Outdoor surface atmospheric temperature prediction method based on visible light

Abstract

The invention discloses a visible light-based outdoor surface atmospheric temperature prediction method, which comprises three steps of training sample construction, model construction and surface temperature prediction, and comprises the steps of firstly collecting surface image data under natural light irradiation, collecting surface atmospheric temperature data of a central point of an image area at a corresponding moment, and constructing a training sample by adopting a set-aside method; secondly, extracting image features by adopting a CNN-GRU network, inputting the image features into a regression network formed by a full-connection neural network, and training a surface atmospheric temperature prediction model by using a training sample; and finally, carrying out model parameter tuning, and predicting the surface atmospheric temperature hourly by using the trained model. According to the invention, surface temperature prediction is carried out by extracting surface visible light image features, and the model is rapidly applied to a similar landform area by adopting a transfer learning method to carry out surface atmospheric temperature prediction, so that the cost of an Internet of Things system is reduced, and the application of a deep learning method in surface temperature monitoring is expanded. And the perception capability of the visible light camera is enhanced.

Description

Technical Field

[0001] The invention relates to the field of agricultural and forestry information technology, and in particular to a method for predicting outdoor surface atmospheric temperature based on visible light. Background Art

[0002] Atmospheric temperature affects the living habits and distribution of plants and animals, and is of great significance in agriculture, forestry, climate and other fields. In the traditional mode, IoT devices such as image acquisition and temperature and humidity sensors are used to regularly collect data and send it to the data center for environmental monitoring. With the development of smart agriculture and smart forestry, the monitoring granularity of ambient atmospheric temperature is becoming smaller and smaller. The increase in the types and number of sensors will not only increase the cost and energy consumption of the forest IoT system, but also restrict the application scope of the IoT system and the upgrading and transformation of the existing IoT system to a certain extent. Therefore, how to monitor and predict the atmospheric temperature of the environment while reducing costs has become a key technical problem that needs to be solved in the field of agricultural and forestry information technology.

[0003] In recent years, with the development of breath data collection technology, a variety of atmospheric temperature monitoring methods have emerged, mainly including near-infrared and temperature sensors. These methods involve the update and upgrade of collection equipment. In theory, there is a certain correlation between atmospheric temperature and sunlight, and the atmospheric temperature can be calculated by the change in surface illumination. It is feasible to use machine learning methods to extract high-dimensional features in visible light images and thus calculate the atmospheric temperature of the environment. Summary of the invention

[0004] The purpose of the present invention is to solve the deficiencies of the prior art and provide a method for predicting land surface temperature based on visible light images.

[0005] In order to achieve the above technical effects, the present invention is implemented by the following technical solutions: a method for predicting outdoor surface atmospheric temperature based on visible light images, characterized in that it includes the following steps:

[0006] S1. Build training data set:

[0007] Data acquisition: A visible light camera is used to collect visible light radiation data reflected by the ground surface in outdoor environments, i.e., visible light images, and a temperature sensor is used to collect the surface atmospheric temperature at the center of the corresponding image area;

[0008] S2, a combination of data classification labels, data preparation, and target temperature setting;

[0009] Data preprocessing:

[0010] Assign image classification labels according to environmental meteorological information.

[0011] Category label 1: According to the natural law of sunrise and sunset, the collected images are divided into three light categories according to time periods: morning low light, medium and high light, and evening low light, and IA, IB, and IC labels are added respectively; it can also be divided into more detailed categories, and the labels are increased accordingly; for example, if the sunrise time in a certain place is 6 o'clock and the sunset time is 18 o'clock, the images can be divided into three categories, namely 30 minutes before sunrise to 3 hours after sunrise, 3 hours after sunrise to 3 hours before sunset, and 3 hours before sunset to 30 minutes after sunset, that is, IA: [5:30, 9:00), IB: [9:00, 15:00), IC: [15:00, 18:30]; or a neural network can be used to classify the average light intensity within △T time, △T is 30 minutes, and the number of classifications is not limited to three categories;

[0012] Category label 2: divide the data set into S1, S2, ...S24 according to the 24 solar terms;

[0013] Data preparation: t is the image sampling period. Setting parameters N and M indicates that N images within a continuous N*t time range are used to predict the temperature at the subsequent M*t time. t0 indicates the time of the last image of N images. The image data of the time window [t0-(N-1)*t, t0] is used as the input of the model's visible light image.

