阅读说明：本技术 一种高速双相机三维检测系统及方法 (High-speed double-camera three-dimensional detection system and method ) 是由 陈泰 王曌 于 2021-09-08 设计创作，主要内容包括：本发明具体公开了一种高速双相机三维检测系统及方法,包括投影装置、第一图像采集装置、第二图像采集装置和处理器,投影装置用于向待测物体表面投射结构光图案；第一图像采集装置用于采集投影装置的部分投影区域图案,该采集区域被配置成第一采集区域；第二图像采集装置用于采集投影装置的部分投影区域图案,该采集区域被配置成第二采集区域,第二采集区域和第一采集区域部分重叠；处理器用于获取采集到的图像,根据图像进行分析计算,获得待测物体的高度信息。通过设置第一图像采集装置和第二图像采集装置,处理器获得采集到的图像并处理,在相同采集速度下获得更大区域的高度信息,提高了检测速度。(The invention discloses a high-speed double-camera three-dimensional detection system and a method, which comprise a projection device, a first image acquisition device, a second image acquisition device and a processor, wherein the projection device is used for projecting a structured light pattern to the surface of an object to be detected; the first image acquisition device is used for acquiring a partial projection area pattern of the projection device, and the acquisition area is configured as a first acquisition area; the second image acquisition device is used for acquiring a partial projection area pattern of the projection device, the acquisition area is configured into a second acquisition area, and the second acquisition area is partially overlapped with the first acquisition area; the processor is used for acquiring the acquired image, and performing analysis calculation according to the image to obtain the height information of the object to be measured. Through setting up first image acquisition device and second image acquisition device, the treater obtains the image of gathering and handles, obtains the height information of bigger region under the same speed of gathering, has improved detection speed.)

1. A high-speed dual-camera three-dimensional inspection system, comprising:

at least one projection device for projecting at least one structured light pattern onto the surface of the object to be measured;

the first image acquisition device is arranged above the object to be measured and used for acquiring a part of projection area patterns of the projection device, and the acquisition area is configured as a first acquisition area;

the second image acquisition device is arranged above the object to be measured and used for acquiring a part of projection area patterns of the projection device, the acquisition area is configured into a second acquisition area, and the second acquisition area is partially overlapped with the first acquisition area;

and the processor is used for acquiring the images acquired by the first image acquisition device and the second image acquisition device, and performing analysis calculation according to the acquired images to acquire the height information of the object to be detected.

2. The system of claim 1, wherein the number of said projection devices is at least one, and said first and second image capturing devices are disposed in parallel and on one side of said projection devices.

3. The three-dimensional detection system for a high-speed dual camera as claimed in claim 1, wherein the processor comprises a height calculation module, the height calculation module comprising:

the initialization module is used for importing preset or calibrated position relations or calibration parameters and the like between the projection device and the first image acquisition device and between the projection device and the second image acquisition device;

the acquisition module is used for acquiring image sequences acquired by the first image acquisition device and the second image acquisition device;

a 3D reconstruction module to calculate height data of the first acquisition region and the second acquisition region, respectively;

the data fusion module is used for fusing the height data of the overlapping region of the first acquisition region and the second acquisition region and the overlapping region of the second acquisition region and the first acquisition region;

and the output module is used for outputting the height information of the object to be detected.

4. A high-speed dual-camera three-dimensional detection method applied to the high-speed dual-camera three-dimensional detection system according to any one of claims 1 to 3, comprising:

s10, projecting a structured light pattern to the surface of the object to be measured by using a projection device;

s20, acquiring a projection area pattern by using a first image acquisition device and a second image acquisition device;

and S30, analyzing the projection area pattern through the processor to acquire the height information of the object to be measured.

5. The three-dimensional detection method for the high-speed dual cameras as claimed in claim 4, wherein the step S30 is specifically as follows:

s300, importing preset or calibrated position relationships or calibration parameters and the like between the projection device and the first image acquisition device and between the projection device and the second image acquisition device by using an initialization module in the processor;

s301, acquiring image sequences acquired by a first image acquisition device and a second image acquisition device by using an acquisition module;

s302, respectively calculating height data of a first acquisition area and a second acquisition area by using a 3D reconstruction module;

s303, fusing the height data of the overlapping region of the first acquisition region and the second acquisition region and the overlapping region of the second acquisition region and the first acquisition region by using a data fusion module.

Technical Field

The invention relates to the technical field of three-dimensional detection equipment, in particular to a high-speed double-camera three-dimensional detection system and method.

