CN110660141A - Road surface condition detection method and device, electronic equipment and readable storage medium - Google Patents
Road surface condition detection method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN110660141A CN110660141A CN201910843984.2A CN201910843984A CN110660141A CN 110660141 A CN110660141 A CN 110660141A CN 201910843984 A CN201910843984 A CN 201910843984A CN 110660141 A CN110660141 A CN 110660141A
- Authority
- CN
- China
- Prior art keywords
- road surface
- surface condition
- information
- sensor
- sample data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application provides a road surface condition detection method, a road surface condition detection device, electronic equipment and a readable storage medium, wherein the method comprises the following steps: obtaining a perception feature tensor generated by a sensor installed on a roadside device; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution; inputting the perceptual feature tensor into a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor; sending the road surface condition information to an information receiving device and/or storing the road surface condition information to an information storage device; the accuracy and the reliability of detecting the road surface condition are improved, and the safe and reliable running of the vehicle is ensured.
Description
Technical Field
The embodiment of the application relates to the technical field of automatic driving, in particular to a road surface condition detection method and device, electronic equipment and a readable storage medium.
Background
The road surface condition of the road influences the control performance of the running vehicle, particularly, the conditions of water accumulation, icing, potholes, damage and the like of the road surface can all have bad influence on the control performance of the running vehicle, so that the running vehicle is in an unstable state, and the potential safety hazard of the running vehicle is caused. Therefore, for an automatically driven or driving-assisted vehicle, it is necessary to provide accurate information of the road surface condition of the road ahead of the vehicle, so that the automatic driving system or driving-assisted system of the vehicle can control the vehicle driving speed in advance according to the road surface condition of the road ahead, adjust the vehicle driving state, and plan the vehicle driving path, so that the vehicle can stably drive under various road surface conditions, avoid the vehicle from being out of control under the bad road surface condition, and ensure the safe and reliable driving of the vehicle.
In addition, the road surface defect condition can be timely and accurately detected, and a road maintenance department can be timely informed to perform timely road maintenance on the road, so that the road surface condition of the road is ensured to be good, and the smoothness of the road is ensured.
In the related art, the detection of the road surface condition is mainly realized by the following modes:
(1) the vehicle-mounted sensors of a traveling vehicle sense and detect road surface conditions with which the tires of the vehicle are in contact. However, this technique is only capable of detecting the road surface condition where the running vehicle and the tire are in contact at every moment, is not capable of sensing the road surface condition around the vehicle and the road in front of the vehicle where the tire of the vehicle cannot be in contact, and is not capable of detecting the road surface condition in front of the running vehicle in advance, and is not suitable for automatic driving and driving assistance.
(2) The on-board sensors of the traveling vehicle sense and detect road surface conditions around and in front of the vehicle. However, since the vehicle-mounted sensor is mounted at a limited position, the road surface area that can be sensed by the vehicle-mounted sensor is limited. In addition, in the running process of the vehicle, the sensed environment changes rapidly, and in order to accurately detect the road surface condition of the front road in the dynamically changing complex environment, a complex algorithm is required, so that the hardware cost and the software cost are greatly increased.
(3) The road pavement is detected by special instrument equipment. This technique can only detect the road surface condition of a specified road at regular time, and therefore cannot detect the road surface condition of a dynamically changing road in real time, and cannot provide the vehicle with information on the change in the road surface condition caused by the change in factors such as climate.
Disclosure of Invention
The embodiment of the application provides a road surface condition detection method and device, electronic equipment and a readable storage medium, so that the accuracy and reliability of road surface condition detection are improved, and vehicles can be guaranteed to run safely and reliably.
A first aspect of an embodiment of the present application provides a road surface condition detection method, including:
obtaining a perception feature tensor generated by a sensor installed on a roadside device; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution;
inputting the perceptual feature tensor into a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor;
and sending the road surface condition information to an information receiving device and/or storing the road surface condition information to an information storage device.
Optionally, after inputting the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor, the method further comprises:
classifying the road surface condition information according to the road surface condition types, and identifying the road surface condition information of different road surface condition types;
transmitting the target road surface condition information to an information receiving apparatus, and/or storing to an information storage apparatus, including:
and sending the marked road surface condition information to the information receiving equipment and/or storing the road surface condition information to the information storage equipment.
Optionally, after inputting the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor, the method further comprises:
converting a sensor coordinate system of the sensor into a unified world coordinate system;
marking the road surface condition information in the corresponding unified world coordinate system so as to display the road surface condition information in a high-precision map;
transmitting the road surface condition information to an information receiving apparatus, and/or storing to an information storage apparatus, including:
and sending the high-precision map to the information receiving equipment and/or storing the high-precision map to the information storage equipment.
Optionally, the method further comprises:
obtaining a sample data set, wherein the sample data set comprises a plurality of sample data records carrying marks, and the carried marks represent road surface condition information of the sample data records;
and training a preset model by taking the plurality of sample data records as input to obtain a road surface condition detection model.
