CN118457322B - A smart shopping cart charging safety management system and method - Google Patents
A smart shopping cart charging safety management system and method Download PDFInfo
- Publication number
- CN118457322B CN118457322B CN202410929099.7A CN202410929099A CN118457322B CN 118457322 B CN118457322 B CN 118457322B CN 202410929099 A CN202410929099 A CN 202410929099A CN 118457322 B CN118457322 B CN 118457322B
- Authority
- CN
- China
- Prior art keywords
- charging
- shopping cart
- intelligent
- intelligent shopping
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims abstract description 17
- 238000007726 management method Methods 0.000 claims description 18
- 238000012015 optical character recognition Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/10—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles characterised by the energy transfer between the charging station and the vehicle
- B60L53/14—Conductive energy transfer
- B60L53/16—Connectors, e.g. plugs or sockets, specially adapted for charging electric vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/30—Constructional details of charging stations
- B60L53/31—Charging columns specially adapted for electric vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/30—Constructional details of charging stations
- B60L53/35—Means for automatic or assisted adjustment of the relative position of charging devices and vehicles
- B60L53/37—Means for automatic or assisted adjustment of the relative position of charging devices and vehicles using optical position determination, e.g. using cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2200/00—Type of vehicles
- B60L2200/30—Trolleys
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Handcart (AREA)
Abstract
The invention provides an intelligent shopping cart charging safety management system and method, wherein the intelligent shopping cart charging safety management system comprises an intelligent shopping cart, a charging pile and a background system; the intelligent shopping cart is provided with a front electrode, a rear electrode, a temperature sensor, a front camera, a visual sensor and an intelligent terminal; the intelligent terminal acquires the charging temperature and the feature number and sends the charging temperature and the feature number to a background system; the background system generates a charging chain according to the charging temperature and the feature number, and detects each node in the charging chain; the background system sends a charging disconnection instruction to an intelligent terminal corresponding to a node with the temperature exceeding a threshold value in the charging chain or a node with the terminal exceeding the limit of the number of the nodes; the intelligent terminal controls the intelligent shopping cart in which the intelligent terminal is positioned to disconnect the charging circuit. Monitoring the temperature of the intelligent shopping cart in real time, and switching off a charging switch when the temperature exceeds a temperature threshold; accurately controlling the number of intelligent shopping carts connected into the charging piles; and the overload risk is effectively avoided.
Description
Technical Field
The invention relates to an intelligent shopping cart charging safety management system and method, and belongs to the field of intelligent shopping carts.
Background
The current intelligent shopping cart charging system has the common problem that the number of the charging vehicle devices is difficult to effectively control and simultaneously access. When a plurality of intelligent shopping carts are simultaneously connected into the charging, the overload of the electric load of the charging pile can be caused, potential safety hazards such as equipment overheat, line damage, even power grid stability reduction and the like are induced, in addition, the number of the plug-in connectors is too large, the stability of the plug-in connectors of the vehicles due to assembly tolerance is reduced, poor contact can be generated, and the problems of heating, melting and the like of contact points caused by overlarge contact resistance can be solved.
Disclosure of Invention
The invention provides an intelligent shopping cart charging safety management system and method, which solve the problems disclosed in the background technology.
In order to solve the technical problems, the invention adopts the following technical scheme:
An intelligent shopping cart charging safety management system comprises an intelligent shopping cart, a charging pile and a background system; the intelligent shopping cart is provided with a front electrode, a rear electrode, a temperature sensor, a front camera, a visual sensor and an intelligent terminal; during charging, a plurality of intelligent shopping carts are sleeved and inserted to form a charging queue, a front electrode of a first intelligent shopping cart of the charging queue is connected with a charging pile, and a front electrode of the intelligent shopping carts except the first intelligent shopping cart in the charging queue is used for being in contact with a rear electrode of a previous intelligent shopping cart to realize serial charging; the temperature sensor is used for collecting the charging temperature of the intelligent shopping cart; the front camera acquires an intelligent shopping cart sleeving state image; the charging pile and the intelligent shopping cart are marked with feature numbers, and the vision sensor is used for extracting the feature number of the charging pile or the intelligent shopping cart in front of the charging pile; the intelligent terminal is used for judging whether the intelligent shopping cart is in the inserting state according to the inserting state image, detecting whether the intelligent shopping cart is in the charging state or not if the intelligent shopping cart is in the inserting state, and acquiring the charging temperature and the feature number and sending the charging temperature and the feature number to the background system if the intelligent shopping cart is in the charging state; the background system generates a charging chain according to the charging temperature and the feature number, and detects each node in the charging chain; the background system sends a charging disconnection instruction to an intelligent terminal corresponding to a node with the temperature exceeding a threshold value in the charging chain or a node with the terminal exceeding the limit of the number of the nodes; the intelligent terminal controls the intelligent shopping cart in which the intelligent terminal is positioned to disconnect the charging circuit.
