CN112861573A

CN112861573A - Obstacle identification method and device, storage medium and intelligent lamp pole

Info

Publication number: CN112861573A
Application number: CN201911178449.6A
Authority: CN
Inventors: 汤祖荣
Original assignee: Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Current assignee: Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Priority date: 2019-11-27
Filing date: 2019-11-27
Publication date: 2021-05-28

Abstract

The embodiment of the application discloses obstacle identification method, device, storage medium and wisdom lamp pole, the method includes: acquiring a road condition video acquired by a camera on the intelligent lamp pole aiming at a monitoring area; inputting the road condition video into a trained obstacle recognition model; and outputting obstacle prompt information when the obstacle exists in the road condition video. By adopting the embodiment of the application, because the intelligent lamp pole has the automatic obstacle identification function, when the intelligent lamp pole monitors the road surface area and identifies the obstacle, prompt information can be generated in time and prompt is given, so that related departments can find the obstacle on the road surface in time and clear the obstacle, accidents are effectively prevented, and the accident probability is reduced.

Description

Obstacle identification method and device, storage medium and intelligent lamp pole

Technical Field

The application relates to the technical field of computers, in particular to a barrier identification method, a barrier identification device, a storage medium and an intelligent lamp pole.

Background

Along with the development of modern society, it is more and more important to ensure road conditions safety, and monitoring through the camera is an effective safeguard measure. When people walk in a street, the monitoring camera mounted on the street lamp is visible everywhere.

At present, during monitoring by using a camera installed on a street lamp, the camera collects road condition videos of a monitoring area and stores the videos. And when an accident occurs due to the existence of the obstacle in the monitored road section, when the related department receives the alarm call and needs to process the accident, the specific position and the related condition of the obstacle are judged by calling the road condition video for playback, and then the accident is processed according to the specific position and the related condition of the obstacle. In the process, even if the monitored road section has the obstacle, the obstacle can only be cleaned after the accident happens, so that the accident probability is increased.

Disclosure of Invention

The embodiment of the application provides a method and a device for identifying obstacles, a storage medium and an intelligent lamp pole, which can reduce the time for processing the obstacles and effectively prevent accidents. The technical scheme is as follows:

in a first aspect, an embodiment of the present application provides an obstacle identification method, where the method includes:

acquiring a road condition video acquired by a camera on the intelligent lamp pole aiming at a monitoring area;

inputting the road condition video into a trained obstacle recognition model;

and outputting obstacle prompt information when the obstacle exists in the road condition video.

In a second aspect, an embodiment of the present application provides an image processing apparatus, including:

the video acquisition module is used for acquiring road condition videos acquired by a camera on the intelligent lamp pole aiming at the monitoring area;

the video input module is used for inputting the road condition video into the trained obstacle recognition model;

and the information output module is used for outputting the prompt information of the obstacles when the obstacles exist in the road condition video.

In a third aspect, embodiments of the present application provide a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the above-mentioned method steps.

In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.

The beneficial effects brought by the technical scheme provided by some embodiments of the application at least comprise:

in this application embodiment, at first utilize the road conditions video that the camera on the barrier recognition device acquireed the monitoring area and gathered to, then will the road conditions video input carries out identification process to the barrier recognition model that the training was accomplished in, after identification process when confirming when there is the barrier in the road conditions video, output barrier prompt information. Therefore, by adopting the embodiment of the application, the intelligent lamp pole has the function of automatically identifying the obstacle, so that when the intelligent lamp pole monitors the road surface area and identifies the obstacle, prompt information can be generated in time and prompt is given, so that related departments can find the obstacle on the road surface in time and clear the obstacle, accidents are effectively prevented, and the accident probability is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a scene schematic diagram of an implementation scenario provided in an embodiment of the present application;

fig. 2 is a schematic diagram illustrating an effect exhibited by an intelligent detection platform according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of an obstacle identification method according to an embodiment of the present application;

fig. 4 is a schematic flow chart of identifying an obstacle according to an embodiment of the present application;

fig. 5 is an interaction diagram of a smart light pole and a plurality of clients provided in an embodiment of the present application;

fig. 6 is a schematic flowchart of another obstacle identification method provided in the embodiment of the present application;

fig. 7 is a coordinate diagram of coordinates of a pixel point of an obstacle according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an obstacle identification device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an information output module according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of another obstacle identification device provided in the embodiment of the present application;

FIG. 11 is a schematic structural diagram of a model generation module provided in an embodiment of the present application;

fig. 12 is a schematic structural diagram of an obstacle marking unit according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. 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 invention.