Optionally, the obtaining the sample data set includes:
acquiring a perception feature tensor generated by a sensor installed on roadside equipment on a series of time nodes in a preset time period;
and taking the perceptual feature tensor generated by each time node in the series of time nodes as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the obtaining the sample data set includes:
acquiring a perception feature tensor generated by a series of time nodes in a preset time period by a sensor installed on roadside equipment and corresponding auxiliary information;
and taking the perceptual feature tensor generated by each time node in the series of time nodes and the corresponding auxiliary information as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the training a preset model with the multiple sample data records as input to obtain a road condition detection model includes:
initializing a model parameter value of a preset model;
circularly inputting the sample data records into the preset model so that the preset model sequentially outputs road surface condition information results;
sequentially determining the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record;
adjusting the model parameters of the preset model according to the difference;
and under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more, stopping adjusting the model parameters and outputting the road surface condition detection model.
A second aspect of the embodiments of the present application provides a road surface condition detection device, including:
the acquisition module is used for acquiring a perception feature tensor generated by a sensor installed on the road side equipment; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution;
an input module, configured to input the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor;
and the sending module is used for sending the road surface condition information to information receiving equipment and/or storing the road surface condition information to information storage equipment.
Optionally, the apparatus further comprises:
the classification module is used for classifying the road surface condition information according to the road surface condition types and identifying the road surface condition information of different road surface condition types;
the sending module comprises:
and the first sending submodule is used for sending the marked road surface condition information to the information receiving equipment and/or storing the marked road surface condition information to the information storage equipment.
Optionally, the apparatus further comprises:
the conversion module is used for converting a sensor coordinate system of the sensor into a unified world coordinate system;
the marking module is used for marking the road surface condition information in the corresponding unified world coordinate system so as to display the road surface condition information in a high-precision map;
the sending module comprises:
and the second sending submodule is used for sending the high-precision map to the information receiving equipment and/or storing the high-precision map to the information storage equipment.
Optionally, the apparatus further comprises:
the system comprises a sample acquisition module, a data acquisition module and a data analysis module, wherein the sample acquisition module is used for acquiring a sample data set, the sample data set comprises a plurality of sample data records carrying marks, and the carried marks represent the road surface condition information of the sample data records;
and the training module is used for training a preset model by taking the plurality of sample data records as input to obtain a road surface condition detection model.
Optionally, the sample obtaining module comprises:
the first acquisition submodule is used for acquiring a perceptual feature tensor generated by a sensor installed on the roadside device on a series of time nodes in a preset time period;
and the first interception submodule is used for taking the perceptual feature tensor generated by each time node in the series of time nodes as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the sample obtaining module comprises:
the second acquisition submodule is used for acquiring a perception feature tensor generated by a series of time nodes in a preset time period by a sensor installed on the road side equipment and corresponding auxiliary information;
and the second intercepting submodule is used for taking the perceptual feature tensor generated by each time node in the series of time nodes and the corresponding auxiliary information as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the training module comprises:
the initial submodule is used for initializing the model parameter value of a preset model;
the input submodule is used for circularly inputting the plurality of sample data records into the preset model so that the preset model sequentially outputs a road surface condition information result;
a determining submodule for sequentially determining a difference between the road surface condition information result and the road surface condition information marked in the corresponding sample data record;
the adjusting submodule is used for adjusting the model parameters of the preset model according to the difference value;
and the output submodule is used for stopping adjusting the model parameters and outputting the road surface condition detection model under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more.
A third aspect of embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, performs the steps in the method according to the first aspect of the present application.
A fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect of the present application when executed.
By adopting the method for detecting the road surface condition, the road surface condition of the same section of monitored road surface can be continuously sensed and detected for a long time by installing the sensor on the road side equipment, the road surface condition information of each road surface of the monitored road surface is provided in real time, accurate road surface condition information is provided for automatic driving or auxiliary driving, and the safety driving of vehicles is guaranteed.
Different from vehicle-mounted sensors in the related art, the sensor mounted on the roadside device has a wider visual field range, can provide road pavement condition information in a wider range in front of the vehicle for the vehicle, enables the vehicle to have sufficient time to adjust the driving state according to the road pavement condition information in front, plans a driving path, greatly improves the capability of the vehicle for processing sudden change of the road condition in front, and improves the driving safety of the vehicle.
Meanwhile, the road area range sensed by the sensor arranged on the road side equipment cannot be changed, and the road condition of the same section of monitored road can be continuously analyzed and tracked for a long time, so that the analysis of the road condition is more accurate and reliable, more accurate and dynamically-changed road condition information can be provided for the vehicle, and the vehicle can be ensured to safely and reliably run in an automatic driving or auxiliary driving state.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart of a road surface condition detection method according to an embodiment of the present application;
fig. 2 is a flowchart of a road surface condition detection method according to an embodiment of the present application;
fig. 3 is a flowchart of a road surface condition detection method according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a training process of a road surface condition detection model according to an embodiment of the present application;
fig. 5 is a flowchart illustrating step S41 in the training process of the road surface condition detection model according to an embodiment of the present application;
fig. 6 is a flowchart illustrating step S41 in the training process of the road surface condition detection model according to an embodiment of the present application;
fig. 7 is a flowchart illustrating step S42 in the training process of the road surface condition detection model according to an embodiment of the present application;
FIG. 8 is a schematic diagram illustrating an updating process of a road surface condition detection model according to an embodiment of the present application;
fig. 9 is a schematic view of a road surface condition detection device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a road surface condition detection method according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S11: obtaining a perception feature tensor generated by a sensor installed on a roadside device; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution.