Further, the intelligent terminal is provided with an OCR (optical character recognition) module, and the intelligent terminal recognizes the feature number through the OCR module.
Further, the intelligent terminal is provided with a wireless communication module, and the intelligent terminal establishes communication with a background system through the wireless communication module.
Further, the background system is provided with a counting module, and the counting module is used for calculating the number of intelligent shopping carts connected with the charging piles.
Further, the intelligent terminal is provided with a GPIO interface, and the intelligent terminal controls the charging switch through the GPIO interface.
Further, the background system is a cloud server.
The invention also provides an intelligent shopping cart charging safety management method, which comprises the following steps:
step1, acquiring an intelligent shopping cart sleeving state image;
Step 2, judging whether the intelligent shopping cart is in the inserting state according to the intelligent shopping cart inserting state image; if the intelligent shopping cart is in the inserting state, the step 3 is carried out, otherwise, the step 1 is returned;
Step 3, judging whether the intelligent shopping cart is in a charging state, if so, entering a step 4, otherwise, returning to the step 2 or the step 1;
step 4, identifying the feature number of the charging pile or the intelligent shopping cart in front of the charging pile;
Step 5, transmitting the identified feature numbers and the charging temperatures of the intelligent shopping carts to a background system;
step 6, the background system generates a charging chain according to the charging temperature and the feature number;
step 7, the background system detects whether a node with the temperature exceeding a threshold value exists in the charging chain or whether the end of the charging chain exceeds the limit of the number of the nodes, if so, the step 8 is started, and otherwise, the step 6 is returned;
step 8, the background system sends a charging disconnection instruction to the intelligent shopping cart corresponding to the node with the temperature exceeding the threshold value in the charging chain or the node with the terminal exceeding the limit of the number of the nodes;
And 9, after receiving the charging disconnection instruction, the corresponding intelligent shopping cart disconnects the charging switch.
Further, in the step 2, a visual algorithm is adopted to process the intelligent shopping cart inserting state image to judge whether the intelligent shopping cart is in the inserting state.
Further, in the step 4, the feature number of the charging post or the previous intelligent shopping cart is identified by adopting an OCR (optical character recognition) algorithm.
The invention has the beneficial effects that: monitoring the temperature of the intelligent shopping cart in real time, and switching off a charging switch when the temperature exceeds a temperature threshold; accurately controlling the number of intelligent shopping carts connected into the charging piles; and the overload risk is effectively avoided.
Drawings
FIG. 1 is a schematic diagram of a smart shopping cart according to the present invention;
FIG. 2 is a schematic diagram of the state of charge and the state of identification feature numbers of the intelligent shopping cart according to the present invention;
FIG. 3 is a schematic diagram of an intelligent shopping cart charging safety management system of the present invention;
FIG. 4 is a flow chart of the intelligent shopping cart charging safety management method.
