CN212093316U - Wood defect detection device based on kinect camera - Google Patents
Wood defect detection device based on kinect camera Download PDFInfo
- Publication number
- CN212093316U CN212093316U CN202020177132.2U CN202020177132U CN212093316U CN 212093316 U CN212093316 U CN 212093316U CN 202020177132 U CN202020177132 U CN 202020177132U CN 212093316 U CN212093316 U CN 212093316U
- Authority
- CN
- China
- Prior art keywords
- wood
- conveyor belt
- pusher
- camera
- defect
- 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.)
- Expired - Fee Related
Links
- 239000002023 wood Substances 0.000 title claims abstract description 68
- 230000007547 defect Effects 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 title claims description 14
- 238000011161 development Methods 0.000 claims description 6
- 238000003491 array Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 8
- 230000002950 deficient Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 3
- 230000018109 developmental process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses a wood defect detecting device based on a kinect camera, which comprises a conveying belt for conveying wood; a wood defect image collecting device is correspondingly arranged above the front end of the conveyor belt; LED lamps are correspondingly arranged on the front side and the rear side of the wood defect image collecting device; the wood defect image collecting device is also connected with a computer processor. This device can gather timber surface image information through kinect camera, and carry out corresponding processing through computer processor, judge whether this timber surface has the defect, and there is the timber of defect at driven in-process, promote forward in the collection box that advances this timber on the conveyer belt to the opposite side via the corresponding catch bar that drives of computer processor control impeller, thereby realize the function that wood defect detected and separated defective timber, not only can increase the degree of accuracy that detects, improve work efficiency, and very big save operating time, manpower and materials have been saved.
Description
Technical Field
The utility model relates to a wood defect detects technical field, specific wood defect detection device based on kinect camera that says so.
Background
The continuing rise in raw material and labor costs forces wood product enterprises to control costs by improving product quality and increasing productivity. In the wood working process, wood surface defects not only affect the strength of the wood, but also severely affect the quality and appearance of the wood working and wood decoration. In current wood working production, the surface defect detection link mostly still relies on the manual work, and the efficiency of detection can aggravate and descend along with the tired of testing personnel. Because different inspectors know different conditions and wood surface defects are various, manual inspection is difficult to give an objective and accurate evaluation to all surfaces. Meanwhile, the manual detection speed is low, and the efficiency is low, so that the simple, feasible and stable method for detecting the wood surface defects is very important for improving the product quality of wood product enterprises and reducing the production cost.
SUMMERY OF THE UTILITY MODEL
The utility model aims at providing a wood defect detection device based on kinect camera to the not enough of prior art existence.
The technical scheme is as follows: the utility model provides a technical scheme that the problem adopted does: a kind of timber defect checkout gear based on kinect camera, including the conveyer belt used for conveying the timber; a wood defect image collecting device is correspondingly arranged above the front end of the conveyor belt; LED lamps are correspondingly arranged on the front side and the rear side of the wood defect image collecting device; the wood defect image collecting device is also connected with a computer processor; the pusher is also arranged at the side surface position of the rear end of the conveyor belt, the front end of the pusher is provided with a push rod which is positioned at one side above the conveyor belt and can be driven by the pusher to push forwards, the rod end of the pusher is also provided with a ball seat, a ball is also embedded in the ball seat, and the ball can rotate in the ball seat and cannot fall off from the ball seat; and the other side of the rear end of the conveyor belt is provided with a collecting box corresponding to the pusher; the computer processor is correspondingly connected with the pusher, and can correspondingly control the pusher to drive the push rod to push forwards so as to push the wood on the conveyor belt into the collecting box.
Preferably, the wood defect image collecting device is correspondingly set as a Kinect camera, and the Kinect camera is provided with three image capturing devices which are sequentially set as an infrared projector, a color camera and an infrared camera; and the height between the kinect camera and the conveyor belt is set to be 0.8-1.2 m.
Preferably, the computer processor is internally provided with an i7 processor and a WINDOW7 flagship edition operating system, the development language is programmed by PYTHON, and the development tool is IDLE.
Preferably, the pushers are arranged in two on the side of the conveyor belt.
