Scattered material three-dimensional feature high-precision recognition device based on multi-sensor fusion

Abstract

A scattered material three-dimensional feature high-precision recognition device based on multi-sensor fusion is used for achieving rapid and high-precision recognition and classification of scattered materials. The device comprises a working platform, a charging tray, a top visual identification unit, an XY bidirectional precise transplanting mechanism, a high-precision detection assembly and a main control and data processing module. Wherein the top visual identification unit adopts a high-resolution industrial camera to carry out global image acquisition and preliminarily position a material contour; the high-precision detection assembly integrates a visual camera and a laser distance measuring sensor, local precise scanning is achieved through a precise transplanting mechanism, and three-dimensional feature data of materials are obtained. The main control module combines multi-source data fusion and a three-dimensional reconstruction algorithm, the recognition precision and efficiency are improved, and the method can be widely applied to the fields of industrial sorting, precision manufacturing and the like.

Description

Technical Field

[0001] This utility model relates to the field of visual recognition device technology, and in particular to a high-precision recognition device for three-dimensional features of scattered materials based on multi-sensor fusion. Background Technology

[0002] In the fields of industrial automation and intelligent manufacturing, rapid and high-precision identification and 3D feature extraction of scattered materials are among the key technologies. Traditional manual sorting methods are inefficient, costly, and difficult to guarantee consistency, while existing automated identification equipment still has significant limitations in accuracy and adaptability in complex scenarios.

[0003] Currently, machine vision-based material recognition technologies are mainly divided into monocular vision, binocular stereo vision, and structured light 3D scanning. Monocular vision systems are simple in structure and low in cost, but can only acquire two-dimensional information, making it difficult to accurately measure the geometric dimensions and spatial orientation of materials. Binocular stereo vision can recover three-dimensional information, but it is highly dependent on lighting conditions and texture features, and performs poorly on smooth surfaces or low-contrast materials. Structured light 3D scanning has high accuracy, but the equipment is complex and expensive, and it is difficult to adapt to the rapid detection needs of dynamically scattered materials.

[0004] Therefore, in view of the shortcomings of the existing technology, it is necessary to design a high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion to solve the above problems.

[0005] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solution of this utility model and facilitating the understanding of those skilled in the art. It should not be assumed that the above content is known to those skilled in the art simply because it has been described in the background section of this utility model. Utility Model Content

[0006] To overcome the shortcomings of the prior art, the present invention discloses a high-precision three-dimensional feature recognition device for scattered materials based on multi-sensor fusion, which is used to realize rapid and high-precision three-dimensional recognition and classification of scattered materials.

[0007] This utility model discloses a high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion, comprising:

[0008] The working platform is used to support the entire device;

[0009] The material tray, located at the top of the work platform, is used to hold the scattered materials to be identified;

[0010] The top vision recognition unit includes a first vision recognition camera mounted directly above the material tray, used for global image acquisition and to identify the outer contour and position information of scattered materials.

[0011] The XY bidirectional precision transfer mechanism is set on a working platform on one side of the material tray and includes an X-axis linear module and a Y-axis linear module that are vertically linked to each other.

[0012] The high-precision detection component, which includes a second vision recognition camera and a laser rangefinder, is fixed to the moving end of the XY bidirectional precision transfer mechanism via a mounting plate. It is used for localized precise measurement and identification of the precise outer contour, shape, and height information of the material.

[0013] The main control and data processing module is connected to the top vision recognition unit, the XY bidirectional precision transplanting mechanism, and the high-precision detection component to control the operation of the device and to model and process the collected data.

[0014] The preferred technical solution is as follows: the X-axis linear module is fixed to the working platform, and one end of the Y-axis linear module is connected to the moving end of the X-axis linear module to form a T-shaped motion mechanism, which ensures motion accuracy while reducing space occupation.

[0015] Preferred technical solution: Both the X-axis linear module and the Y-axis linear module are equipped with grating rulers to improve motion accuracy.