Reference numerals:
1. A front electrode; 2. a rear electrode; 3. a temperature sensor; 4. a front camera; 5. a visual sensor; 6. an intelligent terminal; A. the feature number position of the charging pile; B. intelligent shopping cart feature number position; C. a vision sensor shooting area; D. the front camera shoots the area.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
As shown in fig. 1, the intelligent shopping system for the intelligent shopping cart charging safety management system is provided with a front electrode 1, a rear electrode 2, a temperature sensor 3, a front camera 4, a visual sensor 5, an intelligent terminal 6 and a charging switch; during charging, a plurality of intelligent shopping carts are sleeved and inserted to form a charging queue, a front electrode 1 of a first intelligent shopping cart of the charging queue is connected into a charging pile, and the front electrode 1 of the intelligent shopping carts except the first intelligent shopping cart in the charging queue is used for being in contact with a rear electrode 2 of a previous intelligent shopping cart to realize serial charging; the front electrode 1 and the rear electrode 2 are distributed below a basket of the intelligent shopping cart in a front-back mode; the temperature sensor 3 is arranged at the bottom of the basket of the intelligent shopping cart, is close to the position of the battery compartment of the intelligent shopping cart and is used for collecting the charging temperature of the intelligent shopping cart; the front camera 4 is arranged at the front end of the basket of the intelligent shopping cart and is used for collecting an intelligent shopping cart sleeve-inserting state image; the intelligent terminal 6 is arranged at the handle position of the intelligent shopping cart, the intelligent terminal 6 is a tablet personal computer, and the visual sensor 5 is arranged at the back of the intelligent terminal 6.
As shown in fig. 2, the charging pile feature number position a is located at the topmost end of the charging pile; the intelligent shopping cart feature number position B is positioned on the screen of the intelligent terminal 6; the visual sensor shooting area C covers the charging pile feature number position A or the intelligent shopping cart feature number position B and is positioned at the optimal shooting position; the front camera shooting area D covers the rear end of the whole intelligent shopping cart, and whether the vehicle is in a sleeve inserting state can be clearly judged.
As shown in fig. 3, the intelligent shopping cart charging safety management system of the invention comprises an intelligent shopping cart, a charging pile and a background system;
the feature number of the charging post is marked on the charging post at a position that can be photographed by the high-precision vision sensor 5. Ensuring that the first intelligent shopping cart can be clearly photographed by the vision sensor 5 when being charged.
When the intelligent shopping cart is in a charged state, the standby page of the screen of the intelligent terminal 6 (tablet computer) displays the feature number of the shopping cart, so that the visual sensor 5 of the rear cart can clearly shoot the feature number when the rear cart is inserted;
the feature number is managed and configured in the shopping cart owner data in the background system;
The front camera 4 of the intelligent shopping cart captures the inserting state of the shopping cart in real time, and the image recognition is carried out on the intelligent terminal 6 through the real-time video stream data acquired by the front camera 4 to confirm the inserting state. OCR recognition is turned on when the plug and charge state is detected.
When the intelligent shopping cart is in a charged state, charging neighbor recognition (OCR recognition of feature numbers on piles and front cart screen feature numbers) is carried out
When the intelligent shopping cart is charged, the intelligent terminal 6 reports the charging neighborhood information for one time at regular time, and the charging neighborhood information comprises self charging state, temperature, self characteristic number, front cart or charging pile characteristic number.
The background system receives the charging neighborhood information, caches the charging neighborhood information and forms a charging chain;
the charging chain is as follows:
Pile n— car 1 (numbering temperature) - - > -car 2 (numbering temperature) - - > -car 3 (numbering temperature) - - > -car 4 (numbering temperature) - - > -car 5 (numbering temperature) - - > - … … … … - > -car N (numbering temperature);
The background system continuously receives and reports, processes, removes weight and seeks sources, and spells a cache chain;
The background system supports interface checking and management of the charging chain;
and the background system sends a power-off instruction to all vehicles with the chain end exceeding the configuration number or vehicles with the temperature exceeding the set threshold value according to the system parameters when the number of the single-chain charges exceeds the configuration threshold value.
After receiving the instruction sent by the background system, the intelligent terminal 6 controls the intelligent shopping cart to automatically unlock and insert the sleeve through the GPIO interface, and stops charging.
And after the vehicle is successfully switched from the charging state to the unlocking state, reporting unlocking success information of 'uncharged' to a background system.
The intelligent terminal 6 is embedded with a high-performance wireless communication module (such as 4G/5G, wi-Fi, loRa and the like) to realize real-time data transmission between the intelligent shopping cart and a background system (cloud server), when the data received by the background system (cloud server) are sequenced through an algorithm to form a charging pile, after an array model of sequential access of each numbered vehicle is started, once the number of access devices of a certain charging device is monitored to reach a preset threshold, a control instruction for disconnecting the overrun charging connection is sent to the numbered intelligent shopping cart through a standardized communication interface.