Preferably, the collecting boxes are provided with two corresponding collecting boxes on the side surface of the conveyor belt.
Preferably, the kinect camera further comprises a shell, a base, a heat radiator, four screws of different types, a three-part main board, a fourteen-chip and four microphone arrays.
Has the advantages that: compared with the prior art, the utility model, have following advantage:
(1) the device can collect image information of the surface of the wood through the kinect camera, and carry out corresponding processing through the computer processor, judge whether the surface of the wood has defects, and if the wood has defects, when the wood is sent to the position corresponding to the pusher, the pusher is controlled by the computer processor to correspondingly drive the push rod to push the wood on the conveyor belt forward to the collecting box at the other side after the conveyor belt stops, thereby realizing the functions of detecting the wood defects and separating the defective wood, not only increasing the detection accuracy and improving the working efficiency, but also greatly saving the working time and manpower and material resources;
(2) in the device, when the wood is conveyed by the conveyor belt and is pushed down by the pusher for separation, the conveyor belt needs to be stopped, but the working efficiency is easily reduced; if push away timber when the conveying away, the speed of conveyer belt is difficult too fast, should set up properly, and in order to increase the stability when the in-process timber of conveying pushes away from, at the corresponding installation ball seat of the rod end of catch bar and inlay the dress ball, when pushing away timber like this, the corresponding contact timber of ball pushes away timber from the conveyer belt when rolling, can be more safe convenient, whole process is more smooth and easy, more stable.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a structural diagram of a middle driving unit of the present invention;
fig. 3 is a diagram of the kinect camera structure of the present invention.
Detailed Description
The present invention will be further clarified by the following embodiments with reference to the attached drawings, which are implemented on the premise of the technical solution of the present invention, and it should be understood that these embodiments are only used for illustrating the present invention and are not used for limiting the scope of the present invention.
As shown in fig. 1, 2 and 3, a wood defect detecting apparatus based on a kinect camera includes a conveyor belt 1 for conveying wood; a wood defect image collecting device 2 is correspondingly arranged above the front end of the conveyor belt 1; and the front and back sides of the wood defect image collecting device 2 are correspondingly provided with LED lamps 3; the wood defect image collecting device 2 is also connected with a computer processor 4; a pusher 5 is further installed at the position of the side surface of the rear end of the conveyor belt 1, a push rod 6 is arranged at the front end of the pusher 5, the push rod 6 is located on one side above the conveyor belt 1 and can be driven by the pusher 5 to push forwards, a ball seat 7 is further installed at the rod end, a ball 8 is further embedded in the ball seat 7, and the ball 8 can rotate in the ball seat 7 and cannot fall off from the ball seat; and the other side of the rear end of the conveyor belt 1 is provided with a collecting box 9 corresponding to the pusher 5; the computer processor 4 is correspondingly connected with the pusher 5, and can correspondingly control the pusher 5 to drive the pushing rod 6 to push forwards so as to push the wood 10 on the conveyor belt 1 into the collecting box 9.
The wood-defect image collecting device 2 is correspondingly configured as a Kinect camera provided with three image capturing devices, in turn configured as an infrared projector 22, a color camera 23 and an infrared camera 24.
The computer processor 4 is internally provided with an i7 processor and a WINDOW7 flagship edition operating system correspondingly, a development language adopts PYTHON for programming, and a development tool is IDLE; the pushers 5 are arranged on the side surface of the conveyor belt 1 in total; the collecting boxes 9 are provided with two corresponding collecting boxes on the side surface of the conveyor belt 1; the kinect camera further comprises a shell, a base 21, a heat radiator, four screws of different types, a three-part main board, a fourteen-chip and four microphone arrays.
The defect detection of the device adopts a Kinect core technology, and a developer can acquire depth information of a user through the Kinect and judge the position of the user; the Kinect depth detection adopts a Light Coding mode that an infrared projector projects infrared spectrum to irradiate on wood, and the spectrum is distorted to form speckles. Because the speckles are highly random, the pattern of each speckle in space is not the same. When wood is placed in the space, the infrared camera receives feedback information, and the position of an object can be judged according to speckle patterns on the wood to form a depth image.
In the prior art, a typical wood board defect is divided into a defect area, a stripe area and a non-stripe area; wherein, the defect area is blocky and has the darkest color compared with other parts; the stripes are linear and slightly light in color; the non-stripe part has the lightest color; the detection principle of the device is to extract the characteristics of the defect part in the wood surface image, divide the wood surface image based on the image edge information, judge whether the wood board is defective or not according to the size and the number of the defects, and classify the wood board.
And continuously shooting by adopting a kinect camera to obtain a color image and a depth image of the surface of the wood. In order to enable the depth image to better reflect the surface of the wood, the shooting distance needs to be adjusted, and the optimal distance is 0.8-1.2 m; meanwhile, pixel points in the depth image can express the geometric shape of the surface of the wood more clearly, and subsequent image processing is facilitated.
In the operation process, wood defect data can be influenced by the external environment and errors of measuring equipment and the like, so that noise interference exists in an image shot by the Kinect camera; in order to eliminate noise interference, the device adopts Gaussian filtering to filter the image.
According to the detection principle of the detection system, the gray value of the image defect part on the surface of the wood is smaller than that of the rest part; performing binarization on the image after setting a threshold value by adopting a kinect self-contained threshold value segmentation function; the defect part smaller than the threshold is 0 and is displayed as black, the rest part larger than the threshold is 255 and is displayed as white, the standard carries out segmentation based on image edge information according to the characteristics of the defect part in the extracted wood surface image, and whether the wood board is defective or not is judged according to the size and the number of the defects.
When the device works, the wood board enters an image acquisition area through the power transmission device, the image recognition device starts to acquire images, and the conveying belt keeps moving at the moment. And entering a sorting area after the identification is finished, wherein the sorting device can determine whether the wood is defective according to the identified image information and push the wood into a collection box.
This device can gather timber surface image information through kinect camera, and carry out corresponding processing through computer processor, judge whether this timber surface has the defect, and if there is the defect, when sending timber to the position department corresponding with the impeller, the control conveyer belt stops the back, promote forward the collection case that advances this timber on the conveyer belt to the opposite side via the corresponding catch bar that drives of computer processor control impeller, thereby realize that wood defect detects and the function of coming out defective wood, not only can increase the degree of accuracy that detects, improve work efficiency, and very big save operating time, manpower and materials have been saved.
In the device, when the wood is conveyed by the conveyor belt and is pushed down by the pusher for separation, the conveyor belt needs to be stopped, but the working efficiency is easily reduced; if push away timber when the conveying away, the speed of conveyer belt is difficult too fast, should set up properly, and in order to increase the stability when the in-process timber of conveying pushes away from, at the corresponding installation ball seat of the rod end of catch bar and inlay the dress ball, when pushing away timber like this, the corresponding contact timber of ball pushes away timber from the conveyer belt when rolling, can be more safe convenient, whole process is more smooth and easy, more stable.
The above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the invention and the appended claims, and all equivalent changes and modifications made according to the claims should be included in the scope of the present invention.
Claims (6)
1. The utility model provides a wood defect detection device based on kinect camera which characterized in that: comprising a conveyor belt (1) for conveying wood; a wood defect image collecting device (2) is correspondingly arranged above the front end of the conveyor belt (1); and the front side and the rear side of the wood defect image collecting device (2) are correspondingly provided with LED lamps (3); the wood defect image collecting device (2) is also connected with a computer processor (4); a pusher (5) is further installed at the side position of the rear end of the conveyor belt (1), a push rod (6) is arranged at the front end of the pusher (5), the push rod (6) is located on one side above the conveyor belt (1) and can be driven by the pusher (5) to advance, a ball seat (7) is further installed at the rod end, a ball (8) is further embedded in the ball seat (7), and the ball (8) can rotate in the ball seat (7) and cannot fall off from the ball seat; and the other side of the rear end of the conveyor belt (1) is provided with a collecting box (9) corresponding to the position of the pusher (5); the computer processor (4) is correspondingly connected with the pusher (5), and the pusher (5) can be correspondingly controlled to drive the push rod (6) to push forwards so as to push the wood (10) on the conveyor belt (1) into the collecting box (9).
2. The device as claimed in claim 1, wherein the device comprises: the wood defect image collecting device (2) is correspondingly set as a Kinect camera, the Kinect camera is provided with three image capturing devices which are sequentially set as an infrared projector (22), a color camera (23) and an infrared camera (24); and the height between the kinect camera and the conveyor belt (1) is set to be 0.8-1.2 m.
3. The device as claimed in claim 1, wherein the device comprises: the computer processor (4) is internally provided with an i7 processor and a WINDOW7 flagship edition operating system correspondingly, the development language adopts PYTHON for programming, and the development tool is IDLE.
4. The device as claimed in claim 1, wherein the device comprises: the pushers (5) are arranged on the side surface of the conveyor belt (1) in total.
5. The device as claimed in claim 4, wherein the camera is a kinect camera, and the device comprises: the collecting boxes (9) are provided with two corresponding collecting boxes on the side surface of the conveyor belt (1).
6. The device as claimed in claim 2, wherein the device comprises: the kinect camera further comprises a shell, a base (21), a radiator, four screws of different types, a three-part main board, a fourteen-chip and four microphone arrays.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020177132.2U CN212093316U (en) | 2020-02-17 | 2020-02-17 | Wood defect detection device based on kinect camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020177132.2U CN212093316U (en) | 2020-02-17 | 2020-02-17 | Wood defect detection device based on kinect camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212093316U true CN212093316U (en) | 2020-12-08 |
Family
ID=73631628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020177132.2U Expired - Fee Related CN212093316U (en) | 2020-02-17 | 2020-02-17 | Wood defect detection device based on kinect camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212093316U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113333306A (en) * | 2021-08-09 | 2021-09-03 | 深圳市轻生活科技有限公司 | Sorting method and system for poor chip appearance |
| CN113538428A (en) * | 2021-09-16 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Wood defect detection method, apparatus, medium, and computer program product |
-
2020
- 2020-02-17 CN CN202020177132.2U patent/CN212093316U/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113333306A (en) * | 2021-08-09 | 2021-09-03 | 深圳市轻生活科技有限公司 | Sorting method and system for poor chip appearance |
| CN113333306B (en) * | 2021-08-09 | 2021-10-08 | 深圳市轻生活科技有限公司 | Sorting method and system for poor chip appearance |
| CN113538428A (en) * | 2021-09-16 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Wood defect detection method, apparatus, medium, and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN201223856Y (en) | Bamboo strip automatic sorting apparatus based on machine vision | |
| CN202087540U (en) | Online detector of copper piece appearance defects based on machine vision | |
| CN212093316U (en) | Wood defect detection device based on kinect camera | |
| CN202683498U (en) | Automatic LED (Light-emitting Diode) detection sorting device | |
| CN203750868U (en) | Computer vision-based burr detection device | |
| CN105651782A (en) | Engine cylinder cover defect automatic detection equipment based on machine vision | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN102671870A (en) | Device and method for automatically detecting and sorting light emitting diodes (LEDs) | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN209901748U (en) | Plastic part automatic detection equipment based on machine vision recognition | |
| CN205183172U (en) | A visual inspection device for remote controller button | |
| CN111545483B (en) | Chopstick sorting detection device and detection algorithm thereof | |
| CN106040600A (en) | Automatic sorting method for columnar parts | |
| CN106353336A (en) | Lens coating automatic detection system | |
| CN111889387B (en) | Detection device and image identification method for size and surface defects of safety belt buckle | |
| CN111239142A (en) | Paste appearance defect detection device and method | |
| CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
| CN207593994U (en) | A kind of automatically scanning cutting optimization sorting device | |
| CN111175248B (en) | Intelligent meat quality online detection method and detection system | |
| CN208771900U (en) | CCD automatic sorting device | |
| CN204817231U (en) | Automatic detector | |
| CN109701890A (en) | Magnetic tile surface defect detection and method for sorting | |
| CN211613493U (en) | Electronic component display detection screening plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201208 |