When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims.

In the description of the present application, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art. Further, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

So far, in monitoring by using a camera installed on a street lamp, the camera collects and stores road condition videos in a monitoring area. And when an accident occurs due to the existence of the obstacle in the monitored road section, when the related department receives the alarm call and needs to process the accident, the specific position and the related condition of the obstacle are judged by calling the road condition video for playback, and then the accident is processed according to the specific position and the related condition of the obstacle. In the process, even if the monitored road section has the obstacle, the obstacle can only be cleaned after the accident happens, so that the accident probability is increased. To solve the problems involved in the related art described above. In the technical scheme that this application provided, because the wisdom lamp pole possesses barrier automatic identification function, so when the wisdom lamp pole monitored the road surface region and discerned the barrier, can in time generate tip information and carry out the suggestion to can make timely discovery of relevant department on the road surface barrier and clear up, effectively prevent the emergence of accident, reduce the probability that the accident takes place.

Please refer to fig. 1, which is a schematic view of an implementation scenario shown in an embodiment of the present application, wherein the implementation scenario includes a smart light pole 110, a camera 120, and a user terminal 130. The user terminal 130 is an electronic device with a network communication function, and the electronic device includes, but is not limited to, a smart phone, a tablet computer, a wearable device, a smart home device, a laptop computer, a desktop computer, a smart camera, and the like. User terminal 130 includes one or more processors or memories, which may include one or more processing cores. The processor connects various parts within the entire obstacle identifying device using various interfaces and lines, and performs various functions of the obstacle identifying device and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor may integrate one or more of a Central Processing Unit (CPU), a modem, and the like.

The smart light pole 110 stores therein an obstacle recognition model. Optionally, the obstacle recognition model is a model obtained by training a Neural Network model (e.g., a Convolutional Neural Network (CNN)) with training sample data. The user terminal 130 is connected to the smart light pole 110 through a wireless or wired network, and an application program with an obstacle recognition function is installed in the smart light pole 110.

In one possible implementation, the user first turns on the smart light pole 110 and the user terminal 130, and connects the smart light pole 110 and the user terminal 130 by wire or wirelessly, when the intelligent lamp post 110 is in the open state, the intelligent lamp post 110 monitors the road by using the camera 120 thereon, continuously stores the monitored area image to form a road condition video, after the intelligent lamp post 110 detects the acquired road condition video, the intelligent lamp post 110 uploads the road condition video to the processor through a wired or wireless network, when the processor detects the uploaded road condition video, the processor calls the barrier recognition model for processing through an internal program, the obstacle recognition model is a mathematical model obtained by training a sample image with an obstacle image, and has the function of accurately recognizing the obstacle and the related position information of the obstacle.

After the processor acquires the obstacle identification model, the model is used for identifying the road condition video, and after identification, when the road condition video contains the obstacle, the intelligent lamp pole 110 sends the position and the related information of the obstacle to the user terminal 130 through a wired or wireless network for alarm display. As shown in fig. 2, fig. 2 is an interface displayed when the user terminal 130 receives the alarm information, and the interface includes specific position information of the obstacle and a link of obstacle viewing details, when the user clicks the viewing details, the user terminal 130 jumps to a video detection screen, and the user can specifically view the current state of the obstacle through the video, and then can make a processing scheme according to the current state of the obstacle. And after receiving the alarm information, the user checks and confirms the position and the relevant condition of the barrier, and then quickly processes the barrier. When no obstacle is found after the identification, the smart lamp post 110 continues to acquire road condition images for monitoring by using the camera 120.

The obstacle recognition method provided by the embodiment of the present application will be described in detail below with reference to fig. 3 to 7. The method may be implemented in dependence on a computer program, operable on a von neumann based obstacle recognition device. The computer program may be integrated into the application or may run as a separate tool-like application. Wherein, barrier recognition device in this application embodiment can be wisdom lamp pole.

Please refer to fig. 3, which is a flowchart illustrating an obstacle identification method according to an embodiment of the present disclosure. As shown in fig. 3, the method of the embodiment of the present application may include the steps of:

s101, acquiring a road condition video acquired by a camera on the intelligent lamp pole aiming at a monitoring area;

the intelligent lamp post is a new generation of road lighting lamp formed by combining a computer technology, a communication technology and an artificial intelligence technology, and also bears other public services such as intelligent lighting, green emission reduction, network intercommunication, environmental information release, public safety monitoring and the like on the basis of realizing lighting, and is an indispensable product for realizing intelligent cities. The camera is a video input device and can be used for acquiring images. The region is the area that a place occupies, can understand here to be a certain place, specifically means the place that the camera on the wisdom lamp pole monitored on the road surface. Video generally refers to various storage formats of moving images.

Generally, a road condition video is a dynamic image composed of thousands of road surface image frames, the dynamic image is acquired by a camera on a smart lamp post, and the acquired dynamic image may include pedestrians on the road, vehicles on the road, obstacles and the like.

In a feasible implementation, when the wisdom lamp pole is opened the back and is in operating condition, the regional image that the camera will monitor is gathered. When the wisdom lamp pole detected the image of gathering, the image frame that will gather was preserved. Along with the increase of time, when the wisdom lamp pole had kept thousands of road conditions image frames that the camera was gathered in a period of time, generated the road conditions video that this period of time generated this moment.

S102, inputting the road condition video into a trained obstacle recognition model;

the relevant explanation of the road condition video may specifically refer to S101, which is not described herein again, and the obstacle recognition model is a mathematical model for performing obstacle recognition according to the input road condition video, where the mathematical model is created based on at least one of a Convolutional Neural Network (CNN) model, a Deep Neural Network (DNN) model, a Recurrent Neural Network (RNN) model, an embedding (embedding) model, a Long-Short Term Memory model (Long-Short Term Memory, LSTM), and a Gradient Boosting Decision Tree (GBDT) model, and then the mathematical model is trained by using a road condition image with an obstacle to generate a mathematical model with an obstacle recognition function, and the mathematical model has a capability of detecting abnormal situations such as a foreign object, an accident, and a fire.

In the embodiment of the application, after the intelligent lamp pole obtains the road condition video based on the step S101, the obstacle recognition model stored in the system is called through an internal program, the intelligent lamp pole processes and analyzes the road condition video by using the obstacle recognition model after training, and then judges the related condition of the road surface according to the result of the obstacle recognition model analysis and processing to give a conclusion, and the conclusion can be transmitted to the client through a wireless network or a wired network. When the client displays abnormal conditions, the user can process the abnormal conditions according to the related conditions displayed by the user terminal.

S103, when the situation that the obstacle exists in the road condition video is determined, obstacle prompt information is output.

The obstacle can be a large package falling from the road surface, a fire disaster, a vehicle accident and the like. The prompt information is warning information sent when the obstacle recognition model recognizes that there is an obstacle on the road surface, for example, as shown in fig. 2, the warning information may be "the point marked with 1 is suspected of dropping a large package", the warning information may also be "the point marked with 1 is suspected of having a vehicle collision accident, and the details are checked by clicking", or may be other warning information, which is not limited herein.

In the embodiment of the application, based on step S102, the intelligent lamp pole inputs the road condition video to the obstacle recognition model for processing and analysis, and then determines the early warning information according to the analysis result, and if an obstacle is detected after the processing and analysis, at this time, the related information of the obstacle can be sent to the related department for alarm processing, and the related department can make a scheme according to the obstacle information and then perform processing.

