CN210666871U - Quick detection device of pig body chi - Google Patents
Quick detection device of pig body chi Download PDFInfo
- Publication number
- CN210666871U CN210666871U CN201920412079.7U CN201920412079U CN210666871U CN 210666871 U CN210666871 U CN 210666871U CN 201920412079 U CN201920412079 U CN 201920412079U CN 210666871 U CN210666871 U CN 210666871U
- Authority
- CN
- China
- Prior art keywords
- pig
- pig body
- mobile communication
- communication terminal
- image
- 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
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the utility model discloses pig body chi short-term test device, include: the system comprises a wireless radio frequency electronic ear tag, a card reader, a binocular camera and a mobile communication terminal; the card reader reads a wireless radio frequency electronic ear tag worn on a pig ear and uploads the read tag information to the mobile communication terminal; the binocular camera is erected in a manner of being perpendicular to the ground and parallel to the pig waterer and is used for shooting an image of a pig body and uploading the image to the mobile communication terminal; the mobile communication terminal collects pig body images, obtains pig body depth images according to the pig body images and then obtains pig body outlines, and a pig body ruler detection key point is screened out based on a concave structure inflection point extraction algorithm to calculate the pig body ruler. Adopt the utility model discloses, can be convenient and accurate acquire pig body chi.
Description
Technical Field
The utility model relates to a detection area especially relates to a pig body chi short-term test device.
Background
The body size of the pig is an important parameter for evaluating the growth of the pig and is also an important index for breeding the pig and evaluating the meat quality. The body length, body width, body height, chest circumference and other three-dimensional body scales of the pigs are in positive correlation with the body mass, and the body mass can be estimated by using the body scales. Although experienced farmers can also estimate body quality by visual inspection of the body ruler, this method cannot be quickly reproduced and generalized. The machine vision technology can accurately measure the shape and the representation information of the object without contact, avoid the stress of animals caused by the traditional measuring method and improve the welfare of the animals.
Currently, the body size and the characters of animals are measured by using a machine vision technology. The method for obtaining the height of the pig body by taking pictures from the side surface of a single camera is direct, but the pigs are easy to be shielded, and the method is difficult to be applied to a pig farm. The method of placing the camera on the side is mostly applied to measuring the body shape of the cow passing through a fixed line.
SUMMERY OF THE UTILITY MODEL
In order to solve the problem, the utility model provides a pig body chi short-term test device can be under the condition of the contactless pig body, convenient and accurate acquireing pig body chi.
Based on this, the utility model provides a pig body chi short-term test device, the device includes: the system comprises a wireless radio frequency electronic ear tag, a card reader, a binocular camera and a mobile communication terminal;
the card reader reads a wireless radio frequency electronic ear tag worn on a pig ear and uploads the read tag information to the mobile communication terminal;
the binocular camera is erected in a manner of being perpendicular to the ground and parallel to the pig waterer and is used for shooting an image of a pig body and uploading the image to the mobile communication terminal;
the mobile communication terminal collects pig body images, obtains pig body depth images according to the pig body images and then obtains pig body outlines, and a pig body ruler detection key point is screened out based on a concave structure inflection point extraction algorithm to calculate the pig body ruler.
Wherein the depth image acquisition comprises:
carrying out Gaussian blur processing on a pig body image to be processed to obtain an edge image;
calculating the depth value of each pixel point at the edge of the image so as to obtain a sparse depth map;
and carrying out interpolation processing on the obtained sparse depth map to obtain a depth image.
Wherein, the depth image can be filtered after the depth image is obtained.
Wherein, the pig body contour of acquireing includes: calculating gradient information of the pig body image, calculating structural features of the image according to the gradient information, calculating feature vectors of the structural features, extracting vertical components of the feature vectors, and extracting edge pixel points of the image according to the vertical components of the feature vectors.
Wherein the extracting edge pixel points of the image according to the vertical component of the feature vector comprises: and acquiring vertical direction information of the vertical component of the feature vector, extracting edge pixel points of the image through a Gaussian difference algorithm according to the vertical direction information, and generating contour lines according to the edge pixel points.
The method comprises the steps that a left camera and a right camera of a binocular camera shoot pig images simultaneously and upload the pig images to the mobile communication terminal, the mobile communication terminal divides the pig images into at least two areas, the proportion of the highest value and the lowest value of pixels in each area image is counted, if the proportion exceeds a preset threshold value, the areas are considered to be over-exposed or under-exposed, and if not, the images are stored.
Wherein, the ground surface of the pig drinking bowl is provided with a weight measurer, and the weight measurer can send the collected weight information of the pig body to the mobile communication terminal.
The radio frequency electronic ear tag is used as a pig tag, and the tag information comprises the ear number, the variety, the source immunity condition and the health condition of the pig.
Wherein, pig body chi includes: body length, body width, hip width.
Wherein, include when binocular camera gathers pig body image: and acquiring the pig body image within a preset time, wherein the preset time comprises 9.00-17.00.
The utility model discloses can realize the quick and accurate measurement to the pig body cun under the condition of contactless pig body, just so avoid the manpower to measure trouble, unsafe situation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic view of a pig body ruler rapid detection device provided by the embodiment of the present invention;
FIG. 2 is a flow chart of the device for rapidly detecting the body size of a pig provided by the embodiment of the present invention;
fig. 3 is a schematic diagram of a body measurement point provided by the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative efforts belong to the protection scope of the present invention.
Fig. 1 is the embodiment of the utility model provides a pig body chi short-term test device's schematic diagram, include: the system comprises a wireless radio frequency electronic ear tag 101, a card reader 102, a mobile communication terminal 103 and a binocular camera 104;
201. the card reader reads the wireless radio frequency electronic ear tag worn on the pig ear and uploads the read tag information to the mobile communication terminal.
The wireless radio frequency electronic ear tag 101 is used as a pig tag, the tag comprises the ear number, the variety, the source immunity condition and the health condition of the pig, one ear of each pig is worn with the wireless radio frequency electronic ear tag 101, and the type can be RFID.
The card reader 102 is used for reading a label of a pig to be detected by a pig body ruler.
In addition, a weight measurer may be installed on the ground surface of the pig drinker, and the weight measurer may transmit the collected weight information of the pig body to the mobile communication terminal 103.
202. The binocular camera is perpendicular to the ground and horizontally erected on the pig waterer and used for shooting pig body images and uploading the pig body images to the mobile communication terminal.
The binocular camera 104 includes 2 cameras, camera optical axis interval is 115mm, the CCD size is 7.15mm 5.43mm, the resolution is 1624 pixel 1234 pixel, the pixel size is 4.4 μm, the camera lens model is computarH0514-MP, fixed focal length 5mm, the binocular camera 104 erects in the position of about 2.5m apart from ground, the binocular camera 104 gathers pig body image and will in the time of predetermineeing the pig body image upload to the mobile communication terminal 103, the time of predetermineeing includes 9.00-17.00.
The binocular cameras 104 are erected in parallel on the vertical ground of the pig waterer and used for shooting pig images and uploading the pig images to the mobile communication terminal 103.
203. The mobile communication terminal collects pig body images.
The mobile communication terminal 103 receives the pig body image sent by the binocular camera 104, the automatic image acquisition software of the mobile communication terminal 103 divides the pig body image into at least two regions, the ratio of the highest value and the lowest value of the pixels in each region image is counted, if the ratio exceeds a preset threshold value, the region is considered to have overexposure or underexposure, otherwise, the pig body image is stored.
204. And acquiring a pig body depth image.
The pig body depth image acquisition comprises: performing Gaussian blur processing on a pig body image to be processed, and selecting N different Gaussian filter parameters to obtain N blurred images, wherein N is more than or equal to 2;
detecting the edges of the pig body image and the N blurred images to obtain edge images of the images;
calculating fuzzy parameter estimation values corresponding to all pixel points at the edge of the edge image under all Gaussian filter parameters;
obtaining the optimal fuzzy parameter estimation value of each pixel point at the edge according to the N fuzzy parameter estimation values of each pixel point at the edge;
calculating the depth value of each pixel point at the edge in the image according to the obtained optimal fuzzy parameter estimation value of each pixel point at the edge, thereby obtaining a sparse depth map;
and carrying out interpolation processing on the obtained sparse depth map to obtain a depth image.
After the depth image of the pig body image is obtained, the pig body image can be filtered, and the filtering process comprises the following steps: dividing the pig body image into at least two image areas; calculating a spatial distance coefficient and a pixel difference coefficient for each of the at least two image regions; and for any pixel in the target image, carrying out bilateral filtering on the pixel according to the spatial distance coefficient and the pixel difference coefficient of the image area where the pixel is located.
205. And acquiring the contour of the pig body.
The mobile communication terminal 103 obtaining the pig body contour comprises: calculating gradient information of the pig body image, calculating structural features of the image according to the gradient information, calculating feature vectors of the structural features, extracting vertical components of the feature vectors, and extracting edge pixel points of the image according to the vertical components of the feature vectors.
Extracting edge pixel points of the image from the vertical component of the feature vector comprises: and acquiring vertical direction information of the vertical component of the feature vector, extracting edge pixel points of the image through a Gaussian difference algorithm according to the vertical direction information, and generating contour lines according to the edge pixel points to obtain the pig body contour.
206. And screening out pig body ruler detection key points based on the inflection point extraction algorithm of the concave structure to calculate the pig body ruler.
After the pig body contour is obtained, a pig body ruler detection key point is screened out based on the inflection point extraction algorithm of the concave structure to calculate the pig body ruler.
The position of the water fountain is fixed, so that the orientation of the pig head can be determined, and the short axis of the pig body particles is taken as a segmentation line, and the alternative points are divided into an ear root alternative point and a tail root alternative point; the 2 tail root candidate points farthest from the short axis are tail root segmentation points, and the 2 ear root candidate points closest to the short axis are neck segmentation points.
The more obvious angular points of pig body profile have: 2 tails, 2 joints of abdomen and buttocks, 2 joints of abdomen and shoulders, 2 necks and 2 joints of head and ears, which are all angular points.
The provided pig body head and tail removal algorithm based on convex hull analysis can detect pig tail root and ear root segmentation points, and the calculation steps of the body size detection key points are as follows:
(1) and calculating the envelope curve of the pig body particles, and calculating the coincidence point of the envelope curve and the contour.
(2) And calculating the length of the envelope line segment between the adjacent coincident points, and screening out the envelope line segment with the length larger than 30 pixels.
(3) And calculating the distances d between all points on the contour line segment and the envelope line segment, and selecting the point with the largest distance as a candidate point of the tail root and the ear root segmentation point, wherein the largest distance is called the depth of the depression.
(4) Because the position of the water dispenser is fixed, the orientation of the pig head can be determined, and the short axis of the pig body particles is taken as a dividing line to divide the alternative points into an ear root alternative point and a tail root alternative point; the two caudal root candidate points farthest from the short axis are caudal root segmentation points, and the 2 auricular root candidate points closest to the short axis are neck segmentation points.
The utility model discloses a body chi measurement point is as shown in fig. 3, 1, 2 ear roots intercept point, 3, 4 tail roots cut apart the point, 5, neck mid point, 6, 7 shoulder width measuring points, 8, 9 buttockss width measuring points, 10 tail roots mid point.
Firstly, determining a middle point 5 of the ear root segmentation points 1 and 2 and a middle point 12 of the tail root segmentation points 3 and 4; from point 5 to point 12 are the body length of the pig; then determining a rectangle a from the points 1 and 2 along the distance from 1/12 backwards to 1/3 of the length of the pig body particle in the long axis direction, and searching the maximum width of the pig contour in the rectangle a as the shoulder width; determining a rectangle b from the distance from point 3 to the front 1/12 to 1/3 of the body length, finding the maximum width in the rectangle b as the hip width, the middle point of the two body width measuring points as the body height measuring point, the middle point of the two hip width measuring points as the hip height measuring point, and the calculation formula of each body ruler is shown in the table I:
the utility model discloses can realize the quick and accurate measurement to the pig body cun under the condition of contactless pig body, just so avoid the manpower to measure situations such as troublesome, inaccurate.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, a plurality of modifications and replacements can be made without departing from the technical principle of the present invention, and these modifications and replacements should also be regarded as the protection scope of the present invention.
Claims (5)
1. The utility model provides a pig body chi short-term test device which characterized in that includes: the system comprises a wireless radio frequency electronic ear tag, a card reader, a binocular camera and a mobile communication terminal;
the card reader reads a wireless radio frequency electronic ear tag worn on a pig ear and uploads the read tag information to the mobile communication terminal;
the binocular camera is erected in a manner that the binocular camera is perpendicular to the ground and parallel to a pig waterer, and is used for shooting images of pig bodies and uploading the images to the mobile communication terminal, and the pig waterer is provided with a limiting rail, so that the width of the pig waterer only allows one pig to enter drinking water at a time;
the mobile communication terminal collects the pig body image to calculate the pig body size.
2. The device for rapidly detecting the body size of the pig as claimed in claim 1, wherein a weight measurer is installed on the ground surface of the pig water fountain, and the weight measurer can transmit the collected body weight information of the pig to the mobile communication terminal.
3. The device for rapidly detecting the body size of the pig according to claim 1, wherein the radio frequency electronic ear tag is used as a pig tag, and the tag information comprises the ear number, the breed, the source immune status and the health status of the pig.
4. The device for rapidly detecting the pig body ruler according to claim 1, wherein the pig body ruler comprises: body length, body width, hip width.
5. The rapid pig body ruler detection device of claim 1, wherein the binocular camera when acquiring the pig body images comprises: and acquiring the pig body image within a preset time, wherein the preset time comprises 9.00-17.00.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920412079.7U CN210666871U (en) | 2019-03-28 | 2019-03-28 | Quick detection device of pig body chi |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920412079.7U CN210666871U (en) | 2019-03-28 | 2019-03-28 | Quick detection device of pig body chi |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210666871U true CN210666871U (en) | 2020-06-02 |
Family
ID=70821538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920412079.7U Expired - Fee Related CN210666871U (en) | 2019-03-28 | 2019-03-28 | Quick detection device of pig body chi |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210666871U (en) |
-
2019
- 2019-03-28 CN CN201920412079.7U patent/CN210666871U/en not_active Expired - Fee Related
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200267947A1 (en) | Arrangement and method for measuring the biological mass of fish, and use of the arrangement | |
| US20100224140A1 (en) | Method and a System for Measuring an Animal's Height | |
| CN108759973B (en) | Water level measuring method | |
| CA2949768C (en) | Non-invasive multimodal biometrical identification system of animals | |
| RU2543948C2 (en) | Device and method of determining quantitative indicator of body condition of animals | |
| CN101944231B (en) | Method for extracting wheatear morphological parameters | |
| CN109145808B (en) | Tuna identification method based on self-adaptive fish body bending model | |
| CN105260750B (en) | A kind of milk cow recognition methods and system | |
| CN110569735A (en) | Analysis method and device based on back body condition of dairy cow | |
| Kaixuan et al. | Target detection method for moving cows based on background subtraction | |
| CN112232978A (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
| KR20190030082A (en) | System and Method for measuring weight of poultry based on pattern recognition | |
| CN113920138A (en) | Cow body size detection device based on RGB-D camera and detection method thereof | |
| CN109272546A (en) | A kind of fry length measurement method and system | |
| CN114170292A (en) | Pig weight estimation method and device based on depth image | |
| CN204202563U (en) | Fish morphological parameters self-operated measuring unit | |
| Lee et al. | Contour matching for fish species recognition and migration monitoring | |
| CN113180640A (en) | Size measuring method and system for livestock breeding | |
| CN111145205A (en) | Pig body temperature detection method based on infrared image under multiple pig scenes | |
| CN210666871U (en) | Quick detection device of pig body chi | |
| CN113484867A (en) | Imaging sonar-based fish school density detection method in closed space | |
| CN109118540B (en) | Sturgeon rapid statistical method based on ridge line extraction | |
| CN112070791B (en) | Method and system for improving precision and efficiency of number of livestock individuals | |
| CN113888612A (en) | Animal point cloud multi-view real-time acquisition and 3D reconstruction method, device and system | |
| Hashisho et al. | AI-assisted Automated Pipeline for Length Estimation, Visual Assessment of the Digestive Tract and Counting of Shrimp in Aquaculture Production. |
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: 20200602 |