In this embodiment, the sensor mounted on the roadside apparatus includes, but is not limited to, at least one of: the system comprises a camera sensor, a laser radar sensor and an infrared sensor; the information sensed by the camera sensor comprises video image information, the information sensed by the laser radar sensor comprises point cloud information, and the information sensed by the infrared sensor comprises infrared image information. For the camera sensor, if the collected information is visible light information, the perception characteristic information is intensity information of three RGB color channels; for the laser radar sensor, the perception characteristic information is depth distance information and reflection intensity information of laser; for the infrared sensor, the perception characteristic information is infrared ray intensity information.
In this embodiment, the installation position of the sensor satisfies that the sensing range of the sensor can cover the monitored road surface, which means: a road surface area where a road surface condition needs to be detected; the installation position of the sensor is not limited in any way in the present application.
In this embodiment, the sensor senses the monitored road surface according to a preset spatial resolution, and divides the monitored road surface into a plurality of spatial positions, so that each spatial position on the monitored road surface has a corresponding coordinate position in a sensor coordinate system of the sensor, and the corresponding coordinate position corresponds to the corresponding coordinate position.
In order to comprehensively reflect the road surface condition information, in one possible embodiment of the present application, a plurality of sensors may be installed on the roadside device, and the sensing feature tensor generated for the plurality of sensors on the roadside device is: and fusing the perception characteristic tensors generated by each sensor to generate a super perception characteristic tensor. The sensing feature tensors of the sensors are fused and then input into the road condition detection model, so that the times of data processing of the road condition detection model are reduced, and the flow is simplified.
Or, for a plurality of sensors, the perceptual feature tensors generated by the plurality of sensors are obtained, the perceptual feature tensors are input to the road surface condition detection model to obtain road surface condition information, and finally, the obtained road surface condition information is fused to obtain final road surface condition information.
Step S12: inputting the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor.
In this embodiment, the road surface condition detection model may be loaded in the computing device offline or online. The road surface condition information includes: road surface condition types (e.g., dry road surface, wet and slippery road surface, damaged road surface, icy road surface, cracked road surface, pothole road surface, etc.) and condition attribute values (e.g., water accumulation degree, leveling degree, moisture degree, water accumulation depth, etc.).
In this embodiment, in order to obtain more accurate road surface condition information, the perceptual feature tensor and the corresponding auxiliary information may be further input to a road surface condition detection model; the assistance information includes, but is not limited to, at least one of: time information, geographic information, road surface type information and weather information; the time information refers to time period information sensed by a sensor, for example: morning, midday, or evening; the geographic information refers to the geographic position information of the road surface sensed by the sensor, such as: desert areas, saline-alkali areas, southern areas, humid areas, and the like; the road surface type information refers to the type of the road surface sensed by the sensor, for example: concrete pavement, asphalt pavement, and the like; weather information refers to weather information corresponding to a time node sensed by a sensor, such as: temperature, humidity, wind speed, etc.
Step S13: and sending the road surface condition information to an information receiving device and/or storing the road surface condition information to an information storage device.
In the present embodiment, the information receiving device may be a device installed in an autonomous vehicle or a driving-assist vehicle so as to provide accurate road condition information to the autonomous vehicle or the driving-assist vehicle; or may be a device installed at the information processing center.
In this embodiment, by sending the road surface condition information to the information storage device, a data reserve is provided for subsequent training or updating of the road surface condition detection model.
In this embodiment, the road surface condition information may be transmitted wirelessly (e.g., 5G, 4G, and WIFI) or by wire (e.g., optical fiber), and the transmission method is not limited in any way.
Through the technical scheme, the sensor is arranged on the road side equipment, so that the road condition of the same section of monitored road surface can be continuously sensed and detected for a long time, the road condition information of each road surface of the monitored road surface is provided in real time, accurate road condition information is provided for automatic driving or auxiliary driving, and the safety driving of vehicles is guaranteed.
Different from vehicle-mounted sensors in the related art, the sensor mounted on the roadside device has a wider visual field range, can provide road pavement condition information in a wider range in front of the vehicle for the vehicle, enables the vehicle to have sufficient time to adjust the driving state according to the road pavement condition information in front, plans a driving path, greatly improves the capacity of the vehicle for processing sudden change of the road pavement condition in front, and improves the driving safety of the vehicle.