Background

The three-dimensional scanning technology is widely applied to the fields of industrial detection, robot navigation, reverse engineering, target identification and the like. Particularly in the fields of industrial automation and electronics, it is required to obtain an accurate three-dimensional size and surface shape of a measurement target. In the electronic assembly industry, the solder paste sticking quality of a surface mounting production line and components on a circuit board need to be detected through machine vision, 3D (three-dimensional) solder paste detection equipment (3D SPI) is generally adopted to detect the quality of solder paste printing, and three-dimensional optical detection equipment (3D AOI) is adopted to detect the quality of a PCB after furnace-passing welding, so that the yield of products is improved once. The 3D SPI/AOI equipment generally consists of a projection light source, an industrial camera, a lens, a two-dimensional light source, an image acquisition card and core software. The projection light source projects the structured light to the surface of the circuit board, the camera collects the structured light pattern for analysis and processing, the height information of solder paste printing on the circuit board is quickly and accurately obtained, and defective products are eliminated. The currently adopted technology of the projection light source part comprises a linear laser and a surface projection device, the 3D SPI equipment also adopts a marking and mechanical pushing combined mode to generate structured light, and the surface projection device becomes the mainstream technology of the current 3D SPI equipment due to the advantages that the speed is high, mechanical pushing is not needed, and the like. Chinese patent publication No. CN211042118U is a three-dimensional detection system and method, the system includes: the first projection device is used for projecting an optical signal of a first waveband to a sample to be detected; the second projection device is used for projecting the optical signal of a second waveband to the sample to be detected, the second waveband and the first waveband are different wavebands, and the projection areas of the optical signal of the first waveband and the optical signal of the second waveband on the sample to be detected are partially overlapped; the image acquisition device is arranged above the sample to be measured and used for acquiring images of a projection area of the first projection device and a projection area of the second projection device; and the processor is used for acquiring the image acquired by the image acquisition device, calculating the specification parameters of the sample to be detected according to the image and determining the specification parameters of the sample to be detected. This detecting system obtains two projection regions through two projection arrangement, recycle an image acquisition device and gather two projection region's image, this detecting system can obtain the more regional information of sample that awaits measuring, detection efficiency has been improved to a certain extent, but because image acquisition device's resolution ratio has some restrictions, consequently image acquisition device's collection area can not be too big, detection precision and detection speed all receive the restriction, this detecting system and detection method are gathered two projection regions by an image acquisition device, can't satisfy the requirement of high detection precision and high detection speed.

Disclosure of Invention

The invention aims to provide a high-speed double-camera three-dimensional detection system, a high-speed double-camera three-dimensional detection method and a storage medium, so as to improve the detection speed and the detection precision.

A high-speed double-camera three-dimensional detection system comprises at least one projection device, a first image acquisition device, a second image acquisition device and a processor, wherein the projection device is used for projecting at least one structured light pattern to the surface of an object to be detected; the first image acquisition device and the second image acquisition device are arranged above an object to be detected, the first image acquisition device is used for acquiring partial projection area patterns of the projection device, and the acquisition area is configured as a first acquisition area; the second image acquisition device is used for acquiring a partial projection area pattern of the projection device, the acquisition area is configured into a second acquisition area, and the second acquisition area is partially overlapped with the first acquisition area; the processor is used for acquiring the images acquired by the first image acquisition device and the second image acquisition device, and analyzing and calculating according to the acquired images to acquire the height information of the object to be detected.

Optionally, the number of the projection devices is at least one, and the first image acquisition device and the second image acquisition device are arranged in parallel and are located on one side of the projection device. The projection device can project a larger area to the surface of an object to be measured by the arrangement, and the first image acquisition device and the second image acquisition device can more conveniently acquire partial patterns of the projection area of the projection device

Optionally, the processor includes a height calculation module, the height calculation module includes an initialization module, an acquisition module, a 3D reconstruction module, a data fusion module, and an output module, and the initialization module is configured to import a preset or calibrated position relationship or calibration parameters between the projection apparatus and the first image acquisition apparatus or the second image acquisition apparatus; the acquisition module is used for acquiring image sequences acquired by the first image acquisition device and the second image acquisition device; the 3D reconstruction module is used for respectively calculating the height data of the first acquisition area and the second acquisition area; the data fusion module is used for fusing the height data of the overlapping region of the first acquisition region and the second acquisition region and the overlapping region of the second acquisition region and the first acquisition region; the output module is used for outputting the height information of the object to be measured.

The invention also provides a high-speed double-camera three-dimensional detection method which is matched with the high-speed double-camera three-dimensional detection system and is applied to the high-speed double-camera three-dimensional detection system, and the method comprises the following steps:

s10, projecting a structured light pattern to the surface of the object to be measured by using a projection device;

s20, acquiring a projection area pattern by using a first image acquisition device and a second image acquisition device;

and S30, analyzing the projection area pattern through the processor to acquire the height information of the object to be measured.

