CN104616004A - Citrus yield estimation method based on multi-estimation parameters - Google Patents
Citrus yield estimation method based on multi-estimation parameters Download PDFInfo
- Publication number
- CN104616004A CN104616004A CN201510101041.4A CN201510101041A CN104616004A CN 104616004 A CN104616004 A CN 104616004A CN 201510101041 A CN201510101041 A CN 201510101041A CN 104616004 A CN104616004 A CN 104616004A
- Authority
- CN
- China
- Prior art keywords
- tangerines
- oranges
- picture pick
- citrusfruit
- 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.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a citrus yield estimation method based on multi-estimation parameters. The method comprises the following steps: (1) providing a citrus yield estimation system based on the multi-estimation parameters, wherein the estimation system comprises a measurement fixing rod, first camera equipment, second camera equipment, citrus identification equipment and a digital signal processor (DSP); the measurement fixed rod is used for fixing the first camera equipment and the second camera equipment; the first camera equipment and the second camera equipment are respectively used for shooting single citrus plant to acquire a first citrus image and a second citrus image respectively; the citrus identification equipment is respectively connected with the first camera equipment and the second camera equipment and is used for acquiring the multi-estimation parameters of the single citrus plant based on the first orange image and the second orange image; the DSP is connected with the citrus identification equipment and is used for determining the estimation yield of the single citrus plant based on the multi-estimation parameters; (2) estimating by using the system.
Description
Technical field
The present invention relates to agriculture and forestry product field of planting, particularly relate to a kind of orange yield evaluation method based on many estimation parameters.
Background technology
Oranges and tangerines are tangerine, mandarin orange, orange, golden mandarin orange, the general name of shaddock, trifoliate orange etc.The huge number of oranges and tangerines, cultivated area is comparatively wide, and output is considerable, the world has 135 countries to produce oranges and tangerines, annual production 10282.2 ten thousand tons, area 10,730 ten thousand mu, all occupy first of all kinds of fruits, the primary number Brazil of output, 2425.26 ten thousand tons, the second figure place U.S., 1633.52 ten thousand tons, the 3rd, 1,078 ten thousand tons, China, the states such as Zai Houshi Mexico, Spain, Iran, India, Italy.Oranges and tangerines have become the main path of increasing peasant income, growth of agricultural efficiency.
But if oranges and tangerines are excessively planted, will cause the unbalanced supply-demand in region, the downward price adjustment amplitude of oranges and tangerines is excessive, have impact on the income of peasant on the contrary.Therefore needing to carry out orange yield estimation, carry out the modulation of oranges and tangerines planting scheme with the orange yield estimated, ensureing the Simultaneous Stabilization oranges and tangerines price of oranges and tangerines supply, safeguarding the interests of peasant.
Orange yield estimating system of the prior art or the mode by manual measurement or the mode by image recognition are carried out, but the former too relies on manually, at substantial human cost and time cost, the latter uses single image, single estimation parameter detects, the output detection technique indifference of all kinds oranges and tangerines, accuracy is not high, and easily causes the leakage of detected parameters, and these detected parameters often orange yield research institution expend the result of painstaking effort test of many times.
Therefore, need a kind of orange yield evaluation method based on many estimation parameters, original manual measurement mode or single image, single estimation parameter, the indiscriminate image measurement mode of kind can be substituted, while the security of guarantee detected parameters, more accurately more fully obtain the output of oranges and tangerines.
Summary of the invention
In order to solve the problem, the invention provides a kind of orange yield evaluation method based on many estimation parameters, two video cameras of vertical arrangement are adopted to carry out image acquisition to individual plant oranges and tangerines, use comprises front fruit number, side fruit number, multiple estimation parameters of front fruit area and side fruit area perform to be estimated the output of individual plant oranges and tangerines, crucially, in estimation process, the detected parameters of dissimilar oranges and tangerines is different, encryption device is used to ensure that some important detected parameters are not leaked, also right to use re-computation mode, multiple estimation parameter is combined, improve security and the accuracy of orange yield estimation.
