CN111630368A - Object recognition method, object recognition device, and device having storage function - Google Patents
Object recognition method, object recognition device, and device having storage function Download PDFInfo
- Publication number
- CN111630368A CN111630368A CN201880087414.9A CN201880087414A CN111630368A CN 111630368 A CN111630368 A CN 111630368A CN 201880087414 A CN201880087414 A CN 201880087414A CN 111630368 A CN111630368 A CN 111630368A
- Authority
- CN
- China
- Prior art keywords
- target object
- data
- information data
- distribution function
- points
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000005315 distribution function Methods 0.000 claims abstract description 71
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 67
- 238000002310 reflectometry Methods 0.000 claims description 65
- 239000000463 material Substances 0.000 claims description 37
- 230000000007 visual effect Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 5
- 238000011022 operating instruction Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses an object identification method, an object identification device and a device with a storage function, wherein the method comprises the following steps: acquiring information data of a bidirectional reflection distribution function of a target object; and identifying the target object by utilizing the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object. Through the mode, the object identification dimensionality can be increased, and the object identification accuracy is further improved.
Description
[ technical field ] A method for producing a semiconductor device
The present invention relates to the field of computer vision technologies, and in particular, to an object recognition method, an object recognition apparatus, and an apparatus having a storage function.
[ background of the invention ]
Object recognition is one of the important applications of computer vision technology, and the application of object recognition can bring the change of covering the earth for the work and life of people.
At present, the object recognition method is mainly based on image matching, a template is established for the gray distribution of a target object image or a training feature establishing model is extracted, and then the matching is searched pixel by pixel and region by region in the target object image; or a learning algorithm is utilized when the object is identified, so that the identification purpose is achieved.
However, in the long-term research and development process, the inventor of the present application finds that the amount of information for identifying an object is small in the method in the prior art, and many scenes cannot be distinguished well when the object is identified.
[ summary of the invention ]
The invention mainly solves the technical problem of providing an object identification method, an object identification device and a device with a storage function, which can increase the object identification dimension and further improve the accuracy of object identification.
In order to solve the technical problems, the invention adopts a technical scheme that: there is provided an object identification method, the method comprising: acquiring information data of a bidirectional reflection distribution function of a target object; and identifying the target object by utilizing the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object.
In order to solve the technical problem, the invention adopts another technical scheme that: there is provided an object recognition apparatus including: a processor and a memory, the processor coupled to the memory; the memory stores computer operating instructions and data, and the processor executes the computer operating instructions to: acquiring information data of a bidirectional reflection distribution function of a target object; and identifying the target object by utilizing the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object.
In order to solve the technical problem, the invention adopts another technical scheme that: there is provided a device having a storage function, in which program data are stored, which program data, when executed by a processor, are capable of implementing the above object recognition method.
The invention has the beneficial effects that: unlike the case of the prior art, the object recognition method of the present invention includes: acquiring information data of a bidirectional reflection distribution function of a target object; and 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. Through the mode, when the image recognition is carried out, the information data of the bidirectional reflection distribution function of the recognized target object is combined with the image information data, so that the object recognition dimensionality is increased, and the accuracy of the object recognition can be improved.
[ description of the drawings ]
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of an object recognition method according to the present invention;
FIG. 2 is a schematic flow chart diagram illustrating another embodiment of an object recognition method according to the present invention;
FIG. 3 is a schematic flow chart of step S102 in FIG. 1;
FIG. 4 is an exemplary diagram of one embodiment of an object identification method of the present invention;
FIG. 5 is a schematic flowchart of step S202 in FIG. 3;
FIG. 6 is a schematic flowchart of step S301 in FIG. 5;
FIG. 7 is an exemplary diagram of one embodiment of an object identification method of the present invention;
fig. 8 is a schematic flowchart of step S201 in fig. 3;
FIG. 9 is a schematic flow chart of step S104 in FIG. 1;
FIG. 10 is a schematic structural diagram of an embodiment of an object recognition apparatus according to the present invention;
FIG. 11 is a schematic structural diagram of another embodiment of an object recognition apparatus according to the present invention;
FIG. 12 is a schematic structural diagram of an embodiment of an apparatus with a storage function according to the present invention.
[ detailed description ] embodiments
Referring to fig. 1, fig. 1 is a schematic flow chart of an object recognition method according to an embodiment of the present invention. The method comprises the following steps:
step S102: acquiring information data of a bidirectional reflection distribution function of a target object;
a Bidirectional Reflectance Distribution Function (BRDF) describes how a light ray is reflected on a surface of an object, and specifically reflects information of Reflectance distribution of the light ray on the object, which can be used to describe material properties of the object. The reflectivity distribution corresponding to each material is inconsistent, so that the material or the category of the object can be acquired through the BRDF information data of the object, and the identification of the object can be assisted.