The vehicle counting algorithm model is built by means of a background system (cloud server), license plate information recognized by OCR is updated to the background system (cloud server) in real time through a network of an intelligent shopping cart, connection information of each vehicle in the previous time can be formed on the background system (cloud server), a charging pile is formed as an initial, a plurality of groups of models are sequentially accessed by vehicles with different numbers, the number of vehicles accessing each charging device is ensured, and counting accuracy is ensured.
The intelligent shopping cart controls the intelligent switch through the GPIO interface, and the intelligent switch keeps a normally closed state under normal conditions, so that normal serial plug charging is ensured. When the number of the intelligent shopping carts connected to a certain charging pile or the charging temperature reaches a preset threshold value, a control instruction for disconnecting the overrun charging connection is sent to the intelligent shopping carts with the number through a standardized communication interface. After receiving the command of cutting off the overrun charging connection, triggering the internal intelligent switch to execute accurate disconnection operation through the GPIO interface. The intelligent switch matrix accurately positions and instantaneously cuts off a charging loop exceeding a limit according to instruction content, ensures that the whole system load is in a safe range, and effectively prevents overload risks.
As shown in fig. 4, the intelligent shopping cart charging safety management method of the invention comprises the following steps: step 1, acquiring an intelligent shopping cart sleeving state image;
Step 2, processing the intelligent shopping cart inserting state image through a visual algorithm, and judging whether the intelligent shopping cart is in an inserting state or not; if the intelligent shopping cart is in the inserting state, the step 3 is carried out, otherwise, the step 1 is returned;
Step 3, judging whether the intelligent shopping cart is in a charging state, if so, entering a step 4, otherwise, returning to the step 2 or the step 1;
Step 4, starting an OCR recognition algorithm to recognize the feature number of the charging stake or the previous intelligent shopping cart;
Step 5, transmitting the identified feature numbers and the charging temperature of each intelligent shopping cart to a background system (cloud server);
Step 6, a background system (cloud server) generates a charging chain according to the charging temperature and the feature number;
Step 7, a background system (cloud server) detects whether a node with the temperature exceeding a threshold value exists in the charging chain or whether the end of the charging chain exceeds the limit of the number of the nodes, if so, the step 8 is started, and otherwise, the step 6 is returned;
step 8, the background system (cloud server) sends a charging disconnection instruction to an intelligent shopping cart corresponding to a node with the temperature exceeding a threshold value in a charging chain or a node with the terminal exceeding the limit of the number of the nodes;
And 9, after receiving a charging disconnection instruction, the corresponding intelligent shopping cart controls the intelligent shopping cart to automatically unlock the sleeve plug through the GPIO interface, and changes a charging circuit into an open circuit.
In the step 2, the visual algorithm adopts ResNet, mobileNet equal depth learning models to divide the shopping cart states into two types: (1) not in a nested state; (2) in a nested state.
Resnet solves the problem of gradient disappearance in deep neural network training by introducing a residual block, so that the network depth reaches hundreds of layers or more, and remarkable performance improvement is achieved on tasks such as image classification, target detection and the like. When the method is applied to intelligent shopping cart charging state identification, resnet can learn deeper shopping cart state characteristic representation, effectively distinguish various detail differences of two states, and can keep high identification accuracy even under complex scenes such as light change and different visual angles. MobileNet is a lightweight deep learning model specially designed for mobile equipment and embedded systems, which greatly reduces model parameters, reduces computation complexity and maintains good recognition performance through techniques such as deep separable convolution. MobileNet is an ideal choice for application scenarios requiring instant response and low power operation, such as intelligent shopping carts. The charging state can be identified rapidly and efficiently, the intelligent shopping cart management system can be ensured to run stably under various hardware configurations, and meanwhile, the battery endurance of the device is prolonged. The two algorithms have the characteristics of being applicable to different computing resource conditions, but can effectively improve the recognition precision and efficiency. In a practical deployment, an appropriate model may be selected based on the specific needs and hardware limitations of the intelligent shopping cart system. If a chip such as a GPU (graphics processing unit) and an NPU (non-point processing unit) special for depth model reasoning is configured in the tablet personal computer, resNet is preferable to obtain higher recognition accuracy; if the computing resources and power consumption in the tablet computer are limited, mobileNet is preferable to achieve efficient identification.
In practice, a large number of images including two states of the shopping cart are collected as training and testing data sets, the training and testing data sets are independent of each other and cannot be intersected, and the training set and the testing set can cover various environment conditions during various charging, such as various possible illumination conditions of the shopping cart in the external environment, brightness and the like of different supermarkets, various shopping cart color combinations and various left-behind shopping tickets possibly included in a shopping cart frame. Empty shopping bags and the like. Then, the data sets are used for training Resnet or MobileNet, and according to the performance design data enhancement technology of the model on the test set, sample reading positives are increased through operations such as rotation, cutting, overturning, brightness and contrast changing, fitting is reduced, and generalization capability of the model under different environments is improved. Furthermore, the model size and the calculation requirement are reduced through the technologies of model quantization, pruning and the like, and efficient operation under a limited resource environment is ensured. The intelligent shopping cart not only can improve the running speed, but also can reduce the power consumption and prolong the running time of the intelligent shopping cart. Through strategies such as fine training sets, test set collection and labeling, targeted data enhancement, model optimization and the like, the model can accurately and efficiently identify which state the intelligent shopping cart is in. In addition, in order to reduce the erroneous judgment of the algorithm, the multi-frame image is utilized for continuous verification in actual application, so that the robustness of judgment can be improved. Finally, integrating the trained model into a control system of the intelligent shopping cart, analyzing the picture captured by the camera in real time, acquiring the charging state of the intelligent shopping cart, guiding the charging process, and improving the automation level and user experience of the system.
In the step 4, the OCR recognition algorithm uses a high-precision visual sensor 5 (camera) on the intelligent shopping cart to ensure that the viewing angle covers the position of the front cart display screen and the position of the charging pile body, the unique number of each cart is displayed on the terminal display screen of the cart, the unique number is marked above the charging pile, and different feature number sequences are adopted. Video stream data of an area in front of the vehicle is collected and stored. The image data of the front vehicle or the charging pile of the vehicle sleeve insertion can be accurately monitored under various illumination environments. Advanced OCR technology is integrated to perform real-time deep learning processing on video streams captured by a camera, and number information of an access charging pile or number information of a front vehicle is accurately identified and extracted. The different number sequences (number composition is characteristic sequence-number sequence) are used for distinguishing different types of devices (vehicles or charging piles), and digital interference in the environment can be filtered. The OCR technology has excellent illumination adaptability, angle robustness and anti-interference capability in complex environments, and ensures that the serial number information of the intelligent shopping cart or the charging pile is rapidly and accurately identified under various working conditions.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof, but rather as providing for the use of additional embodiments and advantages of all such modifications, equivalents, improvements and similar to the present invention are intended to be included within the scope of the present invention as defined by the appended claims.
Claims (6)
1. An intelligent shopping cart charging safety management system is characterized in that: the intelligent shopping cart comprises an intelligent shopping cart, a charging pile and a background system; the intelligent shopping cart is provided with a front electrode (1), a rear electrode (2), a temperature sensor (3), a front camera (4), a visual sensor (5) and an intelligent terminal (6); during charging, a plurality of intelligent shopping carts are sleeved and inserted to form a charging queue, a front electrode (1) of a first intelligent shopping cart of the charging queue is connected into a charging pile, and the front electrode (1) of the intelligent shopping carts except the first intelligent shopping cart in the charging queue is used for being in contact with a rear electrode (2) of a previous intelligent shopping cart to realize serial charging; the temperature sensor (3) is used for collecting the charging temperature of the intelligent shopping cart; the front camera (4) is used for collecting an intelligent shopping cart sleeving state image; the charging pile and the intelligent shopping cart are marked with feature numbers, and the visual sensor (5) is used for extracting the feature number of the charging pile or the intelligent shopping cart in front; the intelligent terminal (6) is used for judging whether the intelligent shopping cart is in the inserting state according to the inserting state image, if the intelligent shopping cart is in the inserting state, the intelligent terminal (6) detects whether the intelligent shopping cart is in the charging state, and if the intelligent shopping cart is in the charging state, the intelligent terminal (6) acquires the charging temperature and the feature number and sends the charging temperature and the feature number to the background system; the background system generates a charging chain according to the charging temperature and the feature number, and detects each node in the charging chain; the background system sends a charging disconnection instruction to an intelligent terminal (6) corresponding to a node with the temperature exceeding a threshold value in the charging chain or a node with the terminal exceeding the limit of the number of the nodes; the intelligent terminal (6) controls the intelligent shopping cart in which the intelligent terminal is positioned to disconnect a charging circuit;
the intelligent terminal (6) is provided with an OCR (optical character recognition) module, and the intelligent terminal (6) recognizes the feature number through the OCR module;
the charging pile feature number position A is positioned at the topmost end of the charging pile; the intelligent shopping cart feature number position B is positioned on a screen of the intelligent terminal (6); the visual sensor shooting area C covers the charging pile feature number position A or the intelligent shopping cart feature number position B; the front camera shooting area D covers the rear end of the whole intelligent shopping cart;
the front camera (4) of the intelligent shopping cart captures the inserting state of the shopping cart in real time, and the image recognition is carried out on the intelligent terminal 6 through the real-time video stream data acquired by the front camera (4) to confirm the inserting state; when the plugging and charging state are detected, OCR recognition is started;
the intelligent terminal (6) adopts ResNet or MobileNet deep learning models to divide shopping cart states into two types: not in the inserted state or in the inserted state.