According to an aspect of the present invention, provide a kind of orange yield evaluation method based on many estimation parameters, the method comprises the following steps: 1) a kind of orange yield estimating system based on many estimation parameters is provided, described estimating system comprises measurement fixed bar, first picture pick-up device, second picture pick-up device, oranges and tangerines identification equipment and digital signal processor DSP, described measurement fixed bar is used for fixing described first picture pick-up device and described second picture pick-up device, described first picture pick-up device and described second picture pick-up device are used for taking individual plant oranges and tangerines respectively, to obtain the first oranges and tangerines image and the second oranges and tangerines image respectively, described oranges and tangerines identification equipment is connected with described first picture pick-up device and described second picture pick-up device respectively, for obtaining multiple estimation parameters of described individual plant oranges and tangerines based on described first oranges and tangerines image and described second oranges and tangerines image, described DSP is connected with described oranges and tangerines identification equipment, for determining the estimation output of described individual plant oranges and tangerines based on described multiple estimation parameter, 2) use described system to estimate.
More specifically, in the described orange yield estimating system based on many estimation parameters, also comprise: U shield equipment, comprise input block and display unit, described input block is for receiving user's name and the user cipher of active user's input, and described display unit is for showing the every terms of information of active user's input, USB interface, for connecting U shield equipment, the user's name inputted at described U shield equipment according to active user and user cipher determine whether active user is authorized user, memory device, for prestoring the benchmark image template of the oranges and tangerines of each kind, the benchmark image template of the oranges and tangerines of each kind is for taking obtained pattern in advance to the benchmark individual plant oranges and tangerines of each kind, Wireless Telecom Equipment, with the orange yield research platform wireless connections of far-end, for receiving the kind of the individual plant oranges and tangerines that described DSP sends, the kind of described individual plant oranges and tangerines is wirelessly sent to described orange yield research platform, and the citrusfruit upper limit gray threshold corresponding with the kind of described individual plant oranges and tangerines that orange yield research platform described in wireless receiving returns, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter, described multiple estimation parameter is by front fruit number, side fruit number, front fruit area and side fruit area composition, described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold are used for the citrusfruit of kind corresponding in image to be separated with image background, described measurement fixed bar is the fixed bar of the L-type structure around described individual plant oranges and tangerines, for described first picture pick-up device and described second picture pick-up device are fixed on same level mutual vertically, described first picture pick-up device is used for taking the front of described individual plant oranges and tangerines, to obtain described first oranges and tangerines image, described second picture pick-up device is used for taking the side of described individual plant oranges and tangerines, and to obtain described second oranges and tangerines image, described second picture pick-up device adopts identical focal length to take with described first picture pick-up device, described oranges and tangerines identification equipment respectively with described first picture pick-up device, described second picture pick-up device is connected with described memory device, comprise pretreatment unit, fruit cutting unit and estimation parameter recognition unit, described pretreatment unit is connected with described first picture pick-up device and described second picture pick-up device respectively, for performing contrast strengthen successively to described first oranges and tangerines image, medium filtering and gray processing process are to obtain the first gray level image, successively contrast strengthen is performed to described second oranges and tangerines image, medium filtering and gray processing process, to obtain the second gray level image, described fruit cutting unit is connected with described pretreatment unit and described memory device respectively, the pixel identification of gray-scale value in described first gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple first citrusfruit subimage, the pixel identification of gray-scale value in described second gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple second citrusfruit subimage, described estimation parameter recognition unit is connected with described fruit cutting unit, the sum of multiple first citrusfruit subimage is exported as front fruit number, the sum of all pixels of multiple first citrusfruit subimage is exported as front fruit area, the sum of multiple second citrusfruit subimage is exported as side fruit number, the sum of all pixels of multiple second citrusfruit subimage is exported as side fruit area, described DSP is connected respectively with described USB interface, described memory device, described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment, described DSP is when receiving active user that described USB interface returns for authorized user, start described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment, and successively enter kind match pattern and yield estimation model in order, described DSP is when receiving active user that described USB interface returns and not being authorized user, close described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment, and send unauthorized access signal, wherein, described DSP is in described kind match pattern, the benchmark image template of the oranges and tangerines of each kind in described first oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the first Citrus Cultivars, the benchmark image template of the oranges and tangerines of each kind in described second oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the second Citrus Cultivars, when described first Citrus Cultivars is identical with described second Citrus Cultivars, identical Citrus Cultivars is exported to described Wireless Telecom Equipment as the kind of described individual plant oranges and tangerines, and the citrusfruit upper limit gray threshold that described Wireless Telecom Equipment is returned, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter is stored in described memory device, when described first Citrus Cultivars is not identical with described second Citrus Cultivars, export kind it fails to match signal, described DSP, in described yield estimation model, exports based on described oranges and tangerines identification equipment the estimation output that each corresponding respectively weighted value of front fruit number, side fruit number, front fruit area and side fruit area that front fruit number, side fruit number, front fruit area and side fruit area and described memory device store determines described individual plant oranges and tangerines.
