CN115063062A - A method and system for Internet of Things monitoring temperature for fresh food transportation - Google Patents

Abstract

The invention discloses a method and a system for monitoring temperature of the Internet of Things for fresh food transportation. The method includes: acquiring the configuration of the unmanned vehicle formation; if the configuration is in a straight line, when the pilot vehicle is located in the chain logistics When the vehicle is behind the vehicle, the unmanned vehicle captures the first image behind the cold chain logistics vehicle through the infrared camera; the first image, wind speed information and the speed of the cold chain logistics vehicle are input into the first neural network, and the first neural network outputs The second temperature information in the cargo box of the cold chain logistics vehicle; and the second temperature information is sent to the pilot vehicle, the cold chain logistics vehicle sends the first temperature information to the pilot vehicle, and the pilot vehicle transmits the first temperature information and the second temperature information. The information is fused and sent to the remote control terminal. The invention provides a method and a device for monitoring temperature of the Internet of Things for fresh food transportation, which solves the technical problems of low temperature control reliability and single temperature control method of a cold chain logistics vehicle.

Description

A method and system for Internet of Things monitoring temperature for fresh food transportation

technical field

The present invention relates to the technical field of logistics, and in particular relates to a method for monitoring temperature of the Internet of Things for fresh food transportation.

Background technique

Since the beginning of the 21st century, the storage and preservation technology of agricultural products in my country has developed rapidly, the environment and conditions for the development of cold chain logistics of agricultural products have been continuously improved, and the cold chain logistics of agricultural products has developed rapidly. About 400 million tons of fresh agricultural products enter the circulation field in my country every year, and the proportion of cold chain logistics is gradually increasing. With the continuous expansion of the cold chain market, cold chain logistics companies continue to emerge, showing a development trend of networking, standardization, scale and grouping. Cold chain logistics can not only meet people's demand for fresh food, but also minimize the cost and waste of food in transit. However, the temperature control process of the cold chain logistics vehicle is relatively simple, and it cannot be tracked and controlled remotely in real time, and the reliability of temperature control cannot be guaranteed.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide a method and device for monitoring the temperature of the Internet of Things for fresh food transportation, which solves the technical problems of low reliability of temperature control of cold chain logistics vehicles and single temperature control method.

The present application proposes a method for monitoring temperature of the Internet of Things for fresh food transportation, the method comprising:

The cold chain logistics vehicle and the unmanned vehicles around the cold chain logistics vehicle form an unmanned vehicle formation, and at least one unmanned vehicle maintains a communication connection with the remote control terminal, and one of the unmanned vehicles is selected as the pilot vehicle ; Among them, the pilot vehicle maintains a communication connection with the remote control terminal;

Obtain the configuration of the unmanned vehicle formation. If the configuration is arranged in a straight line, when the pilot vehicle is located behind the chain logistics vehicle, the unmanned vehicle will use the infrared camera to capture the first image behind the cold chain logistics vehicle; The first image, the wind speed information and the speed of the cold chain logistics vehicle are input into the first neural network, and the first neural network outputs the second temperature information in the cargo box of the cold chain logistics vehicle; The chain logistics vehicle sends the first temperature information to the pilot vehicle, and the pilot vehicle fuses the first temperature information and the second temperature information and sends it to the remote control terminal.

Preferably, if the configuration is juxtaposed, the unmanned vehicles take a second image of the left side of the cold chain logistics vehicle through an infrared camera respectively; input the second image, wind speed information and the speed of the cold chain logistics vehicle into the second neural network , the second neural network outputs the third temperature information in the cargo box of the cold chain logistics vehicle, and sends the third temperature information to the pilot vehicle; and/or, the unmanned vehicle shoots the left side of the cold chain logistics vehicle through the infrared camera respectively The third image; input the third image, the wind speed information and the speed of the cold chain logistics vehicle into the third neural network, the third neural network outputs the fourth temperature information in the cargo box of the cold chain logistics vehicle, and the fourth temperature The information is sent to the pilot vehicle; the pilot vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and sends it to the remote control terminal.

Preferably, the motion state of the cold chain logistics vehicle and the state information of the temperature sensor are input into the double-door LSTM model, and the double-door LSTM model outputs the confidence level of the first temperature information of the cold chain logistics vehicle, if the confidence level is less than the preset value, the second temperature information is sent to the remote control terminal as the temperature of the cold chain logistics vehicle;

Among them, the two-door LSTM has two input gates and two forget gates. The two input gates receive the motion state and temperature sensor state information of the cold chain logistics vehicle respectively, and analyze the motion state and temperature sensor state information at the same time, and output The confidence level of the user's first temperature information.