2. The intelligent shopping cart charge safety management system of claim 1, wherein: the intelligent terminal (6) is provided with a wireless communication module, and the intelligent terminal (6) establishes communication with a background system through the wireless communication module.
3. The intelligent shopping cart charge safety management system of claim 1, wherein: the background system is provided with a counting module, and the counting module is used for calculating the number of intelligent shopping carts connected with the charging piles.
4. The intelligent shopping cart charge safety management system of claim 1, wherein: the intelligent terminal (6) is provided with a GPIO interface, and the intelligent terminal (6) controls the unlocking sleeve plug of the intelligent shopping cart through the GPIO interface to disconnect the charging circuit.
5. The intelligent shopping cart charge safety management system of claim 1, wherein: the background system is a cloud server.
6. The intelligent shopping cart charging safety management method is characterized by comprising the following steps of:
step1, acquiring an intelligent shopping cart sleeving state image;
Step 2, judging whether the intelligent shopping cart is in the inserting state according to the intelligent shopping cart inserting state image; if the intelligent shopping cart is in the inserting state, the step 3 is carried out, otherwise, the step 1 is returned;
Step 3, judging whether the intelligent shopping cart is in a charging state, if so, entering a step 4, otherwise, returning to the step 2 or the step 1;
step 4, identifying the feature number of the charging pile or the intelligent shopping cart in front of the charging pile;
Step 5, transmitting the identified feature numbers and the charging temperatures of the intelligent shopping carts to a background system;
step 6, the background system generates a charging chain according to the charging temperature and the feature number;
step 7, the background system detects whether a node with the temperature exceeding a threshold value exists in the charging chain or whether the end of the charging chain exceeds the limit of the number of the nodes, if so, the step 8 is started, and otherwise, the step 6 is returned;
step 8, the background system sends a charging disconnection instruction to the intelligent shopping cart corresponding to the node with the temperature exceeding the threshold value in the charging chain or the node with the terminal exceeding the limit of the number of the nodes;
Step 9, the corresponding intelligent shopping cart turns off the charging switch after receiving the charging-off instruction;
in the step 2, a visual algorithm is adopted to process the intelligent shopping cart inserting state image to judge whether the intelligent shopping cart is in an inserting state;
the visual algorithm in the step 2 adopts ResNet or MobileNet deep learning model to divide shopping cart states into two types: is not in the inserting state or is in the inserting state;
Firstly, collecting a large number of images containing two states of a shopping cart as training and testing data sets, ensuring that the training and testing data sets are mutually independent and cannot intersect, wherein the training set and the testing set cover various environmental conditions during various charging, then training Resnet or MobileNet by using the data sets, and continuously verifying by using multi-frame images; integrating the trained model into a control system of the intelligent shopping cart, analyzing the picture captured by the camera in real time, and obtaining the charging state of the intelligent shopping cart;
and in the step 4, the OCR recognition algorithm is adopted to recognize the feature number of the charging stake or the previous intelligent shopping cart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410929099.7A CN118457322B (en) | 2024-07-11 | 2024-07-11 | A smart shopping cart charging safety management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410929099.7A CN118457322B (en) | 2024-07-11 | 2024-07-11 | A smart shopping cart charging safety management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118457322A CN118457322A (en) | 2024-08-09 |
| CN118457322B true CN118457322B (en) | 2024-11-12 |