More specifically, in the described orange yield estimating system based on many estimation parameters, also comprise: LCDs, be connected with described DSP, for showing the estimation output of described individual plant oranges and tangerines, also for showing the word warning message corresponding with described unauthorized access signal or described kind it fails to match signal.
More specifically, in the described orange yield estimating system based on many estimation parameters, also comprise: two-way speaker, be connected with described DSP, for playing the estimation output of described individual plant oranges and tangerines, also for playing the audio alert file corresponding with described unauthorized access signal or described kind it fails to match signal.
More specifically, in the described orange yield estimating system based on many estimation parameters, also comprise: power-supply unit, comprise lithium battery power supply subelement, solar powered subelement and switch subelement, described switching subelement is connected with described lithium battery power supply subelement and described solar powered subelement respectively, when the electric quantity of lithium battery of lithium battery power supply subelement is lower than default power threshold, being switched to solar powered subelement to use sun power is that described estimating system is powered.
More specifically, in the described orange yield estimating system based on many estimation parameters: the pretreatment unit of described oranges and tangerines identification equipment, fruit cutting unit and estimation parameter recognition unit adopt different fpga chips to realize respectively.
More specifically, in the described orange yield estimating system based on many estimation parameters: the orange yield research platform of described Wireless Telecom Equipment wireless connections belonging to orange yield research institution, the server with wireless communication interface.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram of the orange yield estimating system based on many estimation parameters illustrated according to an embodiment of the present invention.
Fig. 2 is the block diagram of the power-supply unit of the orange yield estimating system based on many estimation parameters illustrated according to an embodiment of the present invention.
Embodiment
Below with reference to accompanying drawings the embodiment of the orange yield estimating system based on many estimation parameters of the present invention is described in detail.
The composition of oranges and tangerines by: root, stem, leaf, flower and fruit form, belong to dungarunga, unifoliate compound leaf, winged petiole is usually narrow, or only have vestige, blade lanceolar, oval or wealthy avette, size variation is larger, often there is recess on top, middle arteries and veins becomes dichotomy by near base portion to recess, and leaf margin at least upper semisection has blunt or circle carnassial tooth usually, seldom full edge.Hua Dansheng or 2-3 clusters; The irregular 5-3 of calyx is shallow to be split; Within petal grows 1.5 centimetres usually; Stamen 20-25 piece.
The planting area that oranges and tangerines are not only suitable for is wide, output is high, and citrus fruit is nutritious, and it contains multiple human body health substance, isolate more than 30 to plant, wherein mainly contained: flavonoids, monoterpene, cumarin, carotenoid, class propyl alcohol, acridone, glycerose lipid etc.Citrus Cultivars is numerous, dividing from large class, comprises tangerine, mandarin orange, orange, golden mandarin orange, shaddock, trifoliate orange etc., and dividing from group, the concrete little kind related to more than 72, such as, freezes tangerine, Gan Xia, stone mandarin orange, bright and beautiful orange, oily tangerine, bergamot, Pingshan shaddock, sugar orange etc.
Identification to orange yield of the prior art is except the manual measurement mode of original backwardness, most employing image recognition technology, one strain oranges and tangerines are taken pictures, identify the citrusfruit number in the oranges and tangerines image obtained or citrusfruit area occupied, the output of these strain oranges and tangerines is determined based on citrusfruit number or citrusfruit area occupied, although this mode can obtain orange yield roughly to a certain extent, but due to oranges and tangerines huge number, do not adopt different image recognition parameters and one-parameter recognition mode based on oranges and tangerines kind, cause orange yield deviation larger, simultaneously, some important scientific research parameters relevant to orange yield identification do not adopt any secure fashion, easily cause the leakage of these scientific research parameters, make the painstaking effort of Scientific Research Workers irrevocably lost.
The present invention has built a kind of orange yield estimating system based on many estimation parameters, and take differentiated recognition technology based on dissimilar oranges and tangerines, the introducing of weight calculation mode and detected parameters cipher mode, accurately reliably completes the estimation of orange yield simultaneously.