Meanwhile, the road area range sensed by the sensor arranged on the road side equipment cannot be changed, and the road condition of the same section of monitored road can be continuously analyzed and tracked for a long time, so that the analysis of the road condition is more accurate and reliable, more accurate and dynamically-changed road condition information can be provided for the vehicle, and the vehicle can be ensured to safely and reliably run in an automatic driving or auxiliary driving state.
Referring to fig. 2, fig. 2 is a flowchart of a road surface condition detection method according to an embodiment of the present application. As shown in fig. 2, the method includes the following steps in addition to step S11 and step S12:
step S21: and classifying the road surface condition information according to the road surface condition types, and identifying the road surface condition information of different road surface condition types.
In the present embodiment, in the sensor coordinate system of the sensor, the road surface condition information of all the coordinate positions is classified according to the road surface condition type; the classification method includes, but is not limited to: representing the road surface areas with the same road surface condition type by adopting a polygonal frame or a mask mode; and the road surface area is the road surface area corresponding to the coordinate position of the same road surface condition type in all the coordinate positions.
Classifying the road surface condition information according to the road surface condition types to obtain a plurality of road surface areas with the same road surface condition types; the classification result comprises two parts: the first part is a road surface area range, and the second part is a road surface condition type corresponding to a road surface in the road surface area range.
Thus, identifying the road surface condition information for different road surface condition types may include: identifying the area range of the road surface by adopting an area identifier, and identifying the type of the road surface by adopting a road surface condition classification identifier; wherein the area identifier and the road surface condition classification identifier include, but are not limited to, at least one of: numerical identifiers, letter identifiers and character identifiers; generally, the area identifier and the road surface condition classification identifier are not the same.
Step S13 includes:
step S131: and sending the marked road surface condition information to the information receiving equipment and/or storing the road surface condition information to the information storage equipment.
In this embodiment, the marked road surface condition information is sent to an information receiving device and/or stored in the information storage device, so that the information receiving device and the information storage device can distinguish and call different road surface condition information conveniently.
Referring to fig. 3, fig. 3 is a flowchart of a road surface condition detection method according to an embodiment of the present application. As shown in fig. 3, the method includes the following steps in addition to step S11 and step S12:
step S31: converting a sensor coordinate system of the sensor to a unified world coordinate system.
Step S32: and marking the road surface condition information in the corresponding unified world coordinate system so as to display the road surface condition information in a high-precision map.
Step S13 includes:
step S132: and sending the high-precision map to the information receiving equipment and/or storing the high-precision map to the information storage equipment.
In this embodiment, the conversion method between the sensor coordinate system and the unified world coordinate system is a conventional technical means adopted by those skilled in the art, and is the prior art, and the description of the coordinate conversion is not repeated here.
In this embodiment, the road surface condition information at all the coordinate positions in the sensor coordinate system is marked at the corresponding positions in the unified world coordinate system to display the road surface condition information on the high-precision map, so that the information receiving device can visually display the road surface condition information of the monitored road surface.
In order to implement the method proposed by the applicant more intelligently and to enable the application range of the method to be wider, the applicant firstly constructs a preset model and trains the preset model based on a sample data set to obtain a road condition detection model, and the applicant utilizes the road condition detection model to execute part or all of the steps in the method.
Referring to fig. 4, fig. 4 is a schematic diagram of a training process of a road surface condition detection model according to an embodiment of the present application. As shown in fig. 4, the process includes the steps of:
step S41: and obtaining a sample data set, wherein the sample data set comprises a plurality of sample data records carrying marks, and the carried marks represent the road surface condition information of the sample data records.
In this embodiment, the marking process of the sample data record can be completed manually, that is, the road surface condition information of the sample data record is judged manually, and then the sample data record is marked, so that the sample data record carries a mark.
In this embodiment, the road surface condition information represented by the carried marks includes, but is not limited to, at least one of: the road condition type, the mark corresponding to the road condition type and the condition attribute value; illustratively, taking a sensing feature tensor generated by a certain time node of the camera sensor as an example of sample data record, manually framing a ponding road surface seen in a video picture by using a polygonal frame, identifying the polygonal frame, and marking the ponding degree of the ponding road surface.
In addition, the marking process of the sample data records can also adopt automatic pre-marking, and then the sample data records are checked and corrected manually. Wherein, the mode that automatic pre-labeling adopted is: training a marking model by using a sample data set which is manually marked previously, marking the obtained sample data set by using the trained marking model, outputting a pre-marking result, and finally, manually checking and correcting the pre-marking result to finish marking.
Step S42: and training a preset model by taking the plurality of sample data records as input to obtain a road surface condition detection model.
In this embodiment, the preset model may be a deep neural network model, or may adopt other models.
Referring to fig. 5, fig. 5 is a flowchart of step S41 in the training process schematic diagram of the road surface condition detection model in an embodiment of the present application. As shown in fig. 5, the method comprises the following steps:
step S51: the method comprises the steps of acquiring a perception feature tensor generated by a sensor installed on a road side device on a series of time nodes in a preset time period.