Family
ID=92165351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410929099.7A Active CN118457322B (en) | 2024-07-11 | 2024-07-11 | A smart shopping cart charging safety management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118457322B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1416558A (en) * | 2000-04-20 | 2003-05-07 | 赛斯泰克Pos技术有限公司 | Method and system for detecting and rewarding return of shopping trolleys |
| CN115179803A (en) * | 2022-08-03 | 2022-10-14 | 南京亿猫信息技术有限公司 | A smart shopping cart charging safety management method, system and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105552673A (en) * | 2016-02-05 | 2016-05-04 | 无锡知谷网络科技有限公司 | Connector, safety control device, charging device and mobile device |
| CN110048487B (en) * | 2019-05-16 | 2021-04-13 | 清华大学 | A method and system for controlling charging and discharging of a battery |
| US11208134B2 (en) * | 2020-03-11 | 2021-12-28 | Gatekeeper Systems, Inc. | Monitoring system capable of classifying items added to a shopping cart |
| CN113839447A (en) * | 2021-10-22 | 2021-12-24 | 西安超嗨网络科技有限公司 | Magnetic attraction type fixed charging device and method |
| AU2022471598A1 (en) * | 2022-07-29 | 2025-03-06 | Maplebear Inc. | Stackable charging device for shopping carts with onboard computing systems |
-
2024
- 2024-07-11 CN CN202410929099.7A patent/CN118457322B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1416558A (en) * | 2000-04-20 | 2003-05-07 | 赛斯泰克Pos技术有限公司 | Method and system for detecting and rewarding return of shopping trolleys |
| CN115179803A (en) * | 2022-08-03 | 2022-10-14 | 南京亿猫信息技术有限公司 | A smart shopping cart charging safety management method, system and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118457322A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108109385B (en) | A vehicle identification and dangerous behavior identification system and method for preventing external breakage of power lines | |
| CN105279484A (en) | Method and device for object detection | |
| CN105788286A (en) | Intelligent red light running identifying system and vehicle behavior detecting and capturing method | |
| CN111784444A (en) | Shared bicycle management method and system | |
| CN110035408A (en) | A kind of public safety wisdom detection system and method based on wisdom net connection automobile | |
| CN111445442A (en) | Crowd counting method and device based on neural network, server and storage medium | |
| CN109326125B (en) | Picture quality diagnosis system and method based on embedded system | |
| CN118457322B (en) | A smart shopping cart charging safety management system and method | |
| CN105139665A (en) | Road traffic management system and method | |
| CN111062319B (en) | Driver call detection method based on active infrared image | |
| CN207020820U (en) | Red-running Monitor System | |
| CN114934467B (en) | Parking space barrier control method, parking space barrier system and medium | |
| CN114898420B (en) | Abnormal face file recognition method, device, electronic device and storage medium | |
| CN118918537B (en) | Passenger flow statistics method and device based on umbrella-opening pedestrian and computer equipment | |
| CN102096811A (en) | Intelligent face recognition module based on embedded platform, and recognition method thereof | |
| CN110324589A (en) | A kind of monitoring system and method for tourist attraction | |
| CN108154685A (en) | A kind of portable car plate data acquisition device, server and system | |
| CN118190168B (en) | A method and system for monitoring temperature in key areas of high-speed vehicles | |
| Dizon et al. | Development of an open-space visual smart parking system | |
| CN109034171B (en) | Method and device for detecting unlicensed vehicles in video stream | |
| CN114554179B (en) | Automatic shooting method, system, terminal and storage medium based on target model | |
| CN116030412A (en) | Method and system for abnormal detection of escalator monitoring video | |
| CN116311205A (en) | License plate recognition method, license plate recognition device, electronic equipment and storage medium | |
| CN113496563B (en) | Intelligent gate management method, device and equipment | |
| CN211786038U (en) | Anti-dismantling circuit structure of intelligent sharing terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |