A method, system and apparatus for visual ripening of fruit suitable for transport vehicles

Abstract

The application discloses a fruit visual ripening method, system and device suitable for a transport vehicle, and relates to the technical field of fruit ripening, and aims to realize real-time monitoring of fruit ripening during fruit transportation and control of a ripening agent and temperature and humidity, so that the fruit can reach a preset maturity when transported to a destination, and the purposes of saving storage and improving capital recycling efficiency are achieved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of food transportation, in particular to a fruit visual ripening method, system and device suitable for a transport vehicle. BACKGROUND

[0002] In the industry chain of fruit picking-transportation-sale, the transportation of fruits usually takes a long time, resulting in that the maturity of fruits at the time of sale is much higher than that at the time of picking. In view of this phenomenon, experienced fruit growers will pick fruits before they are mature, and after transportation to the destination, the fruits will be placed in the warehouse and sold in batches according to the maturity of the fruits. In this way, it is inevitable to occupy the storage space and affect the sales progress, which is not conducive to the capital recovery. At the same time, the maturity progress of fruits during transportation is not planned, and the maturity of fruits when reaching the destination is uncertain, which is also not conducive to the arrangement of storage by the staff. Therefore, it is necessary to control the change of maturity of fruits in the transportation process in real time. In the prior art, CN201610629021.9-Multi-purpose vehicle based on ripening gas control and transportation method improves the versatility during fruit transportation, but there is no real-time monitoring and alarm of fruit maturity, and if it is necessary to judge the maturity of fruits, it is necessary to observe by certain professional knowledge personnel; CN201510786659.9-Fruit and vegetable transportation box with ripening function also does not have real-time monitoring and alarm of fruit maturity, and the change of maturity of fruits during transportation cannot be controlled.

[0003] Therefore, those skilled in the art urgently need to develop a new technical solution to solve the above problems. SUMMARY

[0004] In order to overcome the problems in the related art, the present disclosure provides a fruit visual ripening method, system and device suitable for a transport vehicle.

[0005] According to a first aspect of the present disclosure, a fruit visual ripening method suitable for a transport vehicle is provided, which is applied to a fruit visual ripening system suitable for a transport vehicle, the system at least comprising: a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator and a temperature control assembly; the method comprising:

[0006] During the transportation of fruits, the image of the target fruit needing to be ripened is collected in real time by the camera to obtain a target image;

[0007] According to the target image and a pre-trained fruit maturity recognition model, the maturity of the target fruit is determined;

[0008] According to the maturity of the target fruit and the pre-trained fruit ripening model, a target environmental parameter required for ripening the target fruit to a target maturity is determined, the target environmental parameter including a first preset time for a carbon dioxide generator to release carbon dioxide, a second preset time for an oxygen generator to release oxygen, a third preset time for an ethylene generator to release ethylene, and a fourth preset time for a temperature control component to increase temperature;

[0009] According to the target environmental parameter, the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator, and the temperature control component are adjusted to catalyze the target fruit to the target maturity;

[0010] The training method of the fruit maturity recognition model is:

[0011] For each type of fruit, a preset number of sample fruit images Ph are obtained;

[0012] The special vector Y of the sample fruit image Ph is extracted through a ResNet neural network or a ViT neural network;

[0013] The sample fruit maturity prediction value Rp corresponding to the special vector Y is obtained through a fully connected layer;

[0014] The sample fruit image Ph is taken as input, the sample fruit maturity prediction value Rp is taken as output, and the fruit maturity recognition model is trained by taking the loss function as , wherein, is the sample fruit maturity true value, is the sample number.

[0015] Optionally, the sample fruit maturity true value is obtained by the following method:

[0016] For each type of fruit, the fruit maturity at the appropriate picking time is set to 0, and the fruit maturity at the time when it must be eaten immediately or it will go bad is set to 100;

[0017] The total time for the sample fruit to develop from 0 to 100 in a constant temperature and humidity environment is set to t;

[0018] The total time t is evenly divided into 99 time nodes t1, t2, t3, …, t98, t99, the sample fruit images corresponding to the 99 time nodes are obtained, and the sample fruit maturity true values are 1, 2, 3, …, 98, 99.