[0016] Preferred technical solution: The first visual recognition camera is an industrial-grade area array camera.

[0017] Preferred technical solution: Industrial-grade area array camera with a resolution of no less than 20 million pixels and an adjustable frame rate range of 30-120fps.

[0018] Preferred technical solution: The tray is made of a high light transmittance material; a plate-shaped light source is provided below the tray.

[0019] Preferred technical solution: The plate-type light source has a multi-band spectrum switching function, including visible light and near-infrared illumination modes.

[0020] Preferred technical solution: A ring-shaped fill light is provided below the second visual recognition camera to enhance the local lighting effect.

[0021] Preferred technical solution: The main control and data processing module has a built-in multi-source data fusion module and a 3D reconstruction algorithm library to achieve spatiotemporal registration of 2D images and laser ranging data.

[0022] Due to the application of the above technical solution, the beneficial effects of this utility model compared with the prior art are as follows:

[0023] 1) The collaborative working mode of the top vision recognition unit and the movable high-precision detection component is adopted to realize dual data acquisition of global recognition and local precision measurement.

[0024] 2) A specially designed transmissive lighting system (plate-type multispectral light source + high transmittance material tray) combined with a ring supplement light is used to adapt to the imaging needs of different materials.

[0025] 3) The XY bidirectional precision transplanting mechanism, in conjunction with the grating ruler, ensures the positioning accuracy of the high-precision detection components.

[0026] 4) The main control module integrates multi-source data fusion and 3D reconstruction algorithms to improve recognition efficiency and accuracy. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of this utility model or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this utility model. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a diagram of the high-precision three-dimensional feature recognition device for scattered materials based on multi-sensor fusion, according to this utility model.

[0029] In the attached diagrams above, 1 is the working platform; 2 is the material tray; 3 is the first vision recognition camera; 4 is the XY bidirectional precision transplanting mechanism; 41 is the X-axis linear module; 42 is the Y-axis linear module; 5 is the high-precision detection component; 51 is the second vision recognition camera; 52 is the laser rangefinder; 53 is the mounting plate; 54 is the ring light; and 6 is the plate-shaped light source. Detailed Implementation

[0030] The following specific embodiments illustrate the implementation of this utility model. Those skilled in the art can easily understand other advantages and effects of this utility model from the content disclosed in this specification.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the description of embodiments of this application herein. Furthermore, the terms "comprising" and "having," and their synonyms, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing the present invention and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0033] Furthermore, in addition to indicating direction or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this utility model according to the specific circumstances.

[0034] Furthermore, the terms "installation," "setting," "equipped with," "connection," "linking," "fitting," and "fitting" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Similarly, "fitting" can mean completely or partially fitted. Those skilled in the art can understand the specific meaning of the above terms in this utility model based on the specific circumstances.

[0035] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0036] Example:

[0037] like Figure 1 As shown, this utility model discloses a high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion, including a working platform 1, a material tray 2, a top vision recognition unit, an XY bidirectional precision transfer mechanism 4, a high-precision detection component 5, and a main control and data processing module. The main components of this utility model will be described in detail below:

[0038] Working platform 1, as the supporting base of the device, is made of rigid materials to ensure stability;

[0039] The material tray 2, located on the upper part of the working platform 1, is made of high light transmittance material and is used to hold scattered materials; a plate-type light source 6 is installed below it, which supports the switching of visible light and near-infrared multi-band spectrum to adapt to the lighting needs of different materials.

[0040] The top visual recognition unit includes a first visual recognition camera 3 mounted directly above the material tray 2; the first visual recognition camera 3 is a 20-megapixel industrial-grade area array camera with an adjustable frame rate (30-120fps) for global image acquisition and recognition of the outer contour and position information of scattered materials.

[0041] The XY bidirectional precision transplanting mechanism 4 consists of a T-shaped linkage structure composed of an X-axis linear module 41 and a Y-axis linear module 42, both equipped with grating rulers; the X-axis module is fixed to the working platform 1, and the Y-axis module is connected to the X-axis through the moving end to achieve high-precision two-dimensional planar motion;

[0042] The high-precision detection component 5 is fixed to the moving end of the XY bidirectional precision transfer mechanism 4 via the mounting plate 53. It integrates a second vision recognition camera 51 and a laser range sensor 52. A ring light 54 is provided below the second vision recognition camera 51 for local precise measurement and identification of the precise outer contour, shape and height information of the material.

[0043] The main control and data processing module is connected to the top visual recognition unit 3, the XY bidirectional precision transplanting mechanism 4, and the high-precision detection component 5. It has a built-in multi-source data fusion module and a three-dimensional reconstruction algorithm library to coordinate the operation of each component and complete data modeling.

[0044] The method of use and principle of this utility model are as follows:

[0045] Global scan phase:

[0046] The plate-type light source 6 activates the visible light mode and illuminates the transparent material tray 2. The first vision recognition camera 3 captures a global image of the material tray 2, extracts the outline and position of the scattered materials, and generates preliminary sorting coordinates.

[0047] Local fine measurement stage:

[0048] The main control module drives the XY bidirectional precision transfer mechanism 4 to move according to global data, positioning the high-precision detection component 5 above the target material; the ring light 54 is turned on, and the second vision recognition camera 51 captures a local high-definition image to identify the precise outer contour and shape of the material; at the same time, the laser range sensor 52 measures the height information of the material.

[0049] Data fusion and 3D reconstruction:

[0050] The main control module spatiotemporally registers the global two-dimensional image with the local three-dimensional data, integrates multi-source information such as the total type of the device, its external dimensions, the number of leads, its height, and pattern information, reconstructs the complete three-dimensional model of the material, and outputs accurate dimensions, orientation, and classification results.

[0051] Finally, it should be noted that the above are merely preferred embodiments of the present utility model and are not intended to limit the present utility model. Although the present utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present utility model should be included within the protection scope of the present utility model.

Claims

1. A high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion, characterized in that, include: Work platform (1); The material tray (2) is set at the upper end of the working platform (1); The top visual recognition unit includes a first visual recognition camera (3) mounted directly above the tray (2). The XY bidirectional precision transplanting mechanism (4) is set on the working platform (1) on one side of the material tray (2), and includes an X-axis linear module (41) and a Y-axis linear module (42) that are vertically linked to each other. The high-precision detection component (5) includes a second visual recognition camera (51) and a laser rangefinder (52), which are fixed to the moving end of the XY bidirectional precision transplanting mechanism (4) by a mounting plate (53); The main control and data processing module is connected to the top visual recognition unit, the XY bidirectional precision transplanting mechanism (4), and the high-precision detection component (5) via signal connection.

2. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: The X-axis linear module (41) is fixed to the working platform (1), and one end of the Y-axis linear module (42) is connected to the moving end of the X-axis linear module (41) to form a T-shaped motion mechanism.

3. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: Both the X-axis linear module (41) and the Y-axis linear module (42) are equipped with grating rulers.

4. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: The first visual recognition camera (3) is an industrial-grade area array camera.

5. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 4, characterized in that: The industrial-grade area array camera has a resolution of no less than 20 million pixels and an adjustable frame rate range of 30-120fps.

6. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: The tray (2) is made of a high light transmittance material; a plate-shaped light source (6) is provided below the tray (2).

7. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 6, characterized in that: The plate-type light source (6) has a multi-band spectrum switching function, including visible light and near-infrared illumination modes.

8. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: A ring light (54) is provided below the second visual recognition camera (51).

9. The high-precision identification device for three-dimensional features of scattered materials based on multi-sensor fusion according to claim 1, characterized in that: The main control and data processing module has a built-in multi-source data fusion module and a 3D reconstruction algorithm library.

Images