For example, when the intelligent lamp pole inputs road condition video to the obstacle recognition model and detects that a large package falls off on the road surface, the intelligent lamp pole sends secondary information to the client through a wired or wireless network and carries out alarm information, and the alarm signal can be an alarm ring tone sent by a loudspeaker of the client system.

In a possible implementation manner, for example as shown in fig. 4, fig. 4 is a specific flowchart of the scheme, and first, at the beginning, the smart light pole is turned on, wherein the smart light pole is connected with one or more user terminals (user terminal 1, user terminal 2, user terminal n) of the relevant department, for example as shown in fig. 5. Then utilize the camera on the wisdom lamp pole to monitor the road surface, in the control to the road surface, when discovering the abnormal conditions, further specifically confirm that the foreign matter has the foreign matter on the road surface or the vehicle has taken place the accident, still has taken place the conflagration, confirms that to send the foreign matter information to relevant departments and report to the police after accomplishing, and relevant departments confirm alarm information and foreign matter condition, handle after confirming. If find when not having abnormal conditions, wisdom lamp pole can continue to monitor. Use the camera on every wisdom lamp pole to carry out intelligent monitoring, the road conditions in current monitoring area is fed back in real time, if there is the foreign matter in current monitoring area (like the animal on the car falls the thing or the mistake breaks through on the road), takes place the car accident or vehicle spontaneous combustion takes place conflagration etc. can judge and the suggestion of reporting to the police through AI intelligent recognition technology, and the traffic control department looks over and confirms after receiving the warning to in time the efficient is handled foreign matter, car accident or accident.

In another possible implementation manner, for example, when the obstacle is in a hidden place, the intelligent lamp post can acquire the deviation between the driving tracks of the vehicle and the passerby and the road through the camera to judge whether the vehicle detours. Specifically, firstly, coordinate points of a driving track of a vehicle and a pedestrian are required to be acquired, then, coordinate points of a road are acquired, whether the driving track of the vehicle and the pedestrian deviates relative to the road is judged by judging the coordinate points of the driving track of the vehicle and the pedestrian and the coordinate points of the road through the intelligent lamp post, when the driving track is analyzed and judged to deviate, the deviated place is considered to possibly have an obstacle, and then, the position coordinate points of the deviated place and relevant information are sent to a client of a relevant department to be displayed and give an alarm.

Please refer to fig. 6, which is a flowchart illustrating an obstacle identification method according to an embodiment of the present disclosure. The present embodiment is exemplified by applying the obstacle recognition method to the intelligent lamp post. The obstacle recognition method may include the steps of:

s201, collecting a sample image set, wherein each sample image in the sample image set comprises an obstacle;

the samples are data information sets which are formed by characters, words and sentences and have the functions of expressing the product performance, the functions, the structural principles and the size parameters of the samples, and the data information sets of the samples are stored in a special data warehouse to form a database, and the data information sets are sample image sets in the embodiment. The electronic upgrading method is an electronic upgrading version of a traditional paper sample, can be transmitted through a network, is displayed in front of a user in a novel and visual mode, has a visual and friendly human-computer interaction interface, is rich in expressive force and diversified in expression methods, enables the query speed of the user to be faster, and is higher in efficiency of searching for sample data.

Generally, a collected sample is also called sample acquisition, and today, the internet industry is rapidly developing, the sample collection is widely applied to the internet field, the accurate selection of the sample to be collected has a profound influence on the product, if the collected sample is not accurate enough, a large deviation of a test result can be caused, and inestimable loss is caused to the product. Therefore, it is necessary to accurately collect the sample information.

In the embodiment of the application, a large number of images containing obstacles need to be acquired, the images may be acquired based on a gallery, may also be found through the internet, and may also be stored in a cloud server, and the acquisition of the images may be in many ways, which is not limited herein. The obstacle in the image may be a foreign object such as a large package, an accident of a vehicle, or an accident such as a fire. When a sufficient number of images containing obstacles are acquired, a sample image set is formed.