[0019] According to a second aspect of the present disclosure, a fruit visual ripening system suitable for a transport vehicle is provided, the system applying any of the fruit visual ripening methods described above, the system comprising: a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator, a temperature control component, and a main controller, the main controller being electrically connected with the camera, the carbon dioxide generator, the oxygen generator, the ethylene generator, and the temperature control component, respectively;

[0020] The camera is configured to acquire images of target fruits in need of ripening in real time during the transportation of the fruits, and obtain target images.

[0021] The main controller is configured to:

[0022] determine the ripeness of the target fruits according to the target images and a pre-trained fruit ripeness recognition model;

[0023] determine target environmental parameters required for ripening the target fruits to a target ripeness according to the ripeness of the target fruits and a pre-trained fruit ripening model, the target environmental parameters including a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene, and a fourth preset time for the temperature control component to increase temperature.

[0024] The carbon dioxide generator, the oxygen generator, the ethylene generator, and the temperature control component are configured to:

[0025] adjust working parameters according to the target environmental parameters to ripen the target fruits to the target ripeness.

[0026] Optionally, the system further comprises: an oxygen sensor, a temperature sensor, a humidity sensor, an ethylene sensor, and a carbon dioxide sensor, the oxygen sensor, the temperature sensor, the humidity sensor, the ethylene sensor, and the carbon dioxide sensor being electrically connected with the main controller, respectively.

[0027] The oxygen sensor is configured to monitor the oxygen concentration in the transport vehicle in real time.

[0028] The temperature sensor is configured to monitor the temperature in the transport vehicle in real time.

[0029] The humidity sensor is configured to monitor the humidity in the transport vehicle in real time.

[0030] The ethylene sensor is configured to monitor the ethylene concentration in the transport vehicle in real time.

[0031] The carbon dioxide sensor is configured to monitor the carbon dioxide concentration in the transport vehicle in real time.

[0032] Optionally, the system further comprises an air circulation assembly electrically connected to the main controller, wherein the air circulation assembly comprises an inner circulation unit and an outer circulation unit.

[0033] The inner circulation unit is configured to make the gas in the transport vehicle uniform.

[0034] The outer circulation unit is configured to discharge oxygen, carbon dioxide and ethylene in the transport vehicle.

[0035] Optionally, the system further comprises a communication unit.

[0036] The communication unit is configured to send data to an external mobile device or receive data from an external mobile device.

[0037] Optionally, the system further comprises a power supply unit.

[0038] The power supply unit is connected to the on-board battery and configured to supply power to the fruit visual ripening system.

[0039] According to a third aspect of the present disclosure, a fruit visual ripening device suitable for a transport vehicle is provided, which applies any of the fruit visual ripening methods described above and is applied to a fruit visual ripening system suitable for a transport vehicle, wherein the system at least comprises a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator and a temperature control assembly; and the device comprises:

[0040] An image acquisition module is configured to acquire images of target fruits to be ripened by the camera in real time during the transportation of the fruits, and obtain target images.

[0041] A maturity determination module is connected to the image acquisition module and configured to determine the maturity of the target fruits according to the target images and a pre-trained fruit maturity recognition model.

[0042] An environmental parameter acquisition module is connected to the maturity determination module and configured to determine target environmental parameters required for ripening the target fruits to a target maturity according to the maturity of the target fruits and a pre-trained fruit ripening model, wherein the target environmental parameters include a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene and a fourth preset time for the temperature control assembly to increase temperature.

[0043] A working parameter adjustment module is connected to the environmental parameter acquisition module and configured to adjust the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control assembly according to the target environmental parameters, so as to ripen the target fruits to the target maturity.

[0044] In summary, the technical solutions in the embodiments of the present application can bring the following beneficial effects:

[0045] 1) Real-time monitoring of fruit ripening during fruit transportation by machine vision, and then controlling the ripening agent and temperature and humidity, so that the fruit enters the ripening process during transportation, and reaches the preset maturity when it reaches the destination, and then can enter the sales process as soon as possible, which can save storage, improve capital recycling efficiency, and save costs;

[0046] 2) According to the fruit image collected by the camera, the trained fruit maturity recognition model can scientifically and quantitatively determine the maturity of the fruit, without relying on professional personnel, and the monitoring result is not disturbed by other factors, and the accuracy of maturity determination is improved;

[0047] 3) The sensor assembly is used to monitor the environmental parameters in the transport vehicle in real time, and the catalyst concentration and temperature and humidity control are combined to adjust the environmental index in the transport vehicle / warehouse according to the maturity, so as to achieve the preset effect.