Preferably, the motion state of the cold chain logistics vehicle and the state information of the temperature sensor are input into the double-door LSTM model, and the double-door LSTM model outputs the confidence level of the first temperature information of the cold chain logistics vehicle, if the confidence level is less than the preset value, then send the third temperature information and/or the fourth temperature information to the remote control terminal as the temperature of the cold chain logistics vehicle;

Among them, the two-door LSTM has two input gates and two forget gates. The two input gates receive the motion state and temperature sensor state information of the cold chain logistics vehicle respectively, and analyze the motion state and temperature sensor state information at the same time, and output The confidence level of the user's first temperature information.

Preferably, the first neural network is trained by using the first image, wind speed information and the speed of the cold chain logistics vehicle as input, and the temperature in the cargo box of a standard cold chain logistics vehicle as output.

Preferably, the second image, the wind speed information and the speed of the cold chain logistics vehicle are used as inputs, and the temperature in the cargo box of the standard cold chain logistics vehicle is used as the output to train the second neural network; The speed of the chain logistics vehicle is used as the input, and the temperature inside the container of the standard cold chain logistics vehicle is used as the output to train the second neural network.

Preferably, when the unmanned vehicles form a formation to change the formation, the trajectories of the moving multiple unmanned vehicles are generated according to the model prediction algorithm, and the lane changing of the multiple unmanned vehicles is generated by building an MLP-based neural network. The total cost function of the trajectory, when the total cost function is the smallest, the lane-changing trajectories of multiple UAV-driven vehicles are used as the final lane-changing trajectory.

The present application proposes a temperature monitoring system for the Internet of Things for fresh food transportation, the system includes:

The collaborative control module is used to form an unmanned vehicle formation between the cold chain logistics vehicle and the unmanned vehicles around the cold chain logistics vehicle, and at least one unmanned vehicle maintains a communication connection with the remote control terminal, and one of the unmanned vehicles is selected. The machine-driven vehicle is used as a pilot vehicle; it also includes a communication module for maintaining a communication connection between the pilot vehicle and the remote control terminal;

The remote control module is used to obtain the configuration of the unmanned vehicle formation;

If the configuration is arranged in a straight line, when the pilot vehicle is located behind the chain logistics vehicle, the unmanned vehicle will use the infrared camera to capture the first image behind the cold chain logistics vehicle; the first image, wind speed information and cold chain logistics The vehicle speed is input to the first neural network, and the first neural network outputs the second temperature information in the cargo box of the cold chain logistics vehicle; the second temperature information is sent to the pilot vehicle, and the cold chain logistics vehicle sends the first temperature information to The pilot vehicle, the pilot vehicle fuses the first temperature information and the second temperature information and sends it to the remote control terminal.

Preferably, the remote control module is used to obtain the configuration of the formation of the unmanned vehicles. If the configuration is arranged side by side, the unmanned vehicles shoot the second image of the left side of the cold chain logistics vehicle through the infrared camera respectively; The image, wind speed information and the speed of the cold chain logistics vehicle are input into the second neural network, and the second neural network outputs the third temperature information in the cargo box of the cold chain logistics vehicle, and sends the third temperature information to the pilot vehicle; and/or , the unmanned vehicle takes the third image on the left side of the cold chain logistics vehicle through the infrared camera respectively; the third image is input, the wind speed information and the speed of the cold chain logistics vehicle are input into the third neural network, and the third neural network outputs the cold chain logistics The fourth temperature information in the cargo box of the vehicle is sent, and the fourth temperature information is sent to the pilot vehicle; the pilot vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and sends it to the remote control terminal.

In the present invention, a plurality of unmanned vehicles and cold chain logistics vehicles are formed into a formation, and at least one of the unmanned vehicles maintains a communication connection with the remote control terminal, and the temperature information of the cold chain logistics vehicle can be sent to the remote control terminal in real time through the pilot vehicle. Control the terminal, and by changing the configuration of the unmanned vehicle formation, when the configuration is linear, the temperature of the cold chain logistics vehicle can be determined by merging the second temperature information and the first temperature information of the unmanned vehicle behind , which can improve the reliability of temperature determination. When the cold chain logistics vehicle cannot communicate with the remote control terminal, it can still be determined to remotely grasp its temperature information and control it to maintain a suitable temperature. In addition, the accuracy and technical difficulty of temperature detection of cold chain logistics vehicles are also reduced. Even if there is a problem with the temperature sensor of the cold chain logistics vehicle, it is still possible to determine its temperature information and control its temperature in real time.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the structures shown in these drawings without any creative effort.