[0014] Training data target temperature: Calculate the average temperature within the time range of t0+M*t, and use the result as the target temperature of the training data;

[0015] Wherein, N>1, M≥0; when M=0, it indicates the expected output temperature at time t0, and when M>0, it indicates the expected output temperature at time t0+M*t;

[0016] Temperature prediction data set division: The holdout method is used to construct training samples, with 80% of the collected data as the training data set and the remaining 20% ​​as the test data set;

[0017] S3. Model construction: CNN-GRU, Embedding and regression network are used to form a temperature prediction model. CNN-GRU network is used to extract illumination features in visible light images; Embedding is used to classify meteorological features and map them into a feature space of fixed length; a fully connected neural network with 3 hidden layers and 1 output node is used to construct a temperature regression neural network, and the regression neural network is optimized with adam with a learning rate of lr=0.001, and then the surface atmospheric temperature prediction model is trained using training samples;

[0018] S4, model parameter tuning: set the temperature error threshold parameters α and β, where α = 0.2℃ and β = 3℃, which can be adjusted as needed; use test data to evaluate the model prediction effect, the model output predicted temperature is x, the actual temperature is y, when |xy|≤α, the predicted temperature is correct, otherwise it is wrong; when |xy|≥β, it means that the predicted value deviates too much and needs to be optimized; retrieve the image data 10 minutes before and after the moment from the training data set, use image rotation, flipping and other methods to expand the training samples, and then train the model;

[0019] S5. Actual input prediction:

[0020] Data preprocessing: Assign classification labels 1 and 2 in the same way as the labels in S1, and prepare data using the same parameters N and M as in S1;

[0021] Temperature prediction: Load the model parameters optimized by S3, input the preprocessed data, and output the predicted temperature at the target time.

[0022] Furthermore, the data acquisition in S1 is specifically as follows: a visible light camera at a fixed position and angle collects visible light radiation data modulated by the ground surface and ground cover, namely, a visible light image.

[0023] Furthermore, the image captured by the visible light camera in S1 is a three-channel image with a pixel size greater than 2048*1080 pixels, and the sky accounts for less than 1 / 2 of the captured image.

[0024] Furthermore, CNN-GRU, Embedding and regression networks together constitute a surface atmospheric temperature prediction model. The CNN network in the model adopts the feature extraction structure of image processing networks such as VGG or Restnet, or uses different convolution kernels to establish a four-layer convolutional neural network.

[0025] Furthermore, when using training samples to train the surface atmospheric temperature prediction model, the input dimension of the GRU network is the same as the dimension of the CNN network output after Flattening; Embedding is used to map the average meteorological features into a 64-dimensional vector; the GRU network output and the Embedding result are concatenated as the input of the regression network, the number of nodes in the regression hidden layer is set to half of the number of nodes in the previous input layer, and the output layer outputs the temperature prediction result.

[0026] The beneficial effects of the present invention are:

[0027] The present invention predicts the surface atmospheric temperature from a new perspective, and adopts an artificial intelligence method to establish a correlation between visible light illumination and ground atmospheric temperature through training data. Compared with existing methods and technologies, the present method does not rely on temperature sensing equipment. Temperature prediction only requires a high-definition camera and an algorithm deployed in a data center, and the atmospheric temperature of each node can be centrally processed and predicted, which effectively reduces the types of IoT devices for environmental monitoring, enhances the perception ability of IoT devices, and saves energy and cost; facilitates the upgrading and transformation of IoT systems for environmental monitoring, expands the surface atmospheric temperature prediction method, and provides a reference for simplifying the surface atmospheric temperature prediction. At the same time, the present invention has good applicability and strong generalization ability under conditions of medium and low illumination. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0029] Figure 1 This is a flow chart of the method for predicting land surface temperature based on visible light images according to the present invention;