In this embodiment, the preset time period may be selected according to different lighting conditions on the same day, for example: morning, noon, evening, etc.; the selection can also be made according to different weather conditions, for example: sunny, foggy, rainy, etc.; it is also possible to choose from different seasonal conditions, for example: such as spring, summer, autumn and winter. The series of time nodes are: the sensor has a preset sensing frequency. Illustratively, the camera sensor generates the perceptual feature tensor at a frequency of 30 frames per second, and the lidar sensor generates the perceptual feature tensor at a frequency of 10 frames per second.
Step S52: and taking the perceptual feature tensor generated by each time node in the series of time nodes as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
In this embodiment, the time periods and time nodes corresponding to the intercepted multiple sample data records should be diversified as much as possible, so that the sample data sets can cover the changes of various environments.
To further improve the accuracy of the detection of the road surface condition, the applicant of the present application has found that, in addition to the sensor-generated perceptual feature tensor being indicative of the road surface condition, some auxiliary information may also be used to characterize the road surface condition, including but not limited to at least one of: time information, geographic information, road surface type information and weather information; the time information refers to time period information sensed by a sensor, for example: morning, midday, or evening; the geographic information refers to the geographic position information of the road surface sensed by the sensor, such as: desert areas, saline-alkali areas, southern areas, humid areas, and the like; the road surface type information refers to the type of the road surface sensed by the sensor, for example: concrete pavement, asphalt pavement, and the like; weather information refers to weather information corresponding to a time node sensed by a sensor, such as: temperature, humidity, wind speed, etc.
Taking the auxiliary information as meteorological information as an example, the temperature information and the humidity information in the meteorological information can be used for representing whether the road surface is frozen or not. Therefore, if the sensing feature tensor generated by the sensor and the corresponding auxiliary information are used for representing the road surface condition, the accuracy of detecting the road surface condition can be improved when the road surface condition is detected.
On the basis, the applicant introduces different sample data sets and trains the preset model to obtain the road surface condition detection model.
Referring to fig. 6, fig. 6 is a flowchart of step S41 in the training process schematic diagram of the road surface condition detection model in the embodiment of the present application. As shown in fig. 6, the method comprises the following steps:
step S61: acquiring a perception feature tensor generated by a series of time nodes in a preset time period by a sensor installed on roadside equipment and corresponding auxiliary information;
step S62: and taking the perceptual feature tensor generated by each time node in the series of time nodes and the corresponding auxiliary information as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
In this embodiment, the auxiliary information includes, but is not limited to, at least one of: time information, geographic information, road surface type information and weather information; the time information refers to time period information sensed by a sensor, for example: morning, midday, or evening; the geographic information refers to the geographic position information of the road surface sensed by the sensor, such as: desert areas, saline-alkali areas, southern areas, humid areas, and the like; the road surface type information refers to the type of the road surface sensed by the sensor, for example: concrete pavement, asphalt pavement, and the like; weather information refers to weather information corresponding to a time node sensed by a sensor, such as: temperature, humidity, wind speed, etc.
The time information can be obtained through network time service; meteorological data may be collected by mounting sensors on roadside equipment, for example: the roadside apparatus may be equipped with a temperature sensor, a humidity sensor, an air velocity sensor, and the like, and may be acquired by a meteorological system.
Referring to fig. 7, fig. 7 is a flowchart of step S42 in the training process schematic diagram of the road surface condition detection model in the embodiment of the present application. As shown in fig. 7, the method comprises the following steps:
step S71: initializing the model parameter values of the preset model.
In this embodiment, the model parameter value may be initialized to a selected constant value, or may be initialized to a random number uniformly distributed in a selected value region, or a random number normally distributed in a selected parameter, or a random number distributed in another kind, or an initial value obtained by further processing the above values, where the further processing includes but is not limited to: regularized, multiplied by a numerical value.
In addition, the initial values of the model parameters of the preset model may be model parameter values obtained by pre-training other training data sets.
Step S72: and circularly inputting the sample data records into the preset model so that the preset model sequentially outputs road surface condition information results.
In this embodiment, the input cycle may be a plurality of sample data records of the same batch; or a plurality of sample data records of different batches, that is, a plurality of sample data records input each time are different. Generally, a plurality of sample data records of different batches are input into the preset model.
Step S73: and sequentially determining the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record.
Step S74: and adjusting the model parameters of the preset model according to the difference.
Step S75: and under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more, stopping adjusting the model parameters and outputting the road surface condition detection model.
In this embodiment, first, a difference between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is sequentially determined, and the difference can represent the accuracy of the preset model in predicting the road surface condition in the training round;
then, adjusting the model parameters of the preset model according to the difference value so as to reduce the difference between the road surface condition information and the road surface condition information marked in the corresponding sample data record, updating the preset model, and putting the updated preset model into the next round of training;
and finally, under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more, stopping adjusting the model parameters and outputting the road surface condition detection model.
In addition, the condition for stopping the adjustment of the model parameters may be: and the reduction amount of the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is smaller than a preset threshold value, or the adjustment times of the model parameters of the preset model reach a preset maximum threshold value.