Fig. 1 is the block diagram of the orange yield estimating system based on many estimation parameters illustrated according to an embodiment of the present invention, described estimating system comprises measures fixed bar 1, first picture pick-up device 2, second picture pick-up device 4, oranges and tangerines identification equipment 3 and digital signal processor DSP 5, described measurement fixed bar 1 is for fixing described first picture pick-up device 2 and described second picture pick-up device 4, described first picture pick-up device 2 and described second picture pick-up device 4 are for taking individual plant oranges and tangerines respectively, to obtain the first oranges and tangerines image and the second oranges and tangerines image respectively, described oranges and tangerines identification equipment 3 is connected with described first picture pick-up device 2 and described second picture pick-up device 4 respectively, for obtaining multiple estimation parameters of described individual plant oranges and tangerines based on described first oranges and tangerines image and described second oranges and tangerines image, described DSP 5 is connected with described oranges and tangerines identification equipment 3, for determining the estimation output of described individual plant oranges and tangerines based on described multiple estimation parameter.
Then, continue to be further detailed the concrete structure of the orange yield estimating system based on many estimation parameters of the present invention.
Described estimating system also comprises: U shield equipment, comprises input block and display unit, and described input block is for receiving user's name and the user cipher of active user's input, and described display unit is for showing the every terms of information of active user's input.
Described estimating system also comprises: USB interface, and for connecting U shield equipment, the user's name inputted at described U shield equipment according to active user and user cipher determine whether active user is authorized user.
Described estimating system also comprises: memory device, and for prestoring the benchmark image template of the oranges and tangerines of each kind, the benchmark image template of the oranges and tangerines of each kind is for taking obtained pattern in advance to the benchmark individual plant oranges and tangerines of each kind.
Described estimating system also comprises: Wireless Telecom Equipment, with the orange yield research platform wireless connections of far-end, for receiving the kind of the individual plant oranges and tangerines that described DSP 5 sends, the kind of described individual plant oranges and tangerines is wirelessly sent to described orange yield research platform, and the citrusfruit upper limit gray threshold corresponding with the kind of described individual plant oranges and tangerines that orange yield research platform described in wireless receiving returns, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter, described multiple estimation parameter is by front fruit number, side fruit number, front fruit area and side fruit area composition, described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold are used for the citrusfruit of kind corresponding in image to be separated with image background.
Described measurement fixed bar 1 is the fixed bar of the L-type structure around described individual plant oranges and tangerines, for described first picture pick-up device 2 and described second picture pick-up device 4 are fixed on same level mutual vertically.
Described first picture pick-up device 2 for taking the front of described individual plant oranges and tangerines, to obtain described first oranges and tangerines image.
Described second picture pick-up device 4 is for taking the side of described individual plant oranges and tangerines, and to obtain described second oranges and tangerines image, described second picture pick-up device 4 adopts identical focal length to take with described first picture pick-up device 2.
Described oranges and tangerines identification equipment 3 respectively with described first picture pick-up device 2, described second picture pick-up device 4 is connected with described memory device, described oranges and tangerines identification equipment 3 comprises pretreatment unit, fruit cutting unit and estimation parameter recognition unit, described pretreatment unit is connected with described first picture pick-up device 2 and described second picture pick-up device 4 respectively, for performing contrast strengthen successively to described first oranges and tangerines image, medium filtering and gray processing process are to obtain the first gray level image, successively contrast strengthen is performed to described second oranges and tangerines image, medium filtering and gray processing process, to obtain the second gray level image.
Described fruit cutting unit is connected with described pretreatment unit and described memory device respectively, the pixel identification of gray-scale value in described first gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple first citrusfruit subimage, the pixel identification of gray-scale value in described second gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple second citrusfruit subimage.
Described estimation parameter recognition unit is connected with described fruit cutting unit, the sum of multiple first citrusfruit subimage is exported as front fruit number, the sum of all pixels of multiple first citrusfruit subimage is exported as front fruit area, the sum of multiple second citrusfruit subimage is exported as side fruit number, the sum of all pixels of multiple second citrusfruit subimage is exported as side fruit area.