S202, creating an obstacle identification model, and acquiring a plurality of pixel coordinates of the position of an obstacle on each sample image in the sample image set;

generally, in the stage of training the obstacle recognition model, it is first necessary to create an obstacle recognition model based on at least one of CNN, RNN and LSTM models, wherein the core function of the obstacle recognition model is to be able to recognize foreign objects in the video image, such as large packages and vehicle accidents on the road surface, and fire, etc. When the whole image is represented in the coordinate axis, each image is formed by arranging pixel coordinates in the horizontal direction and the vertical direction, and each pixel corresponds to a value corresponding to the coordinate point of the image, and then the coordinates are used for marking out the positions of foreign matters, vehicle accidents and fires. For example, as shown in fig. 7, the coordinates of a certain pixel point of an obstacle in the image are (23, 76).

In the embodiment of the application, firstly, an obstacle identification model needs to be created, a large number of sample images containing obstacles can be collected after the obstacle identification model is created, then the large number of sample images are represented in a coordinate axis, and after the representation is finished, the coordinates of a plurality of pixel points of the obstacles in the sample images can be collected by using a computer program.

S203, determining a closed area formed by the pixel coordinates as an obstacle area of the sample image, and marking;

the closed area can be specifically understood as the area formed by the outer edge of the obstacle, the area depends on the size of the obstacle, the coordinates of a plurality of pixel points are the coordinates of the pixel points of the obstacle, the coordinates of the pixel points of the obstacle form the closed area, and the coordinate points of the closed area are marked and then acquired, so that the pixel coordinate points of the obstacle can be obtained.

In the embodiment of the application, an image with an obstacle is represented in a coordinate axis, wherein each pixel point in the image corresponds to a coordinate point at the position, the coordinate points of the pixel points in a closed area formed by the outer edge of the obstacle are marked and then extracted, and at the moment, the coordinate value size corresponding to the coordinate point of the obstacle can be obtained.

S204, inputting the marked sample images into the obstacle recognition model for training, and generating a trained obstacle recognition model;

in a possible implementation manner, in training an obstacle recognition model, a user firstly creates an obstacle recognition model based on an artificial intelligence correlation technique, then collects a large number of images containing obstacles for coordinated representation, then extracts obstacle coordinate points in the images by using a computer correlation technique, trains the extracted obstacle coordinate points through the created obstacle recognition model, and generates the obstacle recognition model after the training is finished.

S205, acquiring a road condition video acquired by a camera on the intelligent lamp pole aiming at a monitoring area;

specifically, refer to step S101, which is not described herein again.

S206, inputting the road condition video into a trained obstacle recognition model;

specifically, refer to step S102, which is not described herein again.

S207, when the situation that the obstacle exists in the road condition video is determined, acquiring position information of the obstacle in the monitoring area;

the position information is specific position information of the obstacle, and the specific position information of the obstacle may be obtained based on positioning by software having a positioning system, or may be obtained by other methods, which is not limited here.

In this application embodiment, based on step S206 with road conditions video input to barrier recognition model and carry out processing analysis, when finding that there is the barrier on the road surface after processing analysis, the wisdom lamp pole acquires the positional information of barrier through inside positioning system.

And S208, sending early warning information containing the position information to a traffic management department.

In a possible implementation manner, after judging that the obstacle exists in the road, the intelligent lamp pole acquires information of the obstacle and outputs the information to the user terminal through a wired or wireless network, wherein the information of the obstacle includes: length and width information of the obstacle, and position information of the obstacle. And the navigation system is informed to broadcast the barrier information for the pedestrians and vehicles in the road, so that the pedestrians and the drivers can have prejudgment time, and the occurrence of related accidents is prevented. And after receiving the information, the user terminal triggers an alarm system to alarm and displays the specific conditions of the obstacles. When the user terminal receives the intelligence confirmation instruction from the user, the alarm is stopped, and then relevant departments can carry out processing in advance according to the specific position and relevant conditions of the obstacle.

Furthermore, wisdom lamp pole intelligent recognition technology is a street lamp of high efficiency, intelligence. This street lamp can let the street lamp have more wisdom through intelligent recognition technology on the basis of providing the illumination. Wisdom lamp pole can intelligent recognition foreign matter on the road surface (like the animal on the car falls or the mistake breaks into on the road), the vehicle of taking place the accident, the conflagration scheduling problem on the road. This street lamp also can prevent traffic accident on the road in time simultaneously, if fallen the thing on the highway and do not have timely clearance again, certainly there is very big potential safety hazard, uses behind the wisdom lamp pole, and the traffic control department can in time discover the foreign matter on the road to make effectual processing. This scheme can also in time efficient handle various accidents on the road, under the prior art, if take place the accident on the road, the traffic control department can only passively wait for on the road pedestrian to call the warning telephone, then carries out processing on next step, if use this wisdom lamp pole, the traffic control department just can be in time the initiative obtain accident alarm information on the road to in time efficient makes the rescue or handles.

The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.

Please refer to fig. 8, which illustrates a schematic structural diagram of an obstacle identification apparatus according to an exemplary embodiment of the present application. The obstacle recognition device may be implemented as all or a part of the terminal by software, hardware, or a combination of both. The apparatus 1 includes a video acquisition module 10, a video input module 20, and an information output module 30.

The video acquisition module 10 is used for acquiring road condition videos acquired by a camera on the intelligent lamp pole aiming at a monitoring area;

the video input module 20 is configured to input the road condition video into the trained obstacle recognition model;

and the information output module 30 is configured to output obstacle prompt information when it is determined that an obstacle exists in the road condition video.

Optionally, as shown in fig. 9, the information output module 30 includes:

an information obtaining unit 301, configured to obtain location information of an obstacle in the monitoring area when it is determined that the obstacle exists in the road condition video;

an information sending unit 302, configured to send early warning information including the location information to a traffic management department.

Optionally, as shown in fig. 10, the apparatus 1 further includes:

an image acquisition module 50, configured to acquire a sample image set, where each sample image in the sample image set includes an obstacle;

and the model generating module 40 is configured to create an obstacle recognition model, input each sample image in the sample image set into the obstacle recognition model, and train the sample image to generate a trained obstacle recognition model.

Optionally, as shown in fig. 11, the model generating module 40 includes:

an obstacle marking unit 401 for marking an obstacle region of each sample image in the sample image set;

a model training unit 402, configured to input the labeled sample images into the obstacle recognition model for training.

Alternatively, as shown in fig. 12, the obstacle marking unit 402 includes:

a coordinate obtaining subunit 4021, configured to obtain a plurality of pixel coordinates of a position where an obstacle is located on each sample image in the sample image set;

an area marking subunit 4022, configured to determine a closed area formed by the multiple pixel coordinates as an obstacle area of the sample image, and mark the closed area.

It should be noted that, when the obstacle identification apparatus provided in the foregoing embodiment executes the obstacle identification method, only the division of the above functional modules is taken as an example, and in practical applications, the above functions may be distributed to different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to complete all or part of the above described functions. In addition, the obstacle identification device provided by the above embodiment and the obstacle identification method embodiment belong to the same concept, and the detailed implementation process thereof is referred to the method embodiment, which is not described herein again.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

The present application also provides a computer readable medium, on which program instructions are stored, which program instructions, when executed by a processor, implement the obstacle identification method provided by the above-mentioned respective method embodiments.

The present application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of obstacle identification as described in the various method embodiments above.

Please refer to fig. 13, which provides a schematic structural diagram of a smart light pole according to an embodiment of the present application. As shown in fig. 13, the smart light pole 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.

Wherein a communication bus 1002 is used to enable connective communication between these components.

The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Processor 1001 may include one or more processing cores, among other things. The processor 1001 interfaces various components throughout the electronic device 1000 using various interfaces and lines to perform various functions of the electronic device 1000 and to process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005 and invoking data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1001, but may be implemented by a single chip.

The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 13, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an obstacle recognition application program.

In the smart light pole 1000 shown in fig. 13, the user interface 1003 is mainly used to provide an input interface for the user to obtain data input by the user; and the processor 1001 may be configured to invoke the obstacle identification application stored in the memory 1005 and specifically perform the following operations:

inputting the road condition video into a trained obstacle recognition model;

In one embodiment, when the processor 1001 executes the operation of outputting the obstacle prompt information when it is determined that the obstacle exists in the road condition video, specifically executing the following operation:

when the situation that the obstacle exists in the road condition video is determined, acquiring position information of the obstacle in the monitoring area;

and sending early warning information containing the position information to a traffic management department.

In one embodiment, before performing the acquiring of the road condition video collected by the camera on the smart light pole for the monitored area, the processor 1001 further performs the following operations:

acquiring a sample image set, wherein each sample image in the sample image set comprises an obstacle;

and creating an obstacle recognition model, inputting each sample image in the sample image set into the obstacle recognition model for training, and generating the trained obstacle recognition model.

In one embodiment, when the processor 1001 inputs each sample image in the sample image set into the obstacle recognition model for training, the following operations are specifically performed:

marking an obstacle area of each sample image in the sample image set;

and inputting the marked sample images into the obstacle recognition model for training.

In one embodiment, the processor 1001, when performing the marking of the obstacle area of each sample image in the sample image set, specifically performs the following operations:

acquiring a plurality of pixel coordinates of the position of the obstacle on each sample image in the sample image set;

and determining a closed area formed by the pixel coordinates as an obstacle area of the sample image, and marking the closed area.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present application and is not to be construed as limiting the scope of the present application, so that the present application is not limited thereto, and all equivalent variations and modifications can be made to the present application.

Claims

1. An obstacle identification method, characterized in that the method comprises:

inputting the road condition video into a trained obstacle recognition model;

2. The method according to claim 1, wherein the outputting an obstacle prompt message when it is determined that an obstacle exists in the video of the road condition comprises:

3. The method as claimed in claim 1, wherein before the obtaining the road condition video collected by the camera on the smart light pole for the monitored area, the method comprises:

4. The method of claim 3, wherein the inputting each sample image of the set of sample images into the obstacle recognition model for training comprises:

marking an obstacle area of each sample image in the sample image set;

5. The method of claim 4, wherein the marking the obstacle region of each sample image in the set of sample images comprises:

6. An obstacle recognition apparatus, characterized in that the apparatus comprises:

7. The apparatus of claim 6, wherein the information output module comprises:

the information acquisition unit is used for acquiring the position information of the obstacle in the monitoring area when the obstacle is determined to exist in the road condition video;

and the information sending unit is used for sending early warning information containing the position information to a traffic management department.

8. The apparatus of claim 6, further comprising:

the system comprises an image acquisition module, a data acquisition module and a data processing module, wherein the image acquisition module is used for acquiring a sample image set, and each sample image in the sample image set comprises an obstacle;

and the model generation module is used for creating an obstacle recognition model, inputting each sample image in the sample image set into the obstacle recognition model for training, and generating the trained obstacle recognition model.

9. The apparatus of claim 8, wherein the model generation module comprises:

an obstacle marking unit for marking an obstacle region of each sample image in the sample image set;

and the model training unit is used for inputting the marked sample images into the obstacle recognition model for training.

10. The apparatus according to claim 9, wherein the obstacle marking unit includes:

the coordinate obtaining subunit is used for obtaining a plurality of pixel coordinates of the positions of the obstacles on each sample image in the sample image set;

and the area marking subunit is used for determining a closed area formed by the pixel coordinates as an obstacle area of the sample image and marking the closed area.

11. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to perform the method steps according to any of claims 1 to 5.

12. The utility model provides a wisdom lamp pole which characterized in that includes: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 5.