[0048] Other features and advantages of the present application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and are used to explain the present disclosure together with the following specific embodiments, but do not constitute a limitation of the present disclosure. In the drawings:

[0050] Figure 1 is a flowchart of a fruit visual ripening method suitable for a transport vehicle according to an exemplary embodiment;

[0051] Figure 2 is a schematic diagram of a fruit visual ripening system suitable for a transport vehicle according to an exemplary embodiment;

[0052] Figure 3 is a schematic diagram of a fruit maturity recognition model training process;

[0053] Figure 4 is a schematic diagram of a fruit ripening model training process;

[0054] Figure 5 is a structural block diagram of a fruit visual ripening device suitable for a transport vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0055] The specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0056] Figure 1 is a flowchart of a fruit visual ripening method suitable for a transport vehicle according to an exemplary embodiment, as shown in Figure 1 , the method comprises:

[0057] In step 101, during the transportation of the fruit, the image of the target fruit that needs to be ripened is collected in real time by a camera to obtain a target image.

[0058] For example, the ripening of the fruit during transportation is monitored in real time by machine vision, and then the ripening agent and temperature and humidity are controlled to make the fruit reach the preset maturity when it arrives at the destination. In the disclosed embodiment, the target image of the target fruit is collected in real time by a camera, and the maturity of the target fruit is identified according to the target image.

[0059] It can be understood that the fruit visual ripening method in the disclosed embodiment is applied to a fruit visual ripening system, as shown in Figure 2 , the system at least comprises: a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator and a temperature control component; through the mutual cooperation of each component in the system, the target fruit can be ripened to the target maturity during transportation. Among them, the camera is used to collect the target image, and the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component are used to release the ripening agent and control the temperature and humidity, so that the environmental parameters in the transport vehicle reach the target environmental parameters required for ripening.

[0060] In step 102, the maturity of the target fruit is determined according to the target image and a pre-trained fruit maturity recognition model.

[0061] For example, after obtaining the target image, the target image is taken as the input of the trained fruit maturity recognition model, and the maturity of the target fruit is determined according to the output of the fruit maturity recognition model.

[0062] The training method of the fruit maturity recognition model is as follows:

[0063] For each type of fruit, a preset number of sample fruit images Ph are obtained; the special vector Y of the sample fruit image Ph is extracted by the ResNet neural network or the ViT neural network; the sample fruit maturity prediction value Rp corresponding to the special vector Y is obtained by the full connection layer; the sample fruit image Ph is taken as the input, the sample fruit maturity prediction value Rp is taken as the output, and the fruit maturity recognition model is trained by taking as the loss function, wherein is the true value of the sample fruit maturity, The number of samples.

[0064] For example, Figure 3 is a schematic diagram of a fruit ripeness recognition model training process, as Figure 3 shown, a large number of sample fruits are obtained, the types of sample fruits include apples, bananas, grapes, strawberries, etc., the ripening speed and appearance of different types of sample fruits are different, therefore, each type corresponds to a ripeness recognition model. Take the sample fruit image Ph as input, and the sample fruit ripeness prediction value Rp as output for training, when extracting the label, the special vector Y of the sample fruit image Ph is extracted through the ResNet neural network or the ViT neural network; the sample fruit ripeness prediction value Rp corresponding to the special vector Y is obtained through the full connection layer. Wherein, Rp is the sample fruit ripeness obtained after the special vector Y is processed by full connection, Resnet backbone is a general neural network skeleton, and FC is full connection.

[0065] The loss function during training is , is the true value of the sample fruit ripeness, Rp is the sample fruit ripeness prediction value, is the number of samples.

[0066] Wherein, the true value of the sample fruit ripeness is obtained by: for each type of fruit, the fruit ripeness when suitable for picking is set to 0, and the fruit ripeness when it must be eaten immediately or it will go bad is set to 100; the total time for the sample fruit to develop from 0 to 100 in a constant temperature and humidity environment is set to t; the total time t is evenly divided into 99 time nodes t1, t2, t3, …, t98, t99, the sample fruit images corresponding to the 99 time nodes are obtained, and the sample fruit ripeness true value is 1, 2, 3, …, 98, 99.

[0067] Specifically, three farmers independently judge, set the ripeness when suitable for picking from the tree as 0, and set the ripeness when it must be eaten or disposed of otherwise it will go bad as 100. Let the three farmers randomly judge the ripeness of the sample fruit, which are R1, R2, and R3 respectively. When max{R1, R2, R3}-min{R1, R2, R3} < 20, take the ripeness as mean{R1, R2, R3}, otherwise, discard this time of labeling.

[0068] In order to reduce the workload, the fruit with maturity of 0 is placed in a constant temperature and humidity environment, and continuous shooting is started at this time t0, and when the maturity reaches 100, the time is t100. The total time is averaged to 99 time points from t0 to t100, which are t1, t2, t3, …… t99 respectively. Each time point corresponds to the maturity Urp of the photo, which is 1~99 respectively.

[0069] In step 103, according to the maturity of the target fruit and the pre-trained fruit ripening model, the target environmental parameter required to ripen the target fruit to the target maturity is determined.

[0070] Among them, the target environmental parameter includes: the first preset time of the carbon dioxide generator releasing carbon dioxide, the second preset time of the oxygen generator releasing oxygen, the third preset time of the ethylene generator releasing ethylene and the fourth preset time of the temperature control component increasing temperature.

[0071] For example, after obtaining the maturity of the target fruit, the maturity is taken as the input of the trained fruit ripening model, and the target environmental parameter is determined according to the output of the fruit ripening model. The target environmental parameter is the concentration of each ripening agent in the transport vehicle and the environmental temperature. That is, the working time of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component.

[0072] It should be noted that the influence of each sensing index on fruit ripening: the higher the ethylene concentration (the greatest influence), the faster the fruit ripening; the higher the temperature, the faster the fruit ripening; the higher the oxygen concentration, the faster the fruit ripening; the higher the carbon dioxide concentration, the faster the fruit ripening. After experimental research, the working start sequence of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component in the fruit visual ripening method disclosed in the embodiment is: preferentially regulating the ethylene concentration (releasing ethylene through the ethylene generator or opening the external circulation), regulating the carbon dioxide concentration (releasing carbon dioxide through the carbon dioxide generator or opening the external circulation), regulating the oxygen concentration (releasing oxygen through the oxygen generator or opening the external circulation), and finally regulating the temperature (opening the temperature control component). The demand for cost minimization can be realized. It can be understood that releasing ethylene through the ethylene generator is to increase the ethylene concentration, opening the external circulation is to reduce the ethylene concentration, and the working principles of the carbon dioxide generator and the oxygen generator are the same.

[0073] The training method of the fruit ripening model is: for each type of fruit, a special vector Y corresponding to the sample fruit image Ph extracted by the ResNet neural network or the ViT neural network is obtained; the sensor parameters Sr of the sample fruit are obtained, the sensor parameters Sr include: the working time Test of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component planned for ripening at the current time node, and the maturity Rpset of the ripening end point at the current time node; the training feature value h of the special vector Y and the sensor parameters Sr is extracted by the RNN neural network; the sample environment parameters corresponding to the training feature value are obtained, the sample environment parameters include: the operation Op of starting the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component, the preset time Tr of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component for ripening, and the maturity Prp of the target fruit according to the operation Op at the current time node to the next time node; the maturity Rp of the sample fruit is taken as the input, the sample environment parameters are taken as the output, the loss function is trained, and the fruit ripening model is obtained.

[0074] Wherein, Op is an array [kc, ko, kch, kt, …], taking the carbon dioxide generator as an example, kc=0, which means closing the carbon dioxide generator; kc=0.5, which means opening the carbon dioxide generator for half of the next time node; kc=1, which means opening the carbon dioxide generator for the whole next time node. kc represents the operation corresponding to the carbon dioxide generator, ko represents the operation corresponding to the oxygen generator, kch represents the operation corresponding to the ethylene generator, and kt represents the operation corresponding to the temperature control component.