Described DSP 5 is connected respectively with described USB interface, described memory device, described Wireless Telecom Equipment, described first picture pick-up device 2, described second picture pick-up device 4 and described oranges and tangerines identification equipment 3; Described DSP 5 is when receiving active user that described USB interface returns for authorized user, start described Wireless Telecom Equipment, described first picture pick-up device 2, described second picture pick-up device 4 and described oranges and tangerines identification equipment 3, and successively enter kind match pattern and yield estimation model in order, described DSP 5 is when receiving active user that described USB interface returns and not being authorized user, close described Wireless Telecom Equipment, described first picture pick-up device 2, described second picture pick-up device 4 and described oranges and tangerines identification equipment 5, and send unauthorized access signal.
Wherein, described DSP 5 is in described kind match pattern, the benchmark image template of the oranges and tangerines of each kind in described first oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the first Citrus Cultivars, the benchmark image template of the oranges and tangerines of each kind in described second oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the second Citrus Cultivars, when described first Citrus Cultivars is identical with described second Citrus Cultivars, identical Citrus Cultivars is exported to described Wireless Telecom Equipment as the kind of described individual plant oranges and tangerines, and the citrusfruit upper limit gray threshold that described Wireless Telecom Equipment is returned, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter is stored in described memory device, when described first Citrus Cultivars is not identical with described second Citrus Cultivars, export kind it fails to match signal, described DSP 5, in described yield estimation model, exports based on described oranges and tangerines identification equipment the estimation output that each corresponding respectively weighted value of front fruit number, side fruit number, front fruit area and side fruit area that front fruit number, side fruit number, front fruit area and side fruit area and described memory device store determines described individual plant oranges and tangerines.
Described estimating system also comprises: LCDs, is connected with described DSP 5, for showing the estimation output of described individual plant oranges and tangerines, also for showing the word warning message corresponding with described unauthorized access signal or described kind it fails to match signal.
Described estimating system also comprises: two-way speaker, is connected with described DSP 5, for playing the estimation output of described individual plant oranges and tangerines, also for playing the audio alert file corresponding with described unauthorized access signal or described kind it fails to match signal.
As shown in Figure 2, described estimating system also comprises: power-supply unit 6, comprise lithium battery power supply subelement 62, solar powered subelement 63 and switch subelement 61, described switching subelement 61 is connected with described lithium battery power supply subelement 62 and described solar powered subelement 63 respectively, when the electric quantity of lithium battery of lithium battery power supply subelement 62 is lower than default power threshold, being switched to solar powered subelement 63 to use sun power is that described estimating system is powered.
Wherein, in described estimating system, the pretreatment unit of described oranges and tangerines identification equipment, fruit cutting unit and estimation parameter recognition unit can adopt different fpga chips to realize respectively, the orange yield research platform of described Wireless Telecom Equipment wireless connections belonging to orange yield research institution, the server with wireless communication interface.
In addition, digital signal processor (digital signal processor) DSP, the processor being used for certain signal processing tasks be made up of extensive or VLSI (very large scale integrated circuit) lamination.He is needs for adapting to High speed real-time signal processing task and grows up gradually.Along with the development of integrated circuit technique and digital signal processing algorithm, the implementation method of digital signal processor is also in continuous change, and processing capacity improves constantly and expands.
Digital signal processor is not confined to audio frequency and video aspect, and he is widely used in many fields such as Communication and Information Systems, Signal and Information Processing, automatically control, radar, military affairs, Aero-Space, medical treatment, household electrical appliance.Adopt general microprocessor to complete a large amount of digital signal processing computing in the past, speed is slower, be difficult to meet actual needs, and use bit slice microprocessor and quick paral-lel multiplier simultaneously, be once the effective way realizing digital signal processing, but the method device is more, logical design and program design complexity, power consumption is comparatively large, expensive.The appearance of digital signal processor DSP, well solves the problems referred to above.DSP can realize the process such as collection, conversion, filtering, valuation, enhancing, compression, identification to signal fast, to obtain the signal form meeting people's needs.
Digital signal processor can be divided into able to programme and non-programmable two large classes by its programmability.Non-programmable signal processor for basic logical structure, does not have control program with the flow process of signal processing algorithm, generally can only complete a kind of main processing capacity, so also known as dedicated signal processors.As fast fourier transform processor, digital filter etc.Although this kind of processor function limitation, has higher processing speed.Programmable signal processor then by the function that programming change processor will complete, has larger versatility, so also known as general purpose signal processor.