Referring to fig. 8, fig. 8 is a schematic diagram of an updating process of the road surface condition detection model in an embodiment of the present application. As shown in fig. 8, a new sample data set is added, and the current model parameters are further trained and adjusted to obtain new model parameters, which are applied to the road surface condition detection process as new model parameters, thereby forming a model updating process.
During the detection process of the road surface condition by the road side device, the road side device stores the perception data of the road surface perception at the specified time and the detection result of the road surface condition at the time. After the data and the results are manually checked and manually marked, a new sample data set can be obtained. The model parameters are further trained according to the new sample data set to obtain new model parameters. And then applying the new model parameters to the detection process of the road surface condition of the road side equipment to finish the updating of the model. This model update process may be continuously cycled as needed.
Based on the same inventive concept, an embodiment of the present application provides a road surface condition detection device. Referring to fig. 9, fig. 9 is a schematic view of a road surface condition detection device according to an embodiment of the present application. As shown in fig. 9, the apparatus includes:
an obtaining module 901, configured to obtain a perceptual feature tensor generated by a sensor installed on a roadside device; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution;
an input module 902, configured to input the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor;
and a sending module 903, configured to send the road surface condition information to an information receiving device, and/or store the road surface condition information in an information storage device.
Optionally, the apparatus further comprises:
the classification module is used for classifying the road surface condition information according to the road surface condition types and identifying the road surface condition information of different road surface condition types;
the sending module comprises:
and the first sending submodule is used for sending the marked road surface condition information to the information receiving equipment and/or storing the marked road surface condition information to the information storage equipment.
Optionally, the apparatus further comprises:
the conversion module is used for converting a sensor coordinate system of the sensor into a unified world coordinate system;
the marking module is used for marking the road surface condition information in the corresponding unified world coordinate system so as to display the road surface condition information in a high-precision map;
the sending module comprises:
and the second sending submodule is used for sending the high-precision map to the information receiving equipment and/or storing the high-precision map to the information storage equipment.
Optionally, the apparatus further comprises:
the system comprises a sample acquisition module, a data acquisition module and a data analysis module, wherein the sample acquisition module is used for acquiring a sample data set, the sample data set comprises a plurality of sample data records carrying marks, and the carried marks represent the road surface condition information of the sample data records;
and the training module is used for training a preset model by taking the plurality of sample data records as input to obtain a road surface condition detection model.
Optionally, the sample obtaining module comprises:
the first acquisition submodule is used for acquiring a perceptual feature tensor generated by a sensor installed on the roadside device on a series of time nodes in a preset time period;
and the first interception submodule is used for taking the perceptual feature tensor generated by each time node in the series of time nodes as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the sample obtaining module comprises:
the second acquisition submodule is used for acquiring a perception feature tensor generated by a series of time nodes in a preset time period by a sensor installed on the road side equipment and corresponding auxiliary information;
and the second intercepting submodule is used for taking the perceptual feature tensor generated by each time node in the series of time nodes and the corresponding auxiliary information as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
Optionally, the training module comprises:
the initial submodule is used for initializing the model parameter value of a preset model;
the input submodule is used for circularly inputting the plurality of sample data records into the preset model so that the preset model sequentially outputs a road surface condition information result;
a determining submodule for sequentially determining a difference between the road surface condition information result and the road surface condition information marked in the corresponding sample data record;
the adjusting submodule is used for adjusting the model parameters of the preset model according to the difference value;
and the output submodule is used for stopping adjusting the model parameters and outputting the road surface condition detection model under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more.
Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method according to any of the above-mentioned embodiments of the present application.
Based on the same inventive concept, another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the electronic device implements the steps of the method according to any of the above embodiments of the present application.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method, the device, the storage medium and the electronic device for detecting the road surface condition provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A road surface condition detection method, characterized by comprising:
obtaining a perception feature tensor generated by a sensor installed on a roadside device; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution;
inputting the perceptual feature tensor into a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor;
and sending the road surface condition information to an information receiving device and/or storing the road surface condition information to an information storage device.
2. The method of claim 1, wherein after inputting the perceptual feature tensor to a road condition detection model to obtain road condition information for the all coordinate locations in a sensor coordinate system of the sensor, the method further comprises:
classifying the road surface condition information according to the road surface condition types, and identifying the road surface condition information of different road surface condition types;
transmitting the target road surface condition information to an information receiving apparatus, and/or storing to an information storage apparatus, including:
and sending the marked road surface condition information to the information receiving equipment and/or storing the road surface condition information to the information storage equipment.
3. The method of claim 1, wherein after inputting the perceptual feature tensor to a road condition detection model to obtain road condition information for the all coordinate locations in a sensor coordinate system of the sensor, the method further comprises:
converting a sensor coordinate system of the sensor into a unified world coordinate system;
marking the road surface condition information in the corresponding unified world coordinate system so as to display the road surface condition information in a high-precision map;
transmitting the road surface condition information to an information receiving apparatus, and/or storing to an information storage apparatus, including:
and sending the high-precision map to the information receiving equipment and/or storing the high-precision map to the information storage equipment.