[0075] For example, Figure 4 is a schematic diagram of a fruit ripening model training process, as Figure 4 shown, a large number of sample fruits are obtained and the maturity Rp of the sample fruits is determined, the maturity Rp of the sample fruits and the maturity Rpset (i.e. target maturity) of the ripening end point are taken as the input, the sensor parameters Sr of the sample fruits are taken as the output, the loss function is trained, and the fruit ripening model is obtained.

[0076] In step 104, the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component are adjusted according to the target environment parameters, so as to catalyze the target fruit to the target maturity.

[0077] For example, the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component are adjusted in a preset order according to the target environment parameters, so as to ensure that the target fruit can reach the preset maturity during transportation.

[0078] Figure 2is a schematic diagram of a fruit visualized ripening system suitable for a transport vehicle according to an exemplary embodiment, as shown in Figure 2 The system comprises a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator, a temperature control assembly, and a main controller, which is electrically connected with the camera, the carbon dioxide generator, the oxygen generator, the ethylene generator, and the temperature control assembly respectively; the camera is configured to acquire images of target fruits in need of ripening in real time during the transportation of the fruits, and obtain target images; the main controller is configured to determine the ripeness of the target fruits according to the target images and a pre-trained fruit ripeness recognition model, and determine target environmental parameters required for ripening the target fruits to a target ripeness according to the ripeness of the target fruits and a pre-trained fruit ripening model, the target environmental parameters comprising a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene, and a fourth preset time for the temperature control assembly to increase temperature; the carbon dioxide generator, the oxygen generator, the ethylene generator, and the temperature control assembly are configured to adjust working parameters according to the target environmental parameters, so as to ripen the target fruits to the target ripeness.

[0079] Optionally, the system further comprises an oxygen sensor, a temperature sensor, a humidity sensor, an ethylene sensor, and a carbon dioxide sensor, which are electrically connected with the main controller respectively; the oxygen sensor is configured to monitor the oxygen concentration in the transport vehicle in real time; the temperature sensor is configured to monitor the temperature in the transport vehicle in real time; the humidity sensor is configured to monitor the humidity in the transport vehicle in real time; the ethylene sensor is configured to monitor the ethylene concentration in the transport vehicle in real time; and the carbon dioxide sensor is configured to monitor the carbon dioxide concentration in the transport vehicle in real time.

[0080] Optionally, the system further comprises an air circulation assembly electrically connected with the main controller, the air circulation assembly comprising an internal circulation unit and an external circulation unit; the internal circulation unit is configured to make the gas in the transport vehicle uniform; and the external circulation unit is configured to discharge oxygen, carbon dioxide, and ethylene in the transport vehicle.

[0081] Optionally, the system further comprises a communication unit; the communication unit is configured to send data to an external mobile device, or receive data from the external mobile device.

[0082] Optionally, the system further comprises a power supply unit (not shown in the figure); the power supply unit is connected with a vehicle-mounted battery, and is configured to supply power to the fruit visualized ripening system.

[0083] Exemplarily, the core components of the system are: a main controller, a sensor part (ethylene sensor, oxygen sensor, carbon dioxide sensor, temperature sensor, and humidity sensor), external devices (carbon dioxide generator, oxygen generator, ethylene generator, air circulation assembly, temperature control assembly, camera), and a power supply unit (not shown in the figure).

[0084] The main controller receives various sensor signals (including the current vehicle compartment internal environment parameters collected by the sensors) and performs operation processing, and finally outputs corresponding data or control instructions to the external devices; the communication unit (embedded in some processors) can be a remote wireless transmission component, such as NB-Lot, 2 / 3 / 4 / 5G; the input can be a button, touch screen, knob, wireless control, etc.; the output can be a vibrator, sound reminder, wireless transmission, display screen, etc.; the oxygen generator is a molecular sieve oxygen module, a compressed oxygen tank, or a chemical oxygen module, responsible for supplementing the preset oxygen concentration to the closed space; the carbon dioxide generator is a compressed CO2 tank or a chemical CO2 module, responsible for supplementing the preset CO2 concentration to the closed space; the ethylene generator is a compressed C2H2 tank or a chemical C2H2 module, responsible for supplementing the preset C2H2 concentration to the closed space; each sensor respectively monitors the O2 concentration, CO2 concentration, C2H2 concentration, environmental temperature T, and humidity RH; the air circulation assembly includes an internal circulation for the closed space to make the gas concentration uniform, and an external circulation to discharge C2H2, CO2, and other gases; the temperature control assembly is responsible for adjusting the temperature of the closed space; the camera is used to observe the appearance of the fruit; the power supply unit can be connected to the vehicle battery or a self-owned battery, and can supply different voltages to different electronic devices.

[0085] Figure 5 is a structural block diagram of a fruit visual ripening device suitable for a transport vehicle according to an exemplary embodiment, as shown in Figure 5 applied to a fruit visual ripening system suitable for a transport vehicle, the system at least includes a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator, and a temperature control assembly; the device 500 includes:

[0086] An image acquisition module 510 acquires images of target fruits that need to be ripened in real time through the camera during the transportation of the fruits, and obtains target images;

[0087] A ripeness judgment module 520 is connected to the image acquisition module 510, determines the ripeness of the target fruits according to the target images and a pre-trained fruit ripeness recognition model;

[0088] The environment parameter acquisition module 530 is connected with the maturity judgment module 520, and determines the target environment parameter required for ripening the target fruit to the target maturity according to the maturity of the target fruit and the pre-trained fruit ripening model, wherein the target environment parameter comprises a first preset time of releasing carbon dioxide by the carbon dioxide generator, a second preset time of releasing oxygen by the oxygen generator, a third preset time of releasing ethylene by the ethylene generator, and a fourth preset time of increasing temperature by the temperature control component.

[0089] The working parameter adjustment module 540 is connected with the environment parameter acquisition module 530, and adjusts the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component according to the target environment parameter, so as to ripen the target fruit to the target maturity.

[0090] In summary, the present disclosure relates to a fruit visual ripening method, system and device suitable for a transport vehicle, which comprises: in the process of transporting the fruit, acquiring a target image by real-time collecting the image of the target fruit to be ripened through a camera; determining the maturity of the target fruit according to the target image and a pre-trained fruit maturity recognition model; determining the target environment parameter required for ripening the target fruit to the target maturity according to the maturity of the target fruit and a pre-trained fruit ripening model; and adjusting the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component according to the target environment parameter, so as to ripen the target fruit to the target maturity. The maturity of the fruit can be monitored in real time during the transportation of the fruit through machine vision, and then the ripening agent and the temperature and humidity are controlled, so that the fruit can reach the preset maturity when it is transported to the destination, thereby achieving the purposes of saving storage and improving the efficiency of capital recycling.

[0091] The preferred embodiments of the present disclosure are described in detail above with reference to the drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0092] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction, and in order to avoid unnecessary repetition, the present disclosure will not further describe various possible combination manners.

[0093] In addition, various different embodiments of the present disclosure can also be combined in any manner, as long as they do not deviate from the idea of the present disclosure, and they should also be considered as disclosed by the present disclosure.

Claims

1. A method for visual ripening of fruits suitable for transport vehicles, characterized in that, The application is applied to a fruit visual ripening system suitable for a transport vehicle, and the system at least comprises a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator and a temperature control component; the method comprises: During the transportation of the fruit, the image of the target fruit that needs to be ripened is collected in real time by the camera to obtain a target image; According to the target image and a pre-trained fruit maturity recognition model, the maturity of the target fruit is determined; According to the maturity of the target fruit and a pre-trained fruit ripening model, target environmental parameters required for ripening the target fruit to a target maturity are determined, and the target environmental parameters include a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene and a fourth preset time for the temperature control component to increase temperature; According to the target environmental parameters, the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component are adjusted to ripen the target fruit to the target maturity; The training method of the fruit maturity recognition model is: For each type of fruit, a preset number of sample fruit images Ph are obtained; The special vector Y of the sample fruit image Ph is extracted by a ResNet neural network or a ViT neural network; The sample fruit maturity prediction value Rp corresponding to the special vector Y is obtained by a full connection layer; Take the sample fruit image Ph as input, take the sample fruit maturity prediction value Rp as output, take the loss function as Training to obtain a fruit maturity recognition model, wherein, Rp is the sample fruit maturity true value, is the sample quantity.

2. The fruit visual ripening method suitable for transport vehicles according to claim 1, characterized in that, The sample fruit maturity real value The acquisition method is: For each type of fruit, the fruit maturity at the appropriate picking time is set to 0, and the fruit maturity at the time when it must be eaten immediately or it will go bad is set to 100; The total time for the sample fruit to develop from 0 to 100 in a constant temperature and humidity environment is set to t; The total time t is evenly divided into 99 time nodes t1, t2, t3, …, t98, t99, sample fruit images corresponding to the 99 time nodes are acquired, and sample fruit maturity true values are acquired are 1, 2, 3, …, 98, 99.

3. A fruit visual ripening system suitable for use in a transport vehicle, said system applying any of the fruit visual ripening methods according to claims 1-2, characterized in that, The system comprises a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator, a temperature control component and a main controller, and the main controller is electrically connected with the camera, the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component respectively; The camera is used to collect the image of the target fruit that needs to be ripened in real time during the transportation of the fruit to obtain a target image; The main controller is used to: According to the target image and a pre-trained fruit maturity recognition model, the maturity of the target fruit is determined; According to the maturity of the target fruit and a pre-trained fruit ripening model, target environmental parameters required for ripening the target fruit to a target maturity are determined, and the target environmental parameters include a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene and a fourth preset time for the temperature control component to increase temperature; The carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control component are used to: According to the target environmental parameters, the working parameters are adjusted to ripen the target fruit to the target maturity.

4. The fruit visual ripening system suitable for use in a transport vehicle according to claim 3, characterized in that, The system further comprises an oxygen sensor, a temperature sensor, a humidity sensor, an ethylene sensor and a carbon dioxide sensor, which are electrically connected with the main controller respectively; The oxygen sensor is used for monitoring the oxygen concentration in the transport vehicle in real time; The temperature sensor is used for monitoring the temperature in the transport vehicle in real time; The humidity sensor is used for monitoring the humidity in the transport vehicle in real time; The ethylene sensor is used for monitoring the ethylene concentration in the transport vehicle in real time; The carbon dioxide sensor is used for monitoring the carbon dioxide concentration in the transport vehicle in real time.

5. The fruit visual ripening system suitable for use in a transport vehicle according to claim 3, characterized in that, The system further comprises an air circulation assembly electrically connected with the main controller, which comprises an inner circulation unit and an outer circulation unit; The inner circulation unit is used for making the gas in the transport vehicle uniform; The outer circulation unit is used for discharging oxygen, carbon dioxide and ethylene in the transport vehicle.

6. The fruit visual ripening system suitable for use in a transport vehicle according to claim 5, characterized in that, The system further comprises a communication unit; The communication unit is used for sending data to an external mobile device or receiving data from an external mobile device.

7. The fruit visual ripening system suitable for use in a transport vehicle according to claim 6, characterized in that, The system further comprises a power supply unit; The power supply unit is connected with the vehicle-mounted battery and is used for supplying power for the fruit visual ripening system.

8. A fruit visual ripening device suitable for use in a transport vehicle, said device applying any of the fruit visual ripening methods as claimed in claims 1-2, characterized in that, The fruit visual ripening system applied to the transport vehicle comprises at least a camera, a carbon dioxide generator, an oxygen generator, an ethylene generator and a temperature control assembly; the device comprises: An image acquisition module, which acquires the image of the target fruit to be ripened in real time through the camera during the transportation of the fruit, and obtains a target image; A maturity judgment module connected with the image acquisition module, which determines the maturity of the target fruit according to the target image and a pre-trained fruit maturity recognition model; An environment parameter acquisition module connected with the maturity judgment module, which determines the target environment parameter required for ripening the target fruit to a target maturity according to the maturity of the target fruit and a pre-trained fruit ripening model, wherein the target environment parameter comprises a first preset time for the carbon dioxide generator to release carbon dioxide, a second preset time for the oxygen generator to release oxygen, a third preset time for the ethylene generator to release ethylene and a fourth preset time for the temperature control assembly to increase temperature; A working parameter adjustment module connected with the environment parameter acquisition module, which adjusts the working parameters of the carbon dioxide generator, the oxygen generator, the ethylene generator and the temperature control assembly according to the target environment parameter, so as to ripen the target fruit to the target maturity.

Images