Fig. 1 is a kind of flow chart of the method for monitoring temperature of the Internet of Things for fresh food transportation of the present invention;

The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relationship between various components under a certain posture (as shown in the accompanying drawings). The relative positional relationship, the movement situation, etc., if the specific posture changes, the directional indication also changes accordingly.

In addition, the descriptions involving the first, the second, etc. in the present invention are only for the purpose of description, and should not be construed as indicating or implying their relative importance or implying the quantity of the indicated technical features. Thus, a feature delimited by a first and a second may expressly or implicitly include at least one of that feature. In addition, the technical solutions between the various embodiments can be combined with each other, but must be based on those of ordinary skill in the art. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that the combination of technical solutions does not exist. , is not within the scope of protection required by the present invention.

The present application proposes a method for monitoring temperature using the Internet of Things for fresh food transportation. Referring to FIG. 1 , the method includes: Step 1, composing a cold chain logistics vehicle and unmanned vehicles around the cold chain logistics vehicle into an unmanned vehicle. Manned vehicles are formed in formation, and at least one unmanned vehicle maintains a communication connection with the remote control terminal, and one of the unmanned vehicles is selected as a pilot vehicle; wherein, the pilot vehicle maintains a communication connection with the remote control terminal;

Step 2, obtain the configuration of the formation of unmanned vehicles, and step 31, if the configuration is in a straight line, when the pilot vehicle is located behind the chain logistics vehicle, the unmanned vehicles respectively use infrared cameras to photograph the rear of the cold chain logistics vehicle. the first image; input the first image, the wind speed information and the speed of the cold chain logistics vehicle into the first neural network, and the first neural network outputs the second temperature information in the cargo box of the cold chain logistics vehicle; and the second temperature information Send to the pilot vehicle, the cold chain logistics vehicle sends the first temperature information to the pilot vehicle, and the pilot vehicle fuses the first temperature information and the second temperature information and sends it to the remote control terminal.

In the present invention, a plurality of unmanned vehicles and cold chain logistics vehicles are formed into a formation, and at least one of the unmanned vehicles maintains a communication connection with the remote control terminal, and the temperature information of the cold chain logistics vehicle can be sent to the remote control terminal in real time through the pilot vehicle. Control the terminal, and by changing the configuration of the unmanned vehicle formation, when the configuration is linear, the temperature of the cold chain logistics vehicle can be determined by merging the second temperature information and the first temperature information of the unmanned vehicle behind , which can improve the reliability of temperature determination. When the cold chain logistics vehicle cannot communicate with the remote control terminal, it can still be determined to remotely grasp its temperature information and control it to maintain a suitable temperature. In addition, the accuracy and technical difficulty of temperature detection of cold chain logistics vehicles are also reduced. Even if there is a problem with the temperature sensor of the cold chain logistics vehicle, it is still possible to determine its temperature information and control its temperature in real time.

Preferably, in step 32, if the configuration is juxtaposed, the unmanned vehicle takes a second image of the left side of the cold chain logistics vehicle through an infrared camera; input the second image, wind speed information and the speed of the cold chain logistics vehicle into the first Second neural network, the second neural network outputs the third temperature information in the cargo box of the cold chain logistics vehicle, and sends the third temperature information to the pilot vehicle; and/or, the unmanned vehicle shoots the cold chain logistics through infrared cameras respectively The third image on the left side of the car; input the third image, the wind speed information and the speed of the cold chain logistics vehicle into the third neural network, and the third neural network outputs the fourth temperature information in the cargo box of the cold chain logistics vehicle, and the The fourth temperature information is sent to the pilot vehicle; the pilot vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and sends it to the remote control terminal.

