said bidirectional reflection distribution of said each point by using a plurality of reflectance data of a plurality of points of said target object acquired at a plurality of angles of view The information data of the function, including:
    获取采集的与所述目标物体的所述每个点在同一区域的其它点的所述反射率数据;Obtaining the reflectance data of the collected other points in the same area as the each point of the target object;
    利用所述每个点的所述反射率数据以及与所述每个点在所述同一区域的其它点的所述反射率数据,得到所述每个点的所述双向反射分布函数的信息数据;Using the reflectance data of each point and the reflectance data of the other points of the same area of each point, the information data of the bidirectional reflection distribution function of each point is obtained. ;
    其中,所述每个点,及与所述每个点在所述同一区域的其他点的所述双向反射分布函数的信息数据一致。Wherein each of the points and the information data of the bidirectional reflection distribution function of the other points of the same area of the same area are consistent.
  14. 根据权利要求11所述的物体识别装置,其特征在于,所述处理器多视角下采集所述目标物体的多个点的多个反射率数据,包括:The object recognition apparatus according to claim 11, wherein the plurality of reflectance data of the plurality of points of the target object are collected by the processor at multiple viewing angles, including:
    分别在环境光源和主动光源的照射下,多视角采集所述目标物体的多个点的第一数据,所述第一数据是指与所述反射率相关的数据;Collecting, by the ambient light source and the active light source, first data of a plurality of points of the target object by using multiple angles of view, where the first data refers to data related to the reflectivity;
    通过所述目标物体的多个点的第一数据得到所述目标物体的多个点的多个反射率数据。A plurality of reflectance data of a plurality of points of the target object are obtained by first data of a plurality of points of the target object.
  15. 根据权利要求10所述的物体识别装置,其特征在于,所述物体识别装置还包括:通信电路;所述处理器利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别之前,The object recognition device according to claim 10, wherein said object recognition device further comprises: communication circuit; said processor utilizing information data of a bidirectional reflection distribution function of said target object and an image of said target object Information data, before identifying the target object,
    所述通信电路用于,获取所述目标物体的图像信息数据。The communication circuit is configured to acquire image information data of the target object.
  16. 根据权利要求15所述的物体识别装置,其特征在于,所述通信电路获取所述目标物体的图像信息数据,包括:The object recognition device according to claim 15, wherein the acquiring, by the communication circuit, the image information data of the target object comprises:
    获取所述目标物体的3D图像信息数据。Obtaining 3D image information data of the target object.
  17. 根据权利要求10所述的物体识别装置,其特征在于,所述处理器利用所述目标物体的双向反射分布函数的信息数据和所述目标物体的图像信息数据,对所述目标物体进行识别,包括:The object recognition device according to claim 10, wherein the processor identifies the target object by using information data of a bidirectional reflection distribution function of the target object and image information data of the target object, include:
    利用所述目标物体的双向反射分布函数的信息数据和物体材质或类别对应的双向反射分布函数的模型数据,确定所述目标物体的材质或类别;Determining a material or a category of the target object by using information data of a bidirectional reflection distribution function of the target object and model data of a bidirectional reflection distribution function corresponding to the object material or category;
    根据所述目标物体的材质或类别和所述目标物体的图像信息数据,进而对所述目标物体进行识别。The target object is further identified according to the material or category of the target object and the image information data of the target object.
  18. 根据权利要求17所述的物体识别装置,其特征在于,所述物体材质或类别对应的双向反射分布函数的模型数据为与所述目标物体的材质或类别相似的物体材质或类别对应的双向反射分布函数的模型数据。The object recognition device according to claim 17, wherein the model data of the bidirectional reflection distribution function corresponding to the object material or category is bidirectional reflection corresponding to the material or category of the object or the category of the target object. Model data for the distribution function.
  19. 一种具有存储功能的装置,其特征在于,所述计算机存储介质中存储有程序数据,所述程序数据被处理器执行时能够实现如权利要求1-9任一项所述的方法。A device having a storage function, wherein the computer storage medium stores program data, and the program data is executed by a processor to implement the method according to any one of claims 1-9.
PCT/CN2018/087551 2018-05-18 2018-05-18 Object detection method, object detection device, and device having storage function WO2019218362A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/087551 WO2019218362A1 (en) 2018-05-18 2018-05-18 Object detection method, object detection device, and device having storage function

