Git Product home page Git Product logo

tomatopredictmodel's Introduction

智慧种植 —— 番茄生长状态预测

模型

在本次项目中,我们采用的是CNN+LSTM的模型结果,其中CNN用于提取图像的图片,然后和传感器特征向量拼接在一起,再使用LSTM对时序数据进行预测。在本模型中,输入的是['图像', '土壤水分%', '土壤温度℃', '叶面积', '叶夹角','高度', 'RVI', 'LNC', 'LNA', 'LAI'],输出的是植株的叶面积指数LAI

数据对齐

在本项目中,共有九次仪器采集的植株生长状态指标,但是由于前两次缺少部分数据,在本项目中并未采用该时间段的数据;然后根据牛顿插值算法对数据按照一小时的时间间隔单位进行插值,并将其和传感器数据进行对齐。除此之外,由于图片数据是每天四张,分别在08、10、14、16这几个时间进行采集,因此还需要对图片进行增广操作。在这里,我们使用调整亮度的方式增加图片数据:

img1 = cv.imread(img1_path)
img2 = cv.imread(img2_path)
img1_beta = np.mean(img1)
img2_beta = np.mean(img2)
div = int(tmp2[2])-int(tmp1[2])
for i in range(div-1):
    img3 = cv.convertScaleAbs(img1, beta=(i+1)*(img2_beta-img1_beta)/div, alpha=1)
    cv.imwrite("./dataset/png/{}/{}_{}_{:0>2}.jpg".format(imgDir, tmp1[0], tmp1[1], int(tmp1[2])+i+1), img3)

分别计算两张图片之间的均值,然后根据生成的图片数量,使用cv.convertScaleAbs()对原图进行亮度的调整。

实验结果

下面是一些预测结果图:

img

img

img

img

tomatopredictmodel's People

Contributors

xingqwq avatar

Watchers

 avatar

tomatopredictmodel's Issues

Model confusion

Dear xingqwq,
I read about the model presentation for your project.
” In this model, the input is [' image ', 'soil moisture %', 'soil temperature ℃, leaf area, leaf Angle,' height 'and' RVI, established 'LNC', 'LNA', 'LAI'], LAI is the output of the plant leaf area index;“
Does this mean that there is an output when there is an input about “LAI", Or is it the comparison between the predicted LAI and the real LAI

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.