Preferably, in step 311, the motion state of the cold chain logistics vehicle and the state information of the temperature sensor are input into the double-door LSTM model, and the double-door LSTM model outputs the confidence level of the first temperature information of the cold chain logistics vehicle, if the confidence level is less than the preset value, the second temperature information is sent to the remote control terminal as the temperature of the cold chain logistics vehicle;

Among them, the two-door LSTM has two input gates and two forget gates. The two input gates receive the motion state and temperature sensor state information of the cold chain logistics vehicle respectively, and analyze the motion state and temperature sensor state information at the same time, and output The confidence level of the user's first temperature information.

When there is no problem with the motion state of the cold chain logistics vehicle and the state information of the temperature sensor, it can be determined that the confidence of the first temperature information is high, but when there is a problem with the motion state of the cold chain logistics vehicle or the state information of the temperature sensor, It means that the confidence of the first temperature information is very low, and remote control is required, and its temperature is detected by other means.

Preferably, in step 321, the motion state of the cold chain logistics vehicle and the temperature sensor state information are input into the double-door LSTM model, and the double-door LSTM model outputs the confidence level of the first temperature information of the cold chain logistics vehicle, if the confidence level is less than the preset value, send the third temperature information and/or the fourth temperature information to the remote control terminal as the temperature of the cold chain logistics vehicle;

Among them, the two-door LSTM has two input gates and two forget gates. The two input gates receive the motion state and temperature sensor state information of the cold chain logistics vehicle respectively, and analyze the motion state and temperature sensor state information at the same time, and output The confidence level of the user's first temperature information.

Preferably, the first neural network is trained by using the first image, wind speed information and the speed of the cold chain logistics vehicle as input, and the temperature in the cargo box of a standard cold chain logistics vehicle as output.

Preferably, the second image, the wind speed information and the speed of the cold chain logistics vehicle are used as inputs, and the temperature in the cargo box of the standard cold chain logistics vehicle is used as the output to train the second neural network; The speed of the chain logistics vehicle is used as the input, and the temperature inside the container of the standard cold chain logistics vehicle is used as the output to train the second neural network.

Preferably, in step 21, when the unmanned vehicles form a formation to transform, generate trajectories of multiple unmanned vehicles according to the model prediction algorithm, and generate multiple unmanned vehicles by building a neural network based on MLP. The total cost function of the lane-changing trajectory, when the total cost function is the smallest, the lane-changing trajectories of multiple UAV-driven vehicles are used as the final lane-changing trajectory.

Specifically, the adversarial cost function L ^D gan of the trajectory discrimination network, the geometric cost Lgeo, and the speed cost Lvel are weighted and linearly combined into the multiple cost functions of the trajectory of each driverless vehicle. The multiple cost function is defined as follows:

式中：LD为判别网络代价。所有无人驾驶车辆的总代价为多个无人驾驶车辆的LD之和，根据数据刷选最小的代价 函数的多个无人驾驶车辆的轨迹作为其阵型变化的轨迹。

Where: LD is the discriminative network cost. The total cost of all unmanned vehicles is the sum of the LDs of multiple unmanned vehicles. According to the data, the trajectories of multiple unmanned vehicles with the smallest cost function are selected as the trajectories of their formation changes.

The present application proposes a temperature monitoring system for the Internet of Things for fresh food transportation, the system includes:

The collaborative control module is used to form an unmanned vehicle formation between the cold chain logistics vehicle and the unmanned vehicles around the cold chain logistics vehicle, and at least one unmanned vehicle maintains a communication connection with the remote control terminal, and one of the unmanned vehicles is selected. The machine-driven vehicle is used as a pilot vehicle; it also includes a communication module for maintaining a communication connection between the pilot vehicle and the remote control terminal;

The remote control module is used to obtain the configuration of the unmanned vehicle formation;

If the configuration is arranged in a straight line, when the pilot vehicle is located behind the chain logistics vehicle, the unmanned vehicle will use the infrared camera to capture the first image behind the cold chain logistics vehicle; the first image, wind speed information and cold chain logistics The vehicle speed is input to the first neural network, and the first neural network outputs the second temperature information in the cargo box of the cold chain logistics vehicle; the second temperature information is sent to the pilot vehicle, and the cold chain logistics vehicle sends the first temperature information to The pilot vehicle, the pilot vehicle fuses the first temperature information and the second temperature information and sends it to the remote control terminal.