Along with improving constantly of the general purpose signal processor ratio of performance to price, his application at signal place is day by day universal.The programmable signal processor developed has three classes haply: (1) is 2,4 by basic bit length, and the microprocessor chip of 8 is main body, be equipped with programmed control sheet, interruption and DMA control strip, time the formation such as time-card.Adopt selective laser sintering, grouping order format, the system of required word length can be formed on demand.Its advantage is that processing speed is fast, efficiency is high.Shortcoming is that power consumption is comparatively large, and the quantity of slice, thin piece is also more.(2) Signal Processors, by arithmetical unit, multiplier, storer, program read-only memory, IO interface, even mould/number D/A switch etc. is all integrated on monolithic, high, the low in energy consumption highly versatile of its fast operation, precision.Compared with general microprocessor, his instruction set and addressing mode are more suitable for the conventional computing of signal transacting and data structure.(3) VLSI (very large scale integrated circuit) (VLSI) array processor.This kind ofly utilizes a large amount of processing unit to complete identical operation to different data under single instrction sequence controls, thus obtain the signal processor of supercomputing.Be very suitable for big data quantity, intensive, the repeated strong signal processing tasks of computing.
Digital signal processor develops into the VLSI array processor of today from the dedicated signal processors of 20 century 70s, and its application has developed into the signal transacting of the video big data quantities such as radar today, image from the process of the low frequency signals such as initial voice, sonar.Due to the utilization of floating-point operation and parallel processing technique, the ability of digital signal processor is greatly improved.Digital signal processor also will continue along raising processing speed and the development of operational precision both direction, and architecturally data flow architecture will be so that artificial neural network structure etc. may become the infrastructure mode of generation digital signal processor.
Adopt the orange yield estimating system based on many estimation parameters of the present invention, for the existing orange yield estimating system based on image recognition technology because one-parameter is estimated, ignore species differences and the estimation error brought is excessive, and estimation parameter is not maintained secrecy brought potential safety hazard, cause estimation precision not high and the technical matters that security performance is low, by adopting multiparameter estimation, the image recognition technology that variety classes estimation parameter is different, introduce weight calculation mode and U shield security protection mode simultaneously, the performance of comprehensive raising orange yield estimating system.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (7)
1., based on an orange yield evaluation method for many estimation parameters, the method comprises the following steps:
1) a kind of orange yield estimating system based on many estimation parameters is provided, described estimating system comprises measurement fixed bar, first picture pick-up device, second picture pick-up device, oranges and tangerines identification equipment and digital signal processor DSP, described measurement fixed bar is used for fixing described first picture pick-up device and described second picture pick-up device, described first picture pick-up device and described second picture pick-up device are used for taking individual plant oranges and tangerines respectively, to obtain the first oranges and tangerines image and the second oranges and tangerines image respectively, described oranges and tangerines identification equipment is connected with described first picture pick-up device and described second picture pick-up device respectively, for obtaining multiple estimation parameters of described individual plant oranges and tangerines based on described first oranges and tangerines image and described second oranges and tangerines image, described DSP is connected with described oranges and tangerines identification equipment, for determining the estimation output of described individual plant oranges and tangerines based on described multiple estimation parameter,
2) use described system to estimate.
2. the method for claim 1, is characterized in that, described estimating system also comprises:
U shield equipment, comprises input block and display unit, and described input block is for receiving user's name and the user cipher of active user's input, and described display unit is for showing the every terms of information of active user's input;
USB interface, for connecting U shield equipment, the user's name inputted at described U shield equipment according to active user and user cipher determine whether active user is authorized user;
Memory device, for prestoring the benchmark image template of the oranges and tangerines of each kind, the benchmark image template of the oranges and tangerines of each kind is for taking obtained pattern in advance to the benchmark individual plant oranges and tangerines of each kind;
Wireless Telecom Equipment, with the orange yield research platform wireless connections of far-end, for receiving the kind of the individual plant oranges and tangerines that described DSP sends, the kind of described individual plant oranges and tangerines is wirelessly sent to described orange yield research platform, and the citrusfruit upper limit gray threshold corresponding with the kind of described individual plant oranges and tangerines that orange yield research platform described in wireless receiving returns, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter, described multiple estimation parameter is by front fruit number, side fruit number, front fruit area and side fruit area composition, described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold are used for the citrusfruit of kind corresponding in image to be separated with image background,
Described measurement fixed bar is the fixed bar of the L-type structure around described individual plant oranges and tangerines, for described first picture pick-up device and described second picture pick-up device are fixed on same level mutual vertically;
Described first picture pick-up device is used for taking the front of described individual plant oranges and tangerines, to obtain described first oranges and tangerines image;
Described second picture pick-up device is used for taking the side of described individual plant oranges and tangerines, and to obtain described second oranges and tangerines image, described second picture pick-up device adopts identical focal length to take with described first picture pick-up device;
Described oranges and tangerines identification equipment respectively with described first picture pick-up device, described second picture pick-up device is connected with described memory device, comprise pretreatment unit, fruit cutting unit and estimation parameter recognition unit, described pretreatment unit is connected with described first picture pick-up device and described second picture pick-up device respectively, for performing contrast strengthen successively to described first oranges and tangerines image, medium filtering and gray processing process are to obtain the first gray level image, successively contrast strengthen is performed to described second oranges and tangerines image, medium filtering and gray processing process, to obtain the second gray level image, described fruit cutting unit is connected with described pretreatment unit and described memory device respectively, the pixel identification of gray-scale value in described first gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple first citrusfruit subimage, the pixel identification of gray-scale value in described second gray level image between described citrusfruit upper limit gray threshold and described citrusfruit lower limit gray threshold is formed multiple second citrusfruit subimage, described estimation parameter recognition unit is connected with described fruit cutting unit, the sum of multiple first citrusfruit subimage is exported as front fruit number, the sum of all pixels of multiple first citrusfruit subimage is exported as front fruit area, the sum of multiple second citrusfruit subimage is exported as side fruit number, the sum of all pixels of multiple second citrusfruit subimage is exported as side fruit area,
Described DSP is connected respectively with described USB interface, described memory device, described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment; Described DSP is when receiving active user that described USB interface returns for authorized user, start described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment, and successively enter kind match pattern and yield estimation model in order, described DSP is when receiving active user that described USB interface returns and not being authorized user, close described Wireless Telecom Equipment, described first picture pick-up device, described second picture pick-up device and described oranges and tangerines identification equipment, and send unauthorized access signal;
Wherein, described DSP is in described kind match pattern, the benchmark image template of the oranges and tangerines of each kind in described first oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the first Citrus Cultivars, the benchmark image template of the oranges and tangerines of each kind in described second oranges and tangerines image and described memory device is mated, using Citrus Cultivars corresponding for benchmark image template the highest for matching degree as the second Citrus Cultivars, when described first Citrus Cultivars is identical with described second Citrus Cultivars, identical Citrus Cultivars is exported to described Wireless Telecom Equipment as the kind of described individual plant oranges and tangerines, and the citrusfruit upper limit gray threshold that described Wireless Telecom Equipment is returned, each weighted value of citrusfruit lower limit gray threshold and multiple estimation parameter is stored in described memory device, when described first Citrus Cultivars is not identical with described second Citrus Cultivars, export kind it fails to match signal,
Wherein, described DSP, in described yield estimation model, exports based on described oranges and tangerines identification equipment the estimation output that each corresponding respectively weighted value of front fruit number, side fruit number, front fruit area and side fruit area that front fruit number, side fruit number, front fruit area and side fruit area and described memory device store determines described individual plant oranges and tangerines.
3. method as claimed in claim 2, it is characterized in that, described estimating system also comprises:
LCDs, is connected with described DSP, for showing the estimation output of described individual plant oranges and tangerines, also for showing the word warning message corresponding with described unauthorized access signal or described kind it fails to match signal.
4. method as claimed in claim 2, it is characterized in that, described estimating system also comprises:
Two-way speaker, is connected with described DSP, for playing the estimation output of described individual plant oranges and tangerines, also for playing the audio alert file corresponding with described unauthorized access signal or described kind it fails to match signal.
5. method as claimed in claim 2, it is characterized in that, described estimating system also comprises:
Power-supply unit, comprise lithium battery power supply subelement, solar powered subelement and switch subelement, described switching subelement is connected with described lithium battery power supply subelement and described solar powered subelement respectively, when the electric quantity of lithium battery of lithium battery power supply subelement is lower than default power threshold, being switched to solar powered subelement to use sun power is that described estimating system is powered.
6. method as claimed in claim 2, is characterized in that:
The pretreatment unit of described oranges and tangerines identification equipment, fruit cutting unit and estimation parameter recognition unit adopt different fpga chips to realize respectively.
7. method as claimed in claim 2, is characterized in that:
The orange yield research platform of described Wireless Telecom Equipment wireless connections belonging to orange yield research institution, the server with wireless communication interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510101041.4A CN104616004A (en) | 2015-03-08 | 2015-03-08 | Citrus yield estimation method based on multi-estimation parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510101041.4A CN104616004A (en) | 2015-03-08 | 2015-03-08 | Citrus yield estimation method based on multi-estimation parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104616004A true CN104616004A (en) | 2015-05-13 |
Family
ID=53150441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510101041.4A Pending CN104616004A (en) | 2015-03-08 | 2015-03-08 | Citrus yield estimation method based on multi-estimation parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104616004A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658379A (en) * | 2018-11-09 | 2019-04-19 | 广西慧云信息技术有限公司 | A method of orange yield is quickly calculated by picture |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200193A (en) * | 2014-08-05 | 2014-12-10 | 北京农业信息技术研究中心 | Fruit tree yield estimation method and device |
-
2015
- 2015-03-08 CN CN201510101041.4A patent/CN104616004A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200193A (en) * | 2014-08-05 | 2014-12-10 | 北京农业信息技术研究中心 | Fruit tree yield estimation method and device |
Non-Patent Citations (3)
| Title |
|---|
| P ANNAMALAI等: "《Color Vision System for Estimating Citrus Yield in Real-time》", 《ASAE/CSAE ANNUAL INTERNATIONAL MEETING》 * |
| QI WANG等: "《Automated Crop Yield Estimation for Apple Orchards》", 《INTERNATIONAL SYMPOSIUM OF EXPERIMENTAL ROBOTICS》 * |
| QI WANG等: "《Design of Crop Yield Estimation System for Apple Orchards Using Computer Vision》", 《2012 ASABE ANNUAL INTERNATIONAL MEETING》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658379A (en) * | 2018-11-09 | 2019-04-19 | 广西慧云信息技术有限公司 | A method of orange yield is quickly calculated by picture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sharath et al. | Image based plant disease detection in pomegranate plant for bacterial blight | |
| Revathi et al. | Advance computing enrichment evaluation of cotton leaf spot disease detection using Image Edge detection | |
| Sarkate et al. | Application of computer vision and color image segmentation for yield prediction precision | |
| CN110245720A (en) | A kind of citrus pest and disease damage intelligent diagnosing method and system based on deep learning | |
| CN103093208A (en) | Method and system for fruit and vegetable recognition | |
| CN112836623B (en) | Auxiliary method and device for agricultural decision of facility tomatoes | |
| Muthevi et al. | Leaf classification using completed local binary pattern of textures | |
| CN104063686A (en) | System and method for performing interactive diagnosis on crop leaf segment disease images | |
| Ma et al. | YOLOv5-lotus an efficient object detection method for lotus seedpod in a natural environment | |
| CN111950391A (en) | Fruit tree bud recognition method and device | |
| CN106960190B (en) | The irrigated area statistical method of medium resolution image is supervised based on high-definition picture | |
| CN103714317A (en) | Plant blade recognition method based on Android platform | |
| CN102156886A (en) | Statistical data and remote sensing image data based regional fertilizer application spatialization method | |
| Huang et al. | A survey of deep learning-based object detection methods in crop counting | |
| Syal et al. | Apple fruit detection and counting using computer vision techniques | |
| CN104616004A (en) | Citrus yield estimation method based on multi-estimation parameters | |
| CN104658000A (en) | Orange yield estimation system based on multiple estimation parameters | |
| CN103824083B (en) | Web online species recognition method based on blade complete and partial two-value characteristics | |
| CN204515855U (en) | Based on the orange yield estimating system of many estimation parameters | |
| Zhao et al. | A dataset of pomegranate growth stages for machine learning-based monitoring and analysis | |
| CN107133634B (en) | Method and device for acquiring plant water shortage degree | |
| Wang et al. | Identification of growing points of cotton main stem based on convolutional neural network | |
| CN109117939A (en) | Neural network and the method for affixing one's name to neural network in mobile awareness upper side | |
| CN113902735A (en) | Crop disease identification method and device, electronic equipment and storage medium | |
| Vig et al. | Saliency-based selection of sparse descriptors for action recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150513 |
|
| RJ01 | Rejection of invention patent application after publication |