Specifically, the method for acquiring the information data of the BRDF of the target object may be acquired through radiation transmission, geometric optics, or computer simulation, and the like, and is not particularly limited herein as long as the information data of the BRDF of the target object can be obtained.
In an application scenario, referring to fig. 2, step S102 further includes: step S101: image information data of a target object is acquired. 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.
Further, in the present embodiment, the information data of the BRDF of the target object is related information data that can be used to directly reflect or obtain the BRDF of the target object by calculation or the like, and may be, for example, distribution information of reflectance of incident light of the target object.
Step S104: and 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.
The image information data of the target object is information that can be acquired from an image including the target object, and is information data such as a gradation distribution, a color, and a brightness. The edge, the spatial distribution state and the like of the target object can be calculated and detected through the image information data of the target object so as to perform preliminary identification on the target object.
However, when the target object is recognized by the image information data, for example, the gray distribution difference between the objects in the image is small, or the amount of information is too small, so that there is overlap between the samples during recognition, and 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 is combined with the image information data of the target object, so that the object identification dimension is increased, and the accuracy of the object identification is further improved.
Referring to fig. 3, in the above embodiment, step S102 includes: substep S201 and substep S202.
Substep S201: acquiring a plurality of reflectivity data of a plurality of points of a target object from multiple visual angles;
it should be noted that the "dot" herein may refer to a minute surface element having a certain area on the surface of the target object.
In this embodiment, the image of the target object may be analyzed to obtain a plurality of reflectance data of a plurality of points of the target object. The reflectivity data of the plurality of points of the target object refers to reflectivity data corresponding to each point of the plurality of collected points, and specifically, reflectivity data corresponding to each point of the plurality of collected points corresponds to a plurality of viewing angles. The plurality of points of the target object may include each point of the target object, or a part of the points of the target object, for example, the points may be uniformly distributed and occupy a certain proportion, and the number of the specifically collected points may be set according to a requirement. In addition, the number and distribution of points collected in each view may be the same, or the points collected in each view may be different, which is not specifically limited herein.
Specifically, the images of the target object with multiple viewing angles can be acquired by a plurality of cameras with different viewing angles, so that a plurality of reflectivity data of a plurality of points can be obtained through analysis, or a rotatable or movable camera can be arranged, so that the images of the target object with multiple viewing angles can be obtained by using one camera.
Substep S202: information data of a bidirectional reflection distribution function of the target object is obtained from a plurality of reflectivity data of a plurality of points of the target object.
It is easily understood that information data of the BRDF of a plurality of points corresponding to a plurality of reflectivity data of a plurality of points of the target object can be derived. In this embodiment, acquiring multiple reflectivity data of multiple points of the target object from multiple views can obtain more accurate information data of the BRDF corresponding to each point, so as to obtain more accurate information data of the BRDF of the target object.
The reflectivity data refers to related data that can directly or indirectly obtain the reflectivity of the target object, and may be, for example, the reflectivity, or the intensity, wavelength, elevation angle, azimuth angle, intensity of outgoing light, elevation angle, azimuth angle, and the like of incident light. The reflectance data for the multiple views for each point then corresponds to the information data for the BRDF for that point.
In an application scenario, referring to fig. 4, when information data of the BRDF of the target object α in fig. 4 is acquired, 5 images (only one of which is shown in fig. 4) with different viewing angles but all including the target object α are acquired. During the specific acquisition, the reflectivity data of the partial points on the target object α in the image shown in fig. 4, specifically, the reflectivity data of the intersection points between the dotted lines in fig. 4, may be acquired, or after the edge detection is performed on the image to obtain the edge contour line of the target object α, the reflectivity data of the intersection points between the dotted lines and the edge contour line may also be included. After the reflectivity data of 5 different visual angles corresponding to each point is obtained, information data of BRDF of the target object alpha is obtained through integration and analysis.
Further, referring to fig. 5, step S202 includes: substeps S301 and substep S302;
substep S301: obtaining information data of a bidirectional reflection distribution function of each point in a plurality of points by using a plurality of reflectivity data of the plurality of points of the target object acquired from a plurality of visual angles;
it is easy to understand that when the information data of the BRDF of the target object is obtained, the BRDF of a representative plurality of points in the target object may be obtained first, and then a plurality of reflectivity data corresponding to each point need to be obtained from a plurality of reflectivity data of a plurality of points of the target object acquired from multiple perspectives, so that the information data of the BRDF of each point can be obtained.
Further, referring to fig. 6, the sub-step S301 includes: substeps S401 and substep S402;
substep S401: acquiring the acquired reflectivity data of other points of each point of the target object in the same area;
substep S402: obtaining information data of the bidirectional reflection distribution function of each point by using the reflectivity data of each point and the reflectivity data of other points in the same area with each point;
wherein the information data of the BRDF of each of the plurality of points and the BRDF of the other points in the same area as the each point are identical.
It should be noted that, in the present embodiment, when acquiring information data of a BRDF at a certain point of a target object, reflectance data of a plurality of views corresponding to the certain point needs to be acquired first, however, in some application scenarios, when acquiring image data of the target object, only a very small number of views are acquired, so that when acquiring information data of a corresponding BRDF by using the reflectance data, the accuracy of the obtained result is not high enough, and therefore, reflectance data corresponding to more views need to be acquired by a certain means.
In the present embodiment, 3D image information data of a target object is acquired from a photographed or directly acquired image of the target object. The 3D distribution of the target object can be obtained from the 3D image information data of the target object, and the target object can be divided into regions according to the 3D distribution of the target object, for example, smooth surfaces without edges can be divided into the same region, and the BRDF of the region is determined to be consistent. On the basis of the identification, because the acquisition visual angle of a certain point in the same area is different from the acquisition visual angles of other points different from the point, the reflectivity data corresponding to other points can be used as the reflectivity data corresponding to other angles of the certain point, and by the means, the reflectivity data of each point can be greatly enriched, especially under the condition that the acquired image data has fewer visual angles, so that the accuracy of image identification can be greatly improved.
For example, in an application scenario, referring to fig. 7, when information data of the BRDF of the target object β in fig. 7 is acquired, only 2 images (one of which is shown in fig. 7) with different viewing angles are acquired, so that the acquired reflectance data of the point a has only two angles, and if the two reflectance data are adopted, the acquired information data of the BRDF will be inaccurate due to too little data. And the collection visual angles of other points B, C, D and E in the same area with the point A are different from the point A, so that the angles of the corresponding reflectivity data are also different, and the reflectivity data corresponding to the points B, C, D, E and the like can be used as the reflectivity data of other angles of the point A, so that the reflectivity data of the point A can be greatly enriched, and the enriched reflectivity data of the point A has the reflectivity data corresponding to a plurality of angles, so that more accurate BRDF information data can be obtained according to the data.
Substep S302: and obtaining the 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.
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 acquired.
Referring to fig. 8, in an embodiment, step S201 in the above embodiment includes: substeps S501 and substep S502;
substep S501: acquiring first data of a plurality of points of a target object from multiple visual angles under the irradiation of an ambient light source and an active light source respectively;
substep S502: a plurality of reflectivity data of a plurality of points of the target object is obtained from the first data of the plurality of points of the target object.
The ambient light source is a natural light source in the environment where the target object is located, and may be, for example, sunlight or a mixed light source composed of sunlight and light. The light intensity, wavelength, incident direction to the target object, position relation with the target object and other related information of the ambient light source are unknown, and the data information of the BRDF of the target object cannot be analyzed by using the image of the target object under the ambient light source.
The active light source is a specially-set light source, information such as light intensity, wavelength, position relation with a target object and the like is known, and an image of the target object shot under the active light source can be used for analyzing data information of the BRDF of the target object.
In this embodiment, image data of the target object under the irradiation of the ambient light source and the active light source may be obtained, and then the image data of the target object under the irradiation of the active light source may be obtained through analysis, so that the image data under the irradiation of the active light source may be utilized to obtain first data of a plurality of points of the target object.
The first data refers to data related to reflectivity, and may be, for example, the intensity, wavelength, elevation angle, azimuth angle, intensity of outgoing light, elevation angle, azimuth angle, and the like. The plurality of reflectivity data of the plurality of points of the target object can be derived directly or indirectly from the first data of the plurality of points of the target object.
Referring to fig. 9, in one embodiment, step S104 includes: substeps S601 and substep S602;
substep S601: determining the material or the category of the target object by utilizing 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 material or the category of the object;
it should be noted that the BRDF may be used to describe the material property of the object, and the reflectivity distributions corresponding to different materials are not consistent, so that the material or the category corresponding to the target object may be obtained according to the information data of the BRDF of the target object obtained through analysis. Specifically, in this embodiment, model data of the BRDF corresponding to the material or the category of the object is pre-established, and after information data of the BRDF of the target object is obtained through analysis, model data of the BRDF having the highest similarity to the pre-established model data is obtained through comparison and matching, so as to obtain the corresponding material or the category.
In an application scene, the model data of the BRDF corresponding to the material or the category of the object is the model data of the BRDF corresponding to the material or the category of the object similar to the material or the category of the target object, so that the material or the category of the target object can be matched in a more targeted manner, the speed of object identification is increased, and the efficiency of object identification is improved.
Substep S602: and identifying the target object according to the material or the category of the target object and the image information data of the target object.
After the material or the category of the target object is obtained, the material or the category is integrated with the image information data of the target object for analysis, so that the target object can be identified more accurately.
In addition, because the information data of the BRDF of the target object is data related to an angle, after the material or the category of the object is analyzed and obtained, the model data of the BRDF corresponding to the material or the category can be used as the information data of the BRDF of the obtained target object, the angle corresponding to the model data is given to the target object, and the target object is identified as a part of the image information data of the obtained target object, so that the error during self-analysis and identification can be reduced, and the accuracy of object identification can be further improved.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an embodiment of an object recognition device according to the present invention, the object recognition device includes: a processor 11 and a memory 12, wherein the processor 11 is coupled to the memory 12.
Wherein, the memory 12 stores therein computer operation instructions and data, and the processor 11 executes the computer operation instructions for: acquiring information data of a bidirectional reflection distribution function of a target object; and 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.
Through the mode, when the object recognition device performs image recognition, the information data of the bidirectional reflection distribution function of the recognized target object is combined with the image information data, so that the object recognition dimensionality is increased, and the object recognition accuracy can be improved.
In one embodiment, the processor 11 obtains information data of a bidirectional reflectance distribution function of a target object, and includes: acquiring a plurality of reflectivity data of a plurality of points of a target object from multiple visual angles; information data of a bidirectional reflection distribution function of the target object is obtained from a plurality of reflectivity data of a plurality of points of the target object.
In one embodiment, the processor 11 obtains the information data of the bidirectional reflectance distribution function of the target object from the reflectivity data of the plurality of points of the target object, and includes: obtaining information data of a bidirectional reflection distribution function of each point in a plurality of points by using a plurality of reflectivity data of the plurality of points of the target object acquired from a plurality of visual angles; and obtaining the 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.
In one embodiment, the processor 11 obtains the information data of the bidirectional reflectance distribution function of each point by using a plurality of reflectivity data of a plurality of points of the target object acquired from a plurality of perspectives, including: acquiring the acquired reflectivity data of other points of each point of the target object in the same area; obtaining information data of the bidirectional reflection distribution function of each point by using the reflectivity data of each point and the reflectivity data of other points in the same area with each point; wherein, the information data of the bidirectional reflection distribution function of each point and other points in the same area with each point are consistent.
In one embodiment, the processor 11 acquires a plurality of reflectivity data of a plurality of points of the target object under a plurality of viewing angles, including: under the irradiation of an ambient light source and an active light source respectively, acquiring first data of a plurality of points of a target object from multiple visual angles, wherein the first data refers to data related to reflectivity; a plurality of reflectivity data of a plurality of points of the target object is obtained from the first data of the plurality of points of the target object.
Referring to fig. 11, in an embodiment, the object recognition apparatus further includes: a communication circuit 13; the processor 11 is configured to acquire image information data of the target object before identifying the target object by using the information data of the bidirectional reflectance distribution function of the target object and the image information data of the target object.
In one embodiment, the communication circuit 13 acquires image information data of a target object, and includes: 3D image information data of a target object is acquired.
In one embodiment, the identifying the target object by the processor 11 using the information data of the bidirectional reflectance distribution function of the target object and the image information data of the target object includes: determining the material or the category of the target object by utilizing 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 material or the category of the object; and identifying the target object according to the material or the category of the target object and the image information data of the target object.
In one embodiment, the model data of the bidirectional reflection distribution function corresponding to the material or the category of the object is the model data of the bidirectional reflection distribution function corresponding to the material or the category of the object similar to the material or the category of the target object.
Referring to fig. 12, fig. 12 is a schematic structural diagram of an embodiment of a device with a storage function according to the present invention. The device with storage function stores program data 21, and when executed by the processor, the program data 21 implement the steps in the embodiment of the object identification method of the present invention, for detailed description, refer to the above method section, and are not described herein again.
The device having a storage function may be at least one of a server, a flexible disk drive, a hard disk drive, a CD-ROM reader, a magneto-optical disk reader, a CPU (for RAM), and the like.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (19)
- An object identification method, characterized in that the method comprises:acquiring information data of a bidirectional reflection distribution function of a target object;and identifying the target object by utilizing the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object.
- The method of claim 1, wherein the obtaining information data of the bidirectional reflectance distribution function of the target object comprises:acquiring a plurality of reflectivity data of a plurality of points of the target object from multiple perspectives;and obtaining the information data of the bidirectional reflection distribution function of the target object through a plurality of reflectivity data of a plurality of points of the target object.
- The method of claim 2, wherein obtaining the information data of the bi-directional reflection distribution function of the target object from the plurality of reflectivity data of the plurality of points of the target object comprises:obtaining information data of the bidirectional reflection distribution function of each point in a plurality of points by using a plurality of reflectivity data of the plurality of points of the target object acquired from a plurality of visual angles;and obtaining the 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.
- The method of claim 3, wherein said obtaining information data of said bi-directional reflection distribution function for each point using a plurality of reflectivity data of a plurality of points of said target object acquired from a plurality of perspectives comprises:acquiring the acquired reflectivity data of other points in the same area with each point of the target object;obtaining information data of the bidirectional reflection distribution function of each point by using the reflectivity data of each point and the reflectivity data of other points of each point in the same area;wherein the information data of the bidirectional reflection distribution function of each point and other points in the same area are consistent.
- The method of claim 2, wherein acquiring a plurality of reflectance data for a plurality of points of the target object at the plurality of viewing angles comprises:acquiring first data of a plurality of points of the target object from multiple visual angles under the irradiation of an ambient light source and an active light source respectively, wherein the first data refers to data related to the reflectivity;obtaining a plurality of reflectivity data of a plurality of points of the target object through the first data of the plurality of points of the target object.
- The method according to claim 1, wherein before identifying the target object using the information data of the bidirectional reflectance distribution function of the target object and the image information data of the target object, comprises:and acquiring image information data of the target object.
- The method of claim 6, wherein the obtaining image information data of the target object comprises:and acquiring 3D image information data of the target object.
- The method of claim 1, wherein the identifying the target object using the information data of the bidirectional reflectance distribution function of the target object and the image information data of the target object comprises:determining the material or the category of the target object by utilizing 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 material or the category of the object;and identifying the target object according to the material or the category of the target object and the image information data of the target object.
- The method of claim 8, wherein the model data of the bi-directional reflection distribution function corresponding to the object material or class is model data of a bi-directional reflection distribution function corresponding to an object material or class similar to the material or class of the target object.
- An object recognition apparatus, characterized in that the object recognition apparatus comprises: a processor and a memory, the processor coupled to the memory;the memory stores computer operating instructions and data, and the processor executes the computer operating instructions to:acquiring information data of a bidirectional reflection distribution function of a target object;and identifying the target object by utilizing the information data of the bidirectional reflection distribution function of the target object and the image information data of the target object.
- The object recognition device of claim 10, wherein the processor obtains information data of a bidirectional reflectance distribution function of the target object, comprising:acquiring a plurality of reflectivity data of a plurality of points of the target object from multiple perspectives;and obtaining the information data of the bidirectional reflection distribution function of the target object through a plurality of reflectivity data of a plurality of points of the target object.
- The object recognition device of claim 11, wherein the processor derives information data of a bidirectional reflectance distribution function of the target object from a plurality of reflectance data of a plurality of points of the target object, including:obtaining information data of the bidirectional reflection distribution function of each point in a plurality of points by using a plurality of reflectivity data of the plurality of points of the target object acquired from a plurality of visual angles;and obtaining the 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.
- The object recognition device of claim 12, wherein the processor obtains the information data of the bidirectional reflectance distribution function for each point by using a plurality of reflectance data of a plurality of points of the target object acquired from a plurality of viewpoints, including:acquiring the acquired reflectivity data of other points in the same area with each point of the target object;obtaining information data of the bidirectional reflection distribution function of each point by using the reflectivity data of each point and the reflectivity data of other points of each point in the same area;wherein the information data of the bidirectional reflection distribution function of each point and other points in the same area are consistent.
- The object recognition device of claim 11, wherein the processor acquires a plurality of reflectivity data for a plurality of points of the target object at a plurality of viewing angles, comprising:acquiring first data of a plurality of points of the target object from multiple visual angles under the irradiation of an ambient light source and an active light source respectively, wherein the first data refers to data related to the reflectivity;obtaining a plurality of reflectivity data of a plurality of points of the target object through the first data of the plurality of points of the target object.
- The object identifying apparatus according to claim 10, further comprising: a communication circuit; before the processor identifies 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,the communication circuit is used for acquiring the image information data of the target object.
- The object recognition device of claim 15, wherein the communication circuit acquires image information data of the target object, comprising:and acquiring 3D image information data of the target object.
- The object recognition device of claim 10, wherein the processor recognizes the target object using the information data of the bidirectional reflectance distribution function of the target object and the image information data of the target object, comprising:determining the material or the category of the target object by utilizing 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 material or the category of the object;and identifying the target object according to the material or the category of the target object and the image information data of the target object.
- The object recognition apparatus according to claim 17, wherein the model data of the bidirectional reflectance distribution function corresponding to the object material or category is model data of a bidirectional reflectance distribution function corresponding to an object material or category similar to the material or category of the target object.
- An apparatus having a storage function, wherein the computer storage medium has stored therein program data which, when executed by a processor, is capable of implementing the method of any one of claims 1-9.
Applications Claiming Priority (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 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111630368A true CN111630368A (en) | 2020-09-04 |
| CN111630368B CN111630368B (en) | 2023-03-21 |
Family
ID=68539291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880087414.9A Active CN111630368B (en) | 2018-05-18 | 2018-05-18 | Object recognition method, object recognition device, and device having storage function |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111630368B (en) |
| WO (1) | WO2019218362A1 (en) |
Citations (7)
| 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 |
| CN107463659A (en) * | 2017-07-31 | 2017-12-12 | 广东欧珀移动通信有限公司 | Object search method and its device |
-
2018
- 2018-05-18 CN CN201880087414.9A patent/CN111630368B/en active Active
- 2018-05-18 WO PCT/CN2018/087551 patent/WO2019218362A1/en active Application Filing
Patent Citations (7)
| 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 |
| CN107463659A (en) * | 2017-07-31 | 2017-12-12 | 广东欧珀移动通信有限公司 | Object search method and its device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111630368B (en) | 2023-03-21 |
| WO2019218362A1 (en) | 2019-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Adams et al. | The southampton-york natural scenes (syns) dataset: Statistics of surface attitude | |
| US20210406516A1 (en) | Method and apparatus for training face detection model, and apparatus for detecting face key point | |
| JP2022546627A (en) | Method for augmenting sensor and imaging systems with polarized light | |
| US9613300B2 (en) | Material classification using multiview capture | |
| CN106228507A (en) | A kind of depth image processing method based on light field | |
| Varol et al. | Monocular 3D reconstruction of locally textured surfaces | |
| Jehle et al. | Learning of optimal illumination for material classification | |
| US20070025594A1 (en) | On optimizing template matching via performance characterization | |
| US11734861B2 (en) | 2D and 3D floor plan generation | |
| CN111239684A (en) | Binocular fast distance measurement method based on YoloV3 deep learning | |
| Führ et al. | Camera self-calibration based on nonlinear optimization and applications in surveillance systems | |
| CN115311618A (en) | Assembly quality inspection method based on deep learning and object matching | |
| O'Byrne et al. | A comparison of image based 3D recovery methods for underwater inspections | |
| Remondino et al. | Evaluating hand-crafted and learning-based features for photogrammetric applications | |
| JP2001147110A (en) | Random pattern generating device and its method, distance image generating device and its method, and program providing medium | |
| Ramakrishnan et al. | Shadow compensation for outdoor perception | |
| Xu et al. | A unified spatial-angular structured light for single-view acquisition of shape and reflectance | |
| Yang et al. | Research on Edge Detection of LiDAR Images Based on Artificial Intelligence Technology | |
| Rantoson et al. | 3D reconstruction of transparent objects exploiting surface fluorescence caused by UV irradiation | |
| Hofmann et al. | Efficiently annotating object images with absolute size information using mobile devices | |
| KR101865886B1 (en) | Method and system for estimating surface geometry and reflectance | |
| US9818234B2 (en) | 3D shape reconstruction using reflection onto electronic light diffusing layers | |
| CN111630368B (en) | Object recognition method, object recognition device, and device having storage function | |
| CN102194249B (en) | Water current modeling data capturing device with combination of infrared rays and visible light | |
| Zou et al. | Automatic inpainting by removing fence-like structures in RGBD images |
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 |