Preferably, the remote control module is used to obtain the configuration of the formation of the unmanned vehicles. If the configuration is arranged side by side, the unmanned vehicles shoot the second image of the left side of the cold chain logistics vehicle through the infrared camera respectively; The image, wind speed information and the speed of the cold chain logistics vehicle are input into the second neural network, and the second neural network outputs the third temperature information in the cargo box of the cold chain logistics vehicle, and sends the third temperature information to the pilot vehicle; and/or , the unmanned vehicle takes the third image on the left side of the cold chain logistics vehicle through the infrared camera respectively; the third image is input, the wind speed information and the speed of the cold chain logistics vehicle are input into the third neural network, and the third neural network outputs the cold chain logistics The fourth temperature information in the cargo box of the vehicle is sent, and the fourth temperature information is sent to the pilot vehicle; the pilot vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and sends it to the remote control terminal.

In the present invention, a plurality of unmanned vehicles and cold chain logistics vehicles are formed into a formation, and at least one of the unmanned vehicles maintains a communication connection with the remote control terminal, and the temperature information of the cold chain logistics vehicle can be sent to the remote control terminal in real time through the pilot vehicle. Control the terminal, and by changing the configuration of the unmanned vehicle formation, when the configuration is linear, the temperature of the cold chain logistics vehicle can be determined by merging the second temperature information and the first temperature information of the unmanned vehicle behind , which can improve the reliability of temperature determination. When the cold chain logistics vehicle cannot communicate with the remote control terminal, it can still be determined to remotely grasp its temperature information and control it to maintain a suitable temperature. In addition, the accuracy and technical difficulty of temperature detection of cold chain logistics vehicles are also reduced. Even if there is a problem with the temperature sensor of the cold chain logistics vehicle, it is still possible to determine its temperature information and control its temperature in real time.

The above descriptions are only the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Under the inventive concept of the present invention, the equivalent structure transformation made by the contents of the description and drawings of the present invention, or the direct/indirect application Other related technical fields are included in the scope of patent protection of the present invention.

Claims (9)

1. A method for monitoring temperature of an Internet of things for fresh food transportation is characterized by comprising the following steps:

forming an unmanned vehicle formation by the cold-chain logistics vehicles and the unmanned vehicles around the cold-chain logistics vehicles, wherein at least one unmanned vehicle is in communication connection with the remote control terminal, and the unmanned vehicle is selected as a piloting vehicle; the piloted vehicle is in communication connection with the remote control terminal;

acquiring the configuration of the unmanned vehicle formation;

if the configuration is in linear arrangement, when the piloting vehicle is positioned behind the chain logistics vehicles, the unmanned vehicles respectively shoot first images behind the cold chain logistics vehicles through the infrared cameras; inputting the first image, the wind speed information and the speed of the cold-chain logistics vehicle into a first neural network, and outputting second temperature information in a container of the cold-chain logistics vehicle by the first neural network; and second temperature information is sent to a piloting vehicle, the cold-chain logistics vehicle sends the first temperature information to the piloting vehicle, and the piloting vehicle fuses the first temperature information and the second temperature information and then sends the fused information to the remote control terminal.

2. The method for monitoring the temperature of the internet of things for fresh food transportation according to claim 1, wherein the obtaining the configuration of the formation of the unmanned vehicle further comprises: if the configuration is arranged in parallel, the unmanned vehicles respectively shoot second images of the left side of the cold-chain logistics vehicle through the infrared cameras; inputting the second image, the wind speed information and the vehicle speed of the cold-chain logistics vehicle into a second neural network, outputting third temperature information in a container of the cold-chain logistics vehicle by the second neural network, and sending the third temperature information to a piloting vehicle; and/or the unmanned vehicle respectively shoots a third image of the left side of the cold-chain logistics vehicle through the infrared cameras; inputting a third image, wind speed information and the speed of the cold-chain logistics vehicle into a third neural network, outputting fourth temperature information in a container of the cold-chain logistics vehicle by the third neural network, and sending the fourth temperature information to a piloting vehicle; and the piloting vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and then sends the fused information to the remote control terminal.

3. The method for monitoring the temperature of the internet of things for fresh food transportation according to claim 1, wherein the motion state information and the state information of the temperature sensor of the cold-chain logistics car are input into a double-door LSTM model, the double-door LSTM model outputs the confidence level of the first temperature information of the cold-chain logistics car, and if the confidence level is smaller than a preset value, the second temperature information is sent to a remote control terminal as the temperature of the cold-chain logistics car;

the LSTM with the double doors is provided with two input doors and two forgetting doors, the two input doors respectively receive the motion state and the temperature sensor state information of the cold-chain logistics vehicle, the motion state and the temperature sensor state information are analyzed simultaneously, and the confidence coefficient of the first temperature information of a user is output.

4. The method for monitoring the temperature of the internet of things for fresh food transportation according to claim 2, wherein the motion state information and the state information of the temperature sensor of the cold-chain logistics vehicle are input into a double-door LSTM model, the double-door LSTM model outputs the confidence level of the first temperature information of the cold-chain logistics vehicle, and if the confidence level is smaller than a preset value, the third temperature information and/or the fourth temperature information are/is sent to a remote control terminal as the temperature of the cold-chain logistics vehicle;

the LSTM with the double doors comprises two input doors and two forgetting doors, the two input doors respectively receive the motion state and the temperature sensor state information of the cold-chain logistics vehicle, analyze the motion state and the temperature sensor state information simultaneously, and output the confidence coefficient of the first temperature information of the user.

5. The method for monitoring the temperature of the internet of things for fresh food transportation of claim 1, wherein the first neural network is trained with the first image, wind speed information and a speed of the cold-chain logistics vehicle as inputs and a temperature in a cargo box of a standard cold-chain logistics vehicle as an output.

6. The method for monitoring the temperature of the internet of things for fresh food transportation according to claim 2, wherein a second neural network is trained by taking a second image, wind speed information and a speed of a cold-chain logistics vehicle as inputs, and a temperature in a container of a standard cold-chain logistics vehicle as an output; and taking the third image, the wind speed information and the speed of the cold-chain logistics vehicle as input, and taking the temperature in a container of the standard cold-chain logistics vehicle as output, and training a second neural network.

7. The method for monitoring the temperature of the Internet of things for fresh food transportation is characterized in that when the formation of the unmanned vehicle formation is changed, a plurality of tracks for moving the unmanned vehicles are generated according to a model prediction algorithm, a MLP-based neural network is built, a total cost function of the lane changing tracks of the unmanned vehicles is generated, and when the total cost function is minimum, the lane changing tracks of the unmanned vehicles serve as final lane changing tracks.

8. The utility model provides a system that is used for thing networking of bright food transportation to monitor temperature which characterized in that, this system includes:

the cooperative control module is used for forming the cold-chain logistics vehicles and the unmanned vehicles around the cold-chain logistics vehicles into an unmanned vehicle formation, at least one unmanned vehicle is in communication connection with the remote control terminal, and one unmanned vehicle is selected as a piloting vehicle; the system also comprises a communication module used for keeping the piloting vehicle in communication connection with the remote control terminal;

the remote control module is used for acquiring the configuration of the unmanned vehicle formation;

if the configuration is in linear arrangement, when the piloting vehicle is positioned behind the chain logistics vehicles, the unmanned vehicles respectively shoot first images behind the cold chain logistics vehicles through the infrared cameras; inputting the first image, the wind speed information and the speed of the cold-chain logistics vehicle into a first neural network, and outputting second temperature information in a container of the cold-chain logistics vehicle by the first neural network; and second temperature information is sent to a piloting vehicle, the cold-chain logistics vehicle sends the first temperature information to the piloting vehicle, and the piloting vehicle fuses the first temperature information and the second temperature information and then sends the fused information to the remote control terminal.

9. The system for monitoring the temperature of the internet of things for fresh food transportation according to claim 8, wherein the remote control module is used for acquiring the configuration of the formation of the unmanned vehicles, and if the configuration is arranged in parallel, the unmanned vehicles respectively shoot second images of the left side of the cold-chain logistics vehicle through the infrared cameras; inputting the second image, the wind speed information and the vehicle speed of the cold-chain logistics vehicle into a second neural network, outputting third temperature information in a container of the cold-chain logistics vehicle by the second neural network, and sending the third temperature information to a piloting vehicle; and/or the unmanned vehicle respectively shoots a third image of the left side of the cold-chain logistics vehicle through the infrared cameras; inputting a third image, wind speed information and the speed of the cold-chain logistics vehicle into a third neural network, outputting fourth temperature information in a container of the cold-chain logistics vehicle by the third neural network, and sending the fourth temperature information to a piloting vehicle; and the piloting vehicle fuses the first temperature information, the third temperature information and/or the fourth temperature information and then sends the fused information to the remote control terminal.

Images