[0030] Figure 2 This is a schematic diagram of heat exchange between the earth's surface and the atmosphere according to the present invention;

[0031] Figure 3 It is a schematic diagram of the equipment deployment method of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Example 1

[0034] See also Figure 1 As shown, a method for predicting land surface temperature based on visible light images specifically includes the following steps:

[0035] Step 1: Build a training dataset:

[0036] A visible light camera is used to collect visible light radiation data reflected from the ground in outdoor environments. The camera is set to collect surface images in real time at a fixed azimuth and elevation, or images are captured from videos. The pixels of the collected images must be larger than 2048*1080 pixels for three-channel images, the proportion of sky in the captured images must be less than 1 / 2, and the collection time interval can be set from a few seconds to tens of minutes.

[0037] A temperature sensor is used to collect the surface atmospheric temperature at the center of the corresponding image area, or the temperature in the local meteorological data is used as the temperature of the collected image.

[0038] Data preprocessing:

[0039] Assign image classification labels according to environmental meteorological information.

[0040] Category label 1: According to the natural law of sunrise and sunset, the collected images are divided into three light categories according to time periods: morning low light, medium and high light, and evening low light, and IA, IB, and IC labels are added respectively; it can also be divided into more detailed categories, and the labels are increased accordingly; for example, if the sunrise time in a certain place is 6 o'clock and the sunset time is 18 o'clock, the images can be divided into three categories, namely 30 minutes before sunrise to 3 hours after sunrise, 3 hours after sunrise to 3 hours before sunset, and 3 hours before sunset to 30 minutes after sunset, that is, IA: [5:30, 9:00), IB: [9:00, 15:00), IC: [15:00, 18:30]; or a neural network can be used to classify the average light intensity within △T time, △T is 30 minutes, and the number of classifications is not limited to three categories;

[0041] Category label 2: divide the data set into S1, S2, ...S24 according to the 24 solar terms;

[0042] Temperature prediction data set division: Alternatively, the image data of the time window [t0-(N-1)*t, t0] is used to calculate the parameter setting method for predicting the temperature at time t0+M*t, and the samples are divided into a training data set and a test data set.

[0043] Step 2: Model construction:

[0044] The temperature prediction model is divided into two parts: feature extraction and regression network. The CNN-GRU network is used to extract illumination features, and the illumination type characteristics are integrated as illumination features. A fully connected neural network with three hidden layers and one output node is used to build a temperature regression neural network, and then the training samples are used to train the surface atmospheric temperature prediction model.

[0045] The CNN network in the feature extraction network uses 7*7, 5*5, 4*4, and 4*4 convolution kernels and ReLU activation functions to extract image features in turn. The output of the CNN network is flattened into a one-dimensional vector and input into the GRU network. The average meteorological feature map corresponding to the Embedding input image is mapped into a 64-dimensional vector. The GRU network output and the Embedding result are concatenated into a 4096+64-dimensional vector and input into the regression network. The number of regression network nodes is set to 4160, 2080, 1040, 510, 1, and the dropout rate is 0.1. The network is optimized using adam, with lr=0.001.

[0046] Step 3: Model parameter tuning:

[0047] Set the temperature error threshold parameters α and β, where α = 0.2℃ and β = 3℃, and adjust as needed; use test data to evaluate the model prediction effect, the model output predicted temperature is x, the actual temperature is y, when |xy|≤α, the predicted temperature is correct, otherwise it is wrong; when |xy|≥β, it means that the predicted value deviates too much and needs to be optimized; retrieve the image data 10 minutes before and after the moment from the training data set, use image rotation, flipping and other methods to expand the training samples, and then train the model.

[0048] Step 4: Actually bring in the prediction:

[0049] Data preprocessing: Assign classification labels 1 and 2 in the same way as in step 1, and prepare data using the same parameters N and M as in step 1;

[0050] Temperature prediction: Load the model parameters optimized in step 3, input the preprocessed data, and output the predicted temperature at the target moment.

[0051] The electronic device of the present invention can be deployed at an IoT endpoint or at a convergence node of an IoT system.

Claims

1. A method for predicting outdoor surface atmospheric temperature based on visible light images, characterized in that: The following steps are involved: S1. Build training data set: Data acquisition: A visible light camera is used to collect visible light radiation data reflected by the ground surface in outdoor environments, i.e., visible light images, and a temperature sensor is used to collect the surface atmospheric temperature at the center of the corresponding image area; S2, a combination of data classification labels, data preparation, and target temperature setting; Data preprocessing: Assign image classification labels according to environmental meteorological information. Category label 1: According to the natural law of sunrise and sunset, the collected images are divided into three lighting categories according to time periods: morning low light, medium-high light, and evening low light, and are labeled IA, IB, and IC respectively; Category label 2: divide the data set into S1, S2, ...S24 according to the 24 solar terms; Data preparation: t is the image sampling period. Setting parameters N and M indicates that N images within a continuous N*t time range are used to predict the temperature at the subsequent M*t time. t0 indicates the time of the last image of N images. The image data of the time window [t0-(N-1)*t, t0] is used as the input of the model's visible light image. Training data target temperature: Calculate the average temperature within the time range of t0+M*t, and use the result as the target temperature of the training data; Wherein, N>1, M≥0; when M=0, it indicates the expected output temperature at time t0, and when M>0, it indicates the expected output temperature at time t0+M*t; Temperature prediction data set division: The holdout method is used to construct training samples, with 80% of the collected data as the training data set and the remaining 20% ​​as the test data set; S3. Model construction: CNN-GRU, Embedding and regression network are used to form a temperature prediction model. CNN-GRU network is used to extract illumination features in visible light images; Embedding is used to classify meteorological features and map them into a feature space of fixed length; a fully connected neural network with 3 hidden layers and 1 output node is used to construct a temperature regression neural network, and the regression neural network is optimized with adam with a learning rate of lr=0.001, and then the surface atmospheric temperature prediction model is trained using training samples; S4, model parameter tuning: set the temperature error threshold parameters α and β, where α = 0.2℃ and β = 3℃, and adjust as needed; use test data to evaluate the model prediction effect, the model output predicted temperature is x, the actual temperature is y, when |xy|≤α, the predicted temperature is correct, otherwise it is wrong; when |xy|≥β, it means that the predicted value deviates too much and needs to be optimized; retrieve the image data 10 minutes before and after the moment from the training data set, use image rotation, flipping and other methods to expand the training samples, and then train the model; S5. Actual input prediction: Data preprocessing: Assign classification labels 1 and 2 in the same way as the labels in S1, and prepare data using the same parameters N and M as in S1; Temperature prediction: Load the model parameters optimized by S3, input the preprocessed data, and output the predicted temperature at the target time.

2. The method for predicting outdoor surface atmospheric temperature based on visible light according to claim 1, characterized in that: The data acquisition in S1 is specifically as follows: a visible light camera at a fixed position and angle collects visible light radiation data modulated by the ground surface and ground cover, namely, a visible light image.

3. The method for predicting outdoor surface atmospheric temperature based on visible light according to claim 1, characterized in that: The images captured by the visible light camera in S1 are three-channel images with pixels greater than 2048*1080 pixels, and the sky accounts for less than 1 / 2 of the captured images.

4. The method for predicting outdoor surface atmospheric temperature based on visible light according to claim 1, characterized in that: CNN-GRU, Embedding and regression network together constitute the surface atmospheric temperature prediction model. The CNN network in the model adopts the feature extraction structure of image processing networks such as VGG or Restnet, or uses different convolution kernels to establish a four-layer convolutional neural network.

5. The method for predicting outdoor surface atmospheric temperature based on visible light according to claim 1, characterized in that: When using training samples to train the surface atmospheric temperature prediction model, the GRU network input dimension is the same as the dimension of the CNN network output after Flattening; Embedding is used to map the average meteorological features into a 64-dimensional vector; the GRU network output and the Embedding result are concatenated as the input of the regression network, the number of nodes in the regression hidden layer is set to half of the number of nodes in the previous input layer, and the output layer outputs the temperature prediction result.

Images