Optionally, step S30 specifically includes:

s300, importing preset or calibrated position relationships or calibration parameters and the like between the projection device and the first image acquisition device and between the projection device and the second image acquisition device by using an initialization module in the processor;

s301, acquiring image sequences acquired by a first image acquisition device and a second image acquisition device by using an acquisition module;

s302, respectively calculating height data of a first acquisition area and a second acquisition area by using a 3D reconstruction module;

s303, fusing the height data of the overlapping region of the first acquisition region and the second acquisition region and the overlapping region of the second acquisition region and the first acquisition region by using a data fusion module.

Has the advantages that: the projection area is generated through one projection device, the projection area is acquired through the first image acquisition device and the second image acquisition device, two detection areas are obtained on the premise that the accuracy of the images acquired by the first image acquisition device and the second image acquisition device is guaranteed, the acquired images in the first acquisition area and the second acquisition area are acquired and processed through the processor, the same projection area has higher image resolution and higher data transmission and processing speed, and therefore the three-dimensional detection speed and the detection accuracy are improved.

Drawings

Fig. 1 is a schematic structural diagram of a high-speed dual-camera three-dimensional detection system provided by the present invention.

Fig. 2 is a schematic diagram of internal modules of a processor according to the present invention.

Fig. 3 is a schematic structural diagram of the first image capturing device and the second image capturing device arranged in tandem according to the present invention.

Fig. 4 is a schematic structural diagram of the first image capturing device and the second image capturing device according to the present invention when they are arranged in the left-right direction.

Fig. 5 is a schematic structural view of the projection region and the acquisition region acquired in the arrangement of fig. 3.

Fig. 6 is a schematic structural view of the projection region and the acquisition region acquired in the arrangement of fig. 4.

Fig. 7 is a flow chart of a high-speed dual-camera three-dimensional detection method provided by the invention.

FIG. 8 is a flow chart of a processing method of a processor according to the present invention.

Description of reference numerals: 1. a projection device; 2. a first image acquisition device; 3. a second image acquisition device; 5. A processor; 10. a projection area; 20. a first acquisition region; 30. a second acquisition region; 31. an overlap region; 50. initializing a module; 51. an acquisition module; 52. a 3D reconstruction module; 53. a data fusion module; 54. and an output module.

Detailed Description

The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.

In the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, which are merely for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention; the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; furthermore, unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, as they may be fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

Example 1

As shown in fig. 1, a high-speed dual-camera three-dimensional detection system includes a projection device 1, a first image acquisition device 2, a second image acquisition device 3 and a processor 5; the projection device 1 is used for projecting at least one structured light pattern to the surface of an object to be measured; the first image acquisition device 2 and the second image acquisition device 3 are arranged above an object to be measured, the first image acquisition device 2 is used for acquiring a part of a projection area pattern of the projection device 1, and the acquisition area is configured as a first acquisition area 20; the second image acquisition device 3 is used for acquiring a partial projection area pattern of the projection device 1, the acquisition area is configured into a second acquisition area 30, and the second acquisition area 30 and the first acquisition area 20 are partially overlapped; the processor 5 is configured to obtain images acquired by the first image acquisition device 2 and the second image acquisition device 3, perform analysis calculation according to the acquired images, and obtain height information of the object to be measured.

As shown in fig. 1, in the present embodiment, the projection device 1 may be a projector capable of projecting at least one structured light pattern onto the surface of the object to be measured, and the first image capturing device 2 and the second image capturing device 3 are both cameras. Specifically, the first image capturing device 2 and the second image capturing device 3 have two arrangements: the first arrangement is that two cameras are arranged in front of each other (as shown in fig. 3), the projection area and the acquisition area acquired by the arrangement are arranged in front of each other as shown in fig. 5, and correspondingly, the camera acquisition area is also arranged in front of each other relative to the projection area, the trapezoidal area represents the projection area 10, the two square areas represent the first acquisition area 20 and the second acquisition area 30 respectively, the first acquisition area 20 is an FOV1 area, the second acquisition area 30 is an FOV2 area, and the overlapping part of the two square areas is an overlapping area 31, which is an FOV3 area. The second arrangement is that two cameras are arranged side to side (as shown in fig. 4), the projection area and the acquisition area acquired by the arrangement are as shown in fig. 6, the two cameras are arranged side to side, the camera acquisition areas are also arranged side to side relative to the projection area, the trapezoidal area represents the projection area 10, the two square areas represent the first acquisition area 20 and the second acquisition area 30 respectively, the first acquisition area 20 is an FOV1 area, the second acquisition area 30 is an FOV2 area, and the overlapping part of the two square areas is an overlapping area 31, which is an FOV3 area. The relative distance and angle at which the acquisition device and the projection device are placed are set in advance according to the area of the projection device 1 and the overlapping area 31 (FOV 3 area) of the first image acquisition device 2 and the second image acquisition device 3.

As shown in fig. 1, in the present embodiment, the number of the projection apparatuses 1 is one, and the first image capturing apparatus 2 and the second image capturing apparatus 3 are arranged in parallel and are located on the side of the projection apparatus 1. By the arrangement, the patterns of the projection areas acquired by the two image acquisition devices can be maximized.

As shown in fig. 2, the processor 5 includes a height calculating module, the height calculating module includes an initializing module 50, an acquiring module 51, a 3D reconstructing module 52, a data fusing module 53 and an output module 54, the initializing module 50 is configured to import a preset or calibrated position relationship or calibration parameters between the projection apparatus and the first image acquiring apparatus or the second image acquiring apparatus; the acquisition module 51 is configured to acquire an image sequence acquired by the first image acquisition device 2 and the second image acquisition device 3; the 3D reconstruction module 52 is configured to calculate height data of the first acquisition region 20 and the second acquisition region 30, respectively; the data fusion module 53 is configured to fuse the height data of the overlapping area 31 of the first acquisition area 20 and the second acquisition area 30 and the overlapping area 31 of the second acquisition area 30 and the first acquisition area 20; the output module 54 is used for outputting the height information of the object to be measured. Further, the output module 54 may be connected to a display device to transmit the height information to the display device, which is more intuitive.

The detection system generates a projection area through the projection device 1, acquires a projection area through the first image acquisition device 2 and the second image acquisition device 3, acquires two detection areas on the premise of ensuring the acquired image precision of the first image acquisition device 2 and the second image acquisition device 3, and the processor 5 acquires and processes the acquired images in the first acquisition area 20 and the second acquisition area 30, so that the same projection area can have the advantages of acquiring higher image resolution and faster data transmission and processing speed, and the three-dimensional detection speed and detection precision are improved.

Example 2

The structure of the high-speed dual-camera three-dimensional detection system provided in this embodiment is substantially the same as that of embodiment 1, and the main difference is that the number of the projection devices 1 is two, the first image acquisition device 2 and the second image acquisition device 3 are arranged in parallel, and the two projection devices 1 are respectively symmetrically arranged at two sides of the first image acquisition device 2 and the second image acquisition device 3. By arranging the two projection devices 1, the problems of shadow generation, light reflection and the like of a detection target can be solved, and the detection precision is improved.

Example 3

As shown in fig. 7, the present invention provides a high-speed dual-camera three-dimensional detection method, which is applied to the high-speed dual-camera three-dimensional detection system, and includes:

s10, projecting a structured light pattern to the surface of the object to be measured by using the projection device 1;

s20, acquiring a projection area pattern by using the first image acquisition device 2 and the second image acquisition device 3;

s30, analyzing the projection area pattern through the processor 5 to acquire the height information of the object to be measured; as shown in fig. 8, step S30 specifically includes:

s300, importing preset or calibrated position relations or calibration parameters and the like between the projection device and the first image acquisition device and between the projection device and the second image acquisition device by using an initialization module 50 in the processor;

s301, acquiring an image sequence acquired by a first image acquisition device 2 and a second image acquisition device 3 by using an acquisition module 51, wherein the image sequence refers to one or more images acquired by the first image acquisition device 2 and the second image acquisition device 3, and the images form a sequence;

s302, respectively calculating height data of a first acquisition area and a second acquisition area by using the 3D reconstruction module 52, wherein the first acquisition area is an FOV1 area, and the second acquisition area is an FOV2 area;

s303, the data fusion module 53 fuses the height data of the overlapping region of the first acquisition region 20 and the second acquisition region 30 and the overlapping region of the second acquisition region 30 and the first acquisition region 20. For convenience of the following description, the overlapping region of the primary acquisition region 20 with the secondary acquisition region 30 may be designated as N1 and the overlapping region of the secondary acquisition region 30 with the primary acquisition region 20 as N2, with the height data calculated by N1 and N2 being substantially coincident, since N1 and N2 refer to the same region.

According to the three-dimensional detection method, the first image acquisition device 2 and the second image acquisition device 3 are used for acquiring the patterns of the projection areas, the processor 5 is used for acquiring and processing the images acquired in the first acquisition area 20 and the second acquisition area 30, compared with a comparison document 1 (with the publication number being CN 211042118U) in the technical background, the processor 5 in the technical scheme is not required to divide the acquired images to acquire different detection areas, only the images acquired by the first image acquisition device 2 and the second image acquisition device 3 are required to be compared, and the calculated height data of the FOV1 area and the FOV2 area are fused and combined, so that the whole calculation process is simple and convenient. The detection method can obtain the height information of a larger area at the same acquisition speed, and improves the three-dimensional detection speed.

In the description herein, references to the description of the terms "one embodiment," "certain embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.