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/087551 WO2019218362A1 (en) 2018-05-18 2018-05-18 Object detection method, object detection device, and device having storage function
CN201880087414.9A CN111630368A (en) 2018-05-18 2018-05-18 Object recognition method, object recognition device, and device having storage function

Publications (1)

Publication Number Publication Date
WO2019218362A1 true WO2019218362A1 (en) 2019-11-21

Family

ID=68539291

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/087551 WO2019218362A1 (en) 2018-05-18 2018-05-18 Object detection method, object detection device, and device having storage function

Country Status (2)

Country Link
CN (1) CN111630368A (en)
WO (1) WO2019218362A1 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398940A (en) * 2008-11-07 2009-04-01 北京航空航天大学 True object material quality reflecting attribute modeling approach based on linear light
CN102175650A (en) * 2011-01-30 2011-09-07 哈尔滨工业大学 Measuring device of continuous spectrum bidirectional reflectance distribution function
CN104101580A (en) * 2014-07-25 2014-10-15 中国工程物理研究院应用电子学研究所 BRDF quick measuring device based on hemisphere array detection
CN105473999A (en) * 2013-08-30 2016-04-06 富士胶片株式会社 Optical-characteristics measurement device and optical-characteristics measurement method
US20160318259A1 (en) * 2015-05-03 2016-11-03 Canon Kabushiki Kaisha Image processing apparatus, image processing method, and storage medium
CN107392234A (en) * 2017-07-05 2017-11-24 北京航空航天大学 A kind of body surface material kind identification method based on individual 4D light field image

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398940A (en) * 2008-11-07 2009-04-01 北京航空航天大学 True object material quality reflecting attribute modeling approach based on linear light
CN102175650A (en) * 2011-01-30 2011-09-07 哈尔滨工业大学 Measuring device of continuous spectrum bidirectional reflectance distribution function
CN105473999A (en) * 2013-08-30 2016-04-06 富士胶片株式会社 Optical-characteristics measurement device and optical-characteristics measurement method
CN104101580A (en) * 2014-07-25 2014-10-15 中国工程物理研究院应用电子学研究所 BRDF quick measuring device based on hemisphere array detection
US20160318259A1 (en) * 2015-05-03 2016-11-03 Canon Kabushiki Kaisha Image processing apparatus, image processing method, and storage medium
CN107392234A (en) * 2017-07-05 2017-11-24 北京航空航天大学 A kind of body surface material kind identification method based on individual 4D light field image

Also Published As

Publication number Publication date
CN111630368A (en) 2020-09-04

Similar Documents

Publication Publication Date Title
Nayef et al. Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt
JP6816196B2 (en) Systems and methods for comprehensive multi-assay histology analysis
US10799105B2 (en) Digital colposcope system
US10007336B2 (en) Apparatus, system, and method for mobile, low-cost headset for 3D point of gaze estimation
WO2017124990A1 (en) Method, system, device and readable storage medium for realizing insurance claim fraud prevention based on consistency between multiple images
CN100587638C (en) Machine vision system aiming at high real time image collecting and processing
Li et al. Sensing and recognizing surface textures using a gelsight sensor
JP3624353B2 (en) Three-dimensional shape measuring method and apparatus
WO2015172679A1 (en) Image processing method and device
US9094493B2 (en) Capturing and processing instant drug test results using a mobile device
WO2013015528A1 (en) Apparatus, method, and medium detecting object pose
US9432655B2 (en) Three-dimensional scanner based on contours from shadow images
WO2017166933A1 (en) Non-negative matrix factorization face recognition method and system on the basis of kernel machine learning
US7626585B2 (en) Image processing method, image processor, and image processing program
JP2011238228A (en) Screen area detection method and system
RU2431190C2 (en) Facial prominence recognition method and device
US20040120571A1 (en) Apparatus and methods for the inspection of objects
US9350956B2 (en) Capturing and processing instant drug test results using a mobile device
Henricsson et al. 3-D building reconstruction with ARUBA: a qualitative and quantitative evaluation
JP5445460B2 (en) Impersonation detection system, impersonation detection method, and impersonation detection program
US20070009159A1 (en) Image recognition system and method using holistic Harr-like feature matching
CN101135680B (en) Light-induction dielectrophoresis auxiliary unicellular dielectric spectrum automatic test equipment and testing method
Xiong et al. From shading to local shape
CN102930534B (en) Method for automatically positioning acupuncture points on back of human body
JP2004134758A (en) Setup technique for inspection system

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: 18918913

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE