CN213069850U

CN213069850U - Wood block direction recognition device based on machine vision technology

Info

Publication number: CN213069850U
Application number: CN202021693880.2U
Authority: CN
Inventors: 张庆久
Original assignee: Shanghai Gene Automation Technology Co ltd
Current assignee: Shanghai Gene Automation Technology Co ltd
Priority date: 2020-08-14
Filing date: 2020-08-14
Publication date: 2021-04-27
Anticipated expiration: 2030-08-14

Abstract

The utility model provides a wood block direction recognition device based on machine vision technology, which is characterized in that the wood block direction recognition device comprises an image acquisition module and an image processing module, wherein the image acquisition module is connected with the image processing module, the image acquisition module comprises an industrial camera, a lens and a light source, the lens is installed on the upper side of the industrial camera, the industrial camera is installed on a bracket, the light source is installed on one side of the industrial camera, and the light source is installed on a lifting bracket; the utility model provides a based on machine vision technique billet direction recognition device, the device not only can be used for discerning the billet direction, also can be used for discerning similar applied scene, like fragment of brick or other products etc.. The device consists of an image acquisition module and an image processing module. The image acquisition module mainly comprises an industrial camera, a lens and a light source, and the image processing module mainly comprises a visual industrial personal computer and executed algorithm software. The device can complete the calculation of the direction only by acquiring one image.

Description

Wood block direction recognition device based on machine vision technology

Technical Field

The utility model discloses utilize machine vision technique to discern the orientation of putting of billet, for the unloading provides key direction information on the automation of billet, can be applied to billet production and processing field.

Background

In the wood storage and processing industry, the degree of automation and scale is increasing. The mass imported wood needs further processing and is made into a semi-finished product for other middle and downstream enterprises to use. During such pre-processing, automated equipment is required to operate. The method has the advantages that the method has the important step that the wood is subjected to normative feeding, and the direction of fed wood blocks is kept consistent. The wood blocks are generally in a stacking form after being transported, and the direction of each layer is consistent, namely the horizontal direction or the vertical direction. When getting the material with automatic equipment, the level or the vertical direction that will know the billet in advance just can be correct carry out the material loading operation, and this recognition rate must be very fast moreover, can not too much low influence go up unloading efficiency, but the discovery has the device yet to satisfy this requirement at present.

SUMMERY OF THE UTILITY MODEL

According to the technical problem, the utility model provides a wood block direction recognition device based on machine vision technology, which is characterized in that the device comprises an image acquisition module and an image processing module, wherein the image acquisition module is connected with the image processing module, the image acquisition module comprises an industrial camera, a lens and a light source, the lens is arranged on the upper side of the industrial camera, the industrial camera is arranged on a bracket, the light source is arranged on one side of the industrial camera, and the light source is arranged on a lifting bracket; the image processing module is a visual manual control mechanism.

The industrial camera is connected with a computer, and the computer is provided with a signal triggering module.

The light source is an LED light source

The image processing module mainly comprises a visual industrial personal computer and executed algorithm software.

A wood block direction recognition device based on a machine vision technology comprises the following specific operation methods:

(1) installing a support and a telescopic support on a wood block conveying field, respectively installing an industrial camera and a light source on the support, then installing a lens on the industrial camera, and adjusting the light source according to the test requirement;

(2) the industrial camera monitors the signal, the industrial camera acquires an image through light source irradiation, and the signal shot by the industrial camera is transmitted to the image processing module;

(3) the image processing module extracts boundary points of pictures sent by the industrial camera;

(5) the gradient direction to billet conveying place boundary point is makeed statistics of, and is divided into n with 360 degrees, and n sets up as required, if: 720, each representing 0.5 degree, counting bits, and counting the bits into corresponding counting bits according to the angle value of each boundary point;

(6) performing appropriate smoothing on the statistical result, wherein a weighted average is adopted, that is, a value of a certain number of degrees (for example, a value within ± 5 degrees) around each statistical bit is averaged to be used as the value of the statistical bit;

(7) selecting a statistical position corresponding to the maximum value, calculating an angle (angle A) corresponding to the statistical position, and adding 90 degrees to the angle A to obtain the direction of the wood block;

(8) and the image processing module calculates the direction of the wood block, and the recognition result is sent to an observer after the calculation is finished. The utility model has the advantages that: the utility model provides a based on machine vision technique billet direction recognition device, the device not only can be used for discerning the billet direction, also can be used for discerning similar applied scene, like fragment of brick or other products etc.. The device consists of an image acquisition module and an image processing module. The image acquisition module mainly comprises an industrial camera, a lens and a light source, and the image processing module mainly comprises a visual industrial personal computer and executed algorithm software. The device can complete the calculation of the direction only by acquiring one image.

Drawings

FIG. 1 is a flow chart of the present invention

FIG. 2 is the algorithm flow chart of the present invention

Fig. 3 is a graph of the wood direction calculation result of the present invention (thin lines are extracted boundary points, thick lines are calculated directions).

Fig. 4 is the schematic diagram of the principle of the wood direction recognition device of the present invention.

Fig. 5 is a schematic structural diagram of the present invention.

As shown, an industrial camera 1, a lens 2, a light source 3.

Detailed Description

Example 1

The utility model provides a wood block direction recognition device based on machine vision technology, which is characterized in that the wood block direction recognition device comprises an image acquisition module and an image processing module, wherein the image acquisition module is connected with the image processing module, the image acquisition module comprises an industrial camera, a lens and a light source, the lens is installed on the upper side of the industrial camera, the industrial camera is installed on a bracket, the light source is installed on one side of the industrial camera, and the light source is installed on a lifting bracket; the image processing module is a visual manual control mechanism. The industrial camera is connected with a computer, and the computer is provided with a signal triggering module. The light source is an LED light source, and the image processing module is mainly a visual industrial personal computer and executed algorithm software.

Example 2

installing a support and a telescopic support on a wood block conveying field, respectively installing an industrial camera and a light source on the support, then installing a lens on the industrial camera, and adjusting the light source according to the test requirement;

the industrial camera monitors the signal, the industrial camera acquires an image through light source irradiation, and the signal shot by the industrial camera is transmitted to the image processing module;

the image processing module extracts boundary points of pictures sent by the industrial camera;

the gradient direction to billet conveying place boundary point is makeed statistics of, and is divided into n with 360 degrees, and n sets up as required, if: 720, each representing 0.5 degree, counting bits, and counting the bits into corresponding counting bits according to the angle value of each boundary point;

performing appropriate smoothing on the statistical result, wherein a weighted average is adopted, that is, a value of a certain number of degrees (for example, a value within ± 5 degrees) around each statistical bit is averaged to be used as the value of the statistical bit;

selecting a statistical position corresponding to the maximum value, calculating an angle (angle A) corresponding to the statistical position, and adding 90 degrees to the angle A to obtain the direction of the wood block;

and the image processing module calculates the direction of the wood block, and the recognition result is sent to an observer after the calculation is finished.

Example 3

The image acquisition module is located directly over the wood block plane, and the camera can shoot most wood block areas, and adjust light source and lens parameters to enable the wood block boundaries to be clearly seen in the image. An industrial personal computer is additionally connected to the camera and to external automation devices. If shown in fig. 4.

The working process is as follows:

and after the visual industrial personal computer receives the trigger signal, the industrial camera is scheduled to shoot the image.

After the shot image is received, gradient calculation is carried out on the image, a point with a larger gradient value is found out, and the point is used as a boundary point with a larger color change.

And carrying out operations such as statistics, filtering and the like on the directions of the boundary points, ensuring that the statistical value corresponding to points with multiple gradient directions is the largest, and calculating the direction of the wood block according to the vertical relation between the gradient direction and the direction of the wood block.

And changing the direction of the wood blocks into a reasonable value, and sending the value to automatic loading and unloading equipment.

Conclusion

The method has the advantages that the calculation speed is high, the precision can be changed according to the visual condition of the wood block, the control can be generally controlled within 5 degrees, and the requirements for identifying whether the wood block is horizontally placed or vertically placed can be completely met.

The basic principles and the main features of the invention and the advantages of the invention have been shown and described above. The utility model discloses each part that mentions is the common technique in prior art, and the technical personnel of this trade should understand, the utility model discloses do not receive the restriction of above-mentioned embodiment, the description only is the explanation in above-mentioned embodiment and the description the principle of the utility model, under the prerequisite that does not deviate from the spirit and the scope of the utility model, the utility model discloses still can have various changes and improvement, these changes and improvement all fall into the protection of claim the utility model is within the scope. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims

1. The utility model provides a wood block direction recognition device based on machine vision technique, its characterized in that includes image acquisition module and image processing module, image acquisition module and image processing module are connected, and image acquisition module includes industry camera, camera lens, light source, the camera lens is installed to industry camera upside, industry camera installs on the support, the light source is installed to industry camera one side, the light source is installed on lifting support.

2. The wood block direction recognition apparatus based on machine vision technology as claimed in claim 1, wherein the image processing module is a vision manual mechanism.

3. The wood block direction recognition device based on the machine vision technology as claimed in claim 1, wherein the industrial camera is connected with a computer, and the computer is provided with a signal triggering module.

4. The wood block direction recognition device based on machine vision technology as claimed in claim 1, wherein the light source is an LED light source.