4. The method of claim 1, further comprising:
obtaining a sample data set, wherein the sample data set comprises a plurality of sample data records carrying marks, and the carried marks represent road surface condition information of the sample data records;
and training a preset model by taking the plurality of sample data records as input to obtain a road surface condition detection model.
5. The method of claim 4, wherein said obtaining a sample data set comprises:
acquiring a perception feature tensor generated by a sensor installed on roadside equipment on a series of time nodes in a preset time period;
and taking the perceptual feature tensor generated by each time node in the series of time nodes as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
6. The method of claim 4, wherein said obtaining a sample data set comprises:
acquiring a perception feature tensor generated by a series of time nodes in a preset time period by a sensor installed on roadside equipment and corresponding auxiliary information;
and taking the perceptual feature tensor generated by each time node in the series of time nodes and the corresponding auxiliary information as a sample data record, and intercepting a plurality of sample data records to form the sample data set.
7. The method of claim 4, wherein training a predetermined model with the plurality of sample data records as input to obtain a road condition detection model comprises:
initializing a model parameter value of a preset model;
circularly inputting the sample data records into the preset model so that the preset model sequentially outputs road surface condition information results;
sequentially determining the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record;
adjusting the model parameters of the preset model according to the difference;
and under the condition that the difference value between the road surface condition information result and the road surface condition information marked in the corresponding sample data record is not obviously reduced any more, stopping adjusting the model parameters and outputting the road surface condition detection model.
8. A road surface condition detecting device, characterized by comprising:
the acquisition module is used for acquiring a perception feature tensor generated by a sensor installed on the road side equipment; the sensing feature tensor is sensing feature information generated by the sensor at all coordinate positions corresponding to all spatial positions of the monitored road surface in a sensor coordinate system of the sensor according to preset spatial resolution;
an input module, configured to input the perceptual feature tensor to a road condition detection model to obtain road condition information of all coordinate positions in a sensor coordinate system of the sensor;
and the sending module is used for sending the road surface condition information to information receiving equipment and/or storing the road surface condition information to information storage equipment.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executed implements the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843984.2A CN110660141B (en) | 2019-09-06 | 2019-09-06 | Road surface condition detection method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843984.2A CN110660141B (en) | 2019-09-06 | 2019-09-06 | Road surface condition detection method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110660141A true CN110660141A (en) | 2020-01-07 |
| CN110660141B CN110660141B (en) | 2021-04-20 |
Family
ID=69036798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910843984.2A Active CN110660141B (en) | 2019-09-06 | 2019-09-06 | Road surface condition detection method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110660141B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583630A (en) * | 2020-04-10 | 2020-08-25 | 河北德冠隆电子科技有限公司 | Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction |
| WO2021168660A1 (en) * | 2020-02-25 | 2021-09-02 | 华为技术有限公司 | Method and apparatus for identifying special road conditions, electronic device, and storage medium |
| CN116558578A (en) * | 2023-07-12 | 2023-08-08 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564431A (en) * | 2011-11-14 | 2012-07-11 | 南京理工大学 | Multi-sensor-fusion-based unstructured environment understanding method |
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| DE102015206605A1 (en) * | 2015-04-14 | 2016-10-20 | Continental Teves Ag & Co. Ohg | Calibration and monitoring of environmental sensors with the aid of highly accurate maps |
| US20180052445A1 (en) * | 2016-08-18 | 2018-02-22 | Wisconsin Alumni Research Foundation | Homogenization of material properties in additively manufactured structures |
| CN108010360A (en) * | 2017-12-27 | 2018-05-08 | 中电海康集团有限公司 | A kind of automatic Pilot context aware systems based on bus or train route collaboration |
| CN108345831A (en) * | 2017-12-28 | 2018-07-31 | 新智数字科技有限公司 | The method, apparatus and electronic equipment of Road image segmentation based on point cloud data |
| CN109801282A (en) * | 2019-01-24 | 2019-05-24 | 湖北大学 | Pavement behavior detection method, processing method, apparatus and system |
| CN109886152A (en) * | 2019-01-30 | 2019-06-14 | 天津大学 | A kind of unmanned routing resource based on multisensor cooperation |
| CN109903560A (en) * | 2019-03-13 | 2019-06-18 | 中电共建科技(北京)有限公司 | The on-line monitoring method and system of a kind of icy road and deicing or snow melting |
-
2019
- 2019-09-06 CN CN201910843984.2A patent/CN110660141B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564431A (en) * | 2011-11-14 | 2012-07-11 | 南京理工大学 | Multi-sensor-fusion-based unstructured environment understanding method |
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| DE102015206605A1 (en) * | 2015-04-14 | 2016-10-20 | Continental Teves Ag & Co. Ohg | Calibration and monitoring of environmental sensors with the aid of highly accurate maps |
| US20180052445A1 (en) * | 2016-08-18 | 2018-02-22 | Wisconsin Alumni Research Foundation | Homogenization of material properties in additively manufactured structures |
| CN108010360A (en) * | 2017-12-27 | 2018-05-08 | 中电海康集团有限公司 | A kind of automatic Pilot context aware systems based on bus or train route collaboration |
| CN108345831A (en) * | 2017-12-28 | 2018-07-31 | 新智数字科技有限公司 | The method, apparatus and electronic equipment of Road image segmentation based on point cloud data |
| CN109801282A (en) * | 2019-01-24 | 2019-05-24 | 湖北大学 | Pavement behavior detection method, processing method, apparatus and system |
| CN109886152A (en) * | 2019-01-30 | 2019-06-14 | 天津大学 | A kind of unmanned routing resource based on multisensor cooperation |
| CN109903560A (en) * | 2019-03-13 | 2019-06-18 | 中电共建科技(北京)有限公司 | The on-line monitoring method and system of a kind of icy road and deicing or snow melting |
Non-Patent Citations (1)
| Title |
|---|
| 马建: "《交通运输工程学报》", 15 October 2017 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021168660A1 (en) * | 2020-02-25 | 2021-09-02 | 华为技术有限公司 | Method and apparatus for identifying special road conditions, electronic device, and storage medium |
| CN111583630A (en) * | 2020-04-10 | 2020-08-25 | 河北德冠隆电子科技有限公司 | Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction |
| CN111583630B (en) * | 2020-04-10 | 2022-01-07 | 河北德冠隆电子科技有限公司 | Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction |
| CN116558578A (en) * | 2023-07-12 | 2023-08-08 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
| CN116558578B (en) * | 2023-07-12 | 2023-10-17 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110660141B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660141B (en) | Road surface condition detection method and device, electronic equipment and readable storage medium | |
| CN108773373B (en) | Method and device for operating an autonomous vehicle | |
| US10967869B2 (en) | Road surface condition estimation apparatus and road surface condition estimation method | |
| US10987977B2 (en) | Systems and methods for measuring tire wear using embedded image sensors | |
| US20180088228A1 (en) | Obstacle detection method and apparatus for vehicle-mounted radar system | |
| CN111652060B (en) | Laser radar-based height limiting early warning method and device, electronic equipment and storage medium | |
| CN110795819A (en) | Method and device for generating automatic driving simulation scene and storage medium | |
| CN111179300A (en) | Method, apparatus, system, device and storage medium for obstacle detection | |
| US10684622B2 (en) | Vehicle dynamics monitor for autonomous vehicle | |
| US20170236011A1 (en) | Method and arrangement for assessing the roadway surface being driven on by a vehicle | |
| CN115187949A (en) | Method, device and medium for detecting road surface state of tunnel entrance | |
| CN109671077A (en) | A kind of Bitumen Pavement Anti-Skid Performance detection method and system | |
| CN111094095A (en) | Automatically receiving a travel signal | |
| US11748664B1 (en) | Systems for creating training data for determining vehicle following distance | |
| CN112654892A (en) | Method for creating a map of an environment of a vehicle | |
| CN113342701A (en) | Method and device for interaction between unmanned simulation system and tested unmanned software | |
| CN110550041B (en) | Road adhesion coefficient estimation method based on cloud data sharing | |
| CN116985803B (en) | Self-adaptive speed control system and method for electric scooter | |
| Duthon et al. | Benchmark for the robustness of image features in rainy conditions | |
| JP7320755B2 (en) | Vehicle simulation system, vehicle simulation method and computer program | |
| CN113642708A (en) | Training method, recognition method and device for vehicle environment grade recognition model | |
| Kortmann et al. | Creating value from in-vehicle data: Detecting road surfaces and road hazards | |
| US12125222B1 (en) | Systems for determining and reporting vehicle following distance | |
| US20230126833A1 (en) | System and method for simultaneous online lidar intensity calibration and road marking change detection | |
| KR20240079469A (en) | Estimation method for friction coefficient of road and anayzing System supporting the same |
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 | ||
| CB02 | Change of applicant information |
Address after: 353, block a, No.79, Jinyi Road, Xiaoshan Economic and Technological Development Zone, Xiaoshan District, Hangzhou City, Zhejiang Province Applicant after: Newpoint Intelligent Technology Group Co.,Ltd. Address before: 353, block a, No.79, Jinyi Road, Xiaoshan Economic and Technological Development Zone, Xiaoshan District, Hangzhou City, Zhejiang Province Applicant before: Newpoint Enterprise Management Group Co.,Ltd. Address after: 353, block a, No.79, Jinyi Road, Xiaoshan Economic and Technological Development Zone, Xiaoshan District, Hangzhou City, Zhejiang Province Applicant after: Newpoint Enterprise Management Group Co.,Ltd. Address before: Room B2-501, 198 Kaidi Road, Xiaoshan Economic and Technological Development Zone, Hangzhou City, Zhejiang Province Applicant before: Hangzhou Boxin Zhilian Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |