CN109961071A

CN109961071A - A kind of determination method of forward direction watermelon quirk pollination state

Info

Publication number: CN109961071A
Application number: CN201910235809.5A
Authority: CN
Inventors: 不公告发明人
Original assignee: Individual
Current assignee: Individual
Priority date: 2019-03-27
Filing date: 2019-03-27
Publication date: 2019-07-02

Abstract

The invention discloses a kind of determination methods of positive watermelon quirk pollination state, belong to figure identification field, this method is split first to watermelon quirk and the extraction of target area, hsv color space is transformed into obtained target area to extract the color characteristic of pistil and petal, to used color characteristic figure edge detection number come determine in forward direction, then by calculating convex closure salient angle number determine quirk if appropriate for pollination.

Description

A kind of determination method of forward direction watermelon quirk pollination state

Technical field

The present invention relates to a kind of determination methods of positive watermelon quirk pollination state, specifically first to the watermelon of acquisition Quirk carry out target area extraction, determine watermelon quirk be in astern determined using the number of salient angle quirk if appropriate for The method of pollination, belongs to field of image recognition.

Background technique

China is the maximum country of growth of watermelon area, as China's industrialized agriculture constantly develops, the anniversary kind of watermelon The environment opposing seal of cultivation is planted, facility internal environment is more demanding to temperature and humidity, and facility plantation is especially embodied in greenhouse cultivation, Closed planting environment has completely cut off the entrance of extraneous insect pollinator, and watermelon is entomophilous flower, and insect is mainly leaned under natural conditions Pollination, therefore be mostly now that human assistance bears fruit (artificial pollination, growth regulator) to ensure the fruit-setting rate of watermelon, with machine For vision in extensive use agriculturally, intelligent watermelon pollination robot certainly will be research tendency, however intelligent pollination machine It is exactly the position for identifying watermelon flower that the key technology of people, which is selected, determines the character of quirk, however is obtaining the image of watermelon quirk When, since the watermelon grown in its natural state spends the interference that can inevitably have green, tendril and film, it is desirable to obtain background Single target quirk region needs to be split processing to the watermelon quirk image of acquisition, then knows whether identification quirk is located In forward condition, then determine whether quirk can pollinate, there is presently no the judgement sides for the pollination state for determining watermelon quirk Method.

Summary of the invention

Effective pollination state recognition effectively cannot be carried out to watermelon quirk image for the prior art, the present invention mentions A kind of determination method of positive watermelon quirk pollination state is supplied, this method utilizes convex by determining that watermelon quirk is forward direction Packet salient angle number can accurately identify quirk pollination state.

The present invention is achieved by the following technical solutions: a kind of determination method of forward direction watermelon quirk pollination state, should Method is split first to watermelon quirk and the extraction of target area, determines that quirk is in positive and then by salient angle Number is to determine quirk if appropriate for pollination, comprising the following steps:

(1) image of the rgb space of acquisition is pre-processed first, be transformed into Lab color space and utilized in the channel b OTSU algorithm is split, and is negated and Morphological scale-space to binary map is obtained, finally will treated binary map and original image and behaviour Color Segmentation figure is obtained after work；

(2) hsv color space is transformed into obtained target area to extract the color characteristic of pistil and petal, it is right Color characteristic figure carries out edge detection, determines that watermelon quirk is in forward direction by number of edges.

(3) convex closure drafting is carried out to its image for positive quirk, then calculates whether the certain quirk of salient angle number fits Close pollination.

The pretreatment that described image carries out is median filter process, and the convolution kernel size of median filtering is 5*5.

Described that the bianry image that Otsu automatic threshold segmentation obtains is carried out to the channel b, target area color is black, back Scape is white, Ying Jinhang inversion operation, while carrying out Morphological scale-space to image, and Morphological scale-space includes area filling, expansion Corrosion and small area region removal operation, the binary map be single-pass image, should be mapped to triple channel again with original image carry out with Operation, obtains Color Segmentation figure.

The Color Segmentation figure is transformed into the color characteristic that HSV space extracts pistil and petal according to yellow color value Figure, the color characteristic figure of extraction pass through edge detection, and the judgement watermelon quirk that obtained number of edges is two is in forward direction.

The mark that the positive watermelon quirk can authorize is that the number of salient angle is five.

The usefulness of the invention is can be split processing to the watermelon quirk image of acquisition, rapidly and accurately divide It cuts and extracts watermelon quirk target area, and determine that quirk is in forward direction, can accurately be identified just westwards further according to salient angle number Melon quirk is if appropriate for pollination.The method use image of the median filtering function to acquisition to be pre-processed, can be effective Removal noise jamming while retain image marginal information, furthermore with Otsu automatic threshold segmentation algorithm to the channel b into The bianry image that row threshold division obtains can carry out primary segmentation to image, eliminate a large amount of background interference；To preliminary point The bianry image cut carries out Threshold segmentation, after morphologic holes filling and small area removal operation, obtains background Single bianry image；For bianry image inversion operation, and bianry image is mapped to triple channel to be single pass, can be with original Figure carries out obtaining the Color Segmentation effect picture of only watermelon quirk with operation；It is further determined as watermelon quirk and is in forward direction, so Convex closure drafting is carried out for quirk afterwards, the number by calculating salient angle can accurately quickly recognize watermelon quirk if appropriate for awarding Powder.

Detailed description of the invention

Fig. 1 is the flow chart of watermelon quirk character method of discrimination；

Fig. 2 is the effect picture of image median filter；

Fig. 3 is watermelon quirk Color Segmentation effect picture；

Fig. 4 is watermelon quirk edge detection schematic diagram；

Fig. 5 is to draw convex closure schematic diagram

Specific embodiment

A kind of determination method of forward direction watermelon quirk pollination state, the state as shown in Figure 1, a kind of forward direction watermelon quirk is pollinated Determination method, this method is split first to watermelon quirk and the extraction of target area, converts to obtained target area It is extracted to color characteristic of the hsv color space to pistil and petal, edge detection is carried out to color characteristic figure to determine to locate In forward direction, then by the number of convex closure salient angle determine quirk if appropriate for pollination, specifically includes the following steps:

(1) image of acquisition is pre-processed first as shown in Figure 2, pretreatment operation is median filter process, and is planted Planting filtering processing using convolution kernel is 5*5 size, and median filter process can effectively remove the same of noise jamming When retain image marginal information.

(2) since the image of acquisition is RGB color, image is transformed into Lab color space, and return Lab space Image carries out channel separation operation, obtains b channel components figure, carries out the binary map that Otsu automatic threshold segmentation obtains to the channel b Picture, since target area color is black in bianry image, background is white, should be subtracted into the pixel for traversing whole sub-picture, use 255 Each pixel value is removed, so that its value pixel is 0 to take 255, the pixel for being 255 to its pixel value takes 0, completes negating for image Operation, so that target area is shown as white, background area is black, finally obtained bianry image such as Fig. 3 secondary series figure As shown in.

(3) since Fig. 3 secondary series bianry image is there are other interference such as white point, hole, morphology need to be carried out to it Processing, basic removal interference, obtains the binary map as described in arranging Fig. 3 third, and wherein Morphological scale-space includes area filling, expansion Corrosion and small area region remove processing operation, and the binary map that aforesaid operations obtain is single channel image, need to be mapped to threeway Road is carried out and is operated with original image (RGB triple channel) again, obtains color images effect picture, the effect shown in the column of Fig. 3 the 4th Fruit figure, can obtain the color image of watermelon quirk target area.

(4) it can be seen that the flower region of watermelon male flower and female Huadu with yellow, works as flower from the image after segmentation When in forward condition, it can be seen that pistil, and the color between pistil and petal has certain difference, passes through what will be obtained The target color image of watermelon quirk is transformed into hsv color space, and then the pistil of quirk and petal color characteristic extract, For extraction color characteristic figure carry out edge detection, detection there are two edge be forward direction, from Fig. 4 third column in can The sample image tool of first three rows is found out there are two profile, that is, so-called watermelon quirk is in forward condition.

(5) determine that watermelon quirk is in forward condition, when observing positive watermelon quirk and be suitble to the state of pollination, west The petal of melon quirk can open completely, and can be evident that there are five petals, therefore carry out convex closure to watermelon quirk It draws, by drafting convex closure it can be found that the number of salient angle represents the number of petal, energy when salient angle number is five Enough confirmation quirk is to be suitble to pollination, by Fig. 5 it can be seen that it is all suitable that the salient angle number of the sample image of first three columns, which is five, Pollination, the convex closure number of the sample image of fourth line is not five, it cannot also pollinate,

For the ordinary skill in the art, introduction according to the present invention, do not depart from the principle of the present invention with In the case where spirit, changes, modifications that embodiment is carried out, replacement and variant still fall within protection scope of the present invention it It is interior.

Claims

1. a kind of determination method of forward direction watermelon quirk pollination state, it is characterised in that: this method first carries out watermelon quirk The extraction of segmentation and target area determines that quirk is in positive and then whether determines quirk by the number of convex closure salient angle It is suitble to pollination, comprising the following steps:

(1) image of the rgb space of acquisition is pre-processed first, be transformed into Lab color space and utilize OTSU in the channel b Algorithm is split, and is negated and Morphological scale-space to binary map is obtained, finally will be after treated binary map and original image and operation Obtain Color Segmentation figure；

(2) it is transformed into hsv color space to obtained target area to extract the color characteristic of pistil and petal, to color Characteristic pattern carries out edge detection, determines that watermelon quirk is in forward direction by number of edges.

(3) convex closure drafting is carried out to its image for positive quirk, then whether is the certain quirk of number of calculating convex closure salient angle It is suitble to pollination.

2. a kind of determination method of positive watermelon quirk pollination state according to claim 1, it is characterised in that: the figure The pretreatment operation that picture carries out is median filter process, and the convolution kernel size of median filtering is 5*5.

3. a kind of determination method of positive watermelon quirk pollination state according to claim 1, it is characterised in that: described right The channel b carries out the bianry image that Otsu automatic threshold segmentation obtains, and target area color is black, and background is white, Ying Jin Row inversion operation, while Morphological scale-space is carried out to image, Morphological scale-space includes area filling, dilation erosion and small surfaces The operations such as domain removal, the binary map are single-pass image, should be mapped to triple channel and carry out and operate with original image again, obtain colour Segmentation figure.

4. a kind of determination method of positive watermelon quirk pollination state according to claim 3, it is characterised in that: described Color Segmentation figure is transformed into the color characteristic figure that HSV space extracts pistil and petal according to yellow color value, and the color of extraction is special Sign figure passes through edge detection, and the judgement watermelon quirk that obtained number of edges is two is in forward direction.

5. a kind of determination method of positive watermelon quirk pollination state according to claim 4, it is characterised in that: described The number for the flag bit convex closure salient angle that positive watermelon quirk can authorize is five.