CN110209853B - Image searching method, device and equipment for vehicle - Google Patents
Image searching method, device and equipment for vehicle Download PDFInfo
- Publication number
- CN110209853B CN110209853B CN201910520157.XA CN201910520157A CN110209853B CN 110209853 B CN110209853 B CN 110209853B CN 201910520157 A CN201910520157 A CN 201910520157A CN 110209853 B CN110209853 B CN 110209853B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- partition
- screening
- node
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention provides a picture searching method, a picture searching device and picture searching equipment for a vehicle, and relates to the technical field of image recognition, wherein the method comprises the following steps: firstly, determining a file name to be searched according to a vehicle brand and a vehicle model in a vehicle image searching request, then screening a partial list which accords with an algorithm type and a time condition in the vehicle image searching request from an image characteristic index library, determining a searching path, finally loading file data corresponding to the searching path and the file name from the image characteristic index library, screening data which accords with the vehicle characteristic, and returning the data to upper-layer equipment.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method, a device and equipment for searching a picture of a vehicle.
Background
The picture searching technology based on content is based on the principle that the characteristics of color, shape, texture and the like are extracted from pictures, a characteristic index base is established, then characteristic values analyzed according to pictures inquired by a user are compared with the base, and the pictures with high similarity or information related to the pictures are searched.
The vehicle retrieval based on the license plate and vehicle type information is wide in application, images of the same vehicle, attributes of the vehicle, driving paths and even analysis data are conveniently and accurately positioned for a user in the aspect of image video detection, the technology relates to technologies such as image recognition and big data analysis, the key technology is characteristic extraction, similarity comparison and the like, in the prior art, a large amount of invalid image data needs to be loaded in the characteristic extraction and similarity comparison processes, and the image recognition efficiency and accuracy rate cannot meet the requirements of the user easily.
Disclosure of Invention
The invention aims to provide a picture searching method, a picture searching device and picture searching equipment for a vehicle, so that the picture searching efficiency and the picture searching accuracy of the vehicle are improved.
The invention provides a picture searching method of a vehicle, which is applied to a server, wherein a picture characteristic index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the method comprises the following steps: receiving a vehicle image searching request sent by upper-layer equipment; the vehicle map searching request comprises a time condition, a vehicle brand, a vehicle model, an algorithm type and vehicle characteristics; determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request; screening out a partial list which meets the algorithm type and time condition in the vehicle image searching request from the image feature index library; determining a search path according to the algorithm type, the time condition and the partial list in the vehicle map search request; loading file data corresponding to the search path and the file name from the picture feature index library; and screening data which accord with the vehicle characteristics from the loaded file data, and returning a screening result to the upper-layer equipment.
Further, the directory structure of the picture feature index library further comprises partition numbers; the picture feature index library is divided into a plurality of partitions, and each partition is provided with a corresponding partition number; and file data distributed according to a preset distribution rule is stored in each partition.
Further, a main node, a first node and a second node are arranged in the server; the first node is allocated with a partition corresponding to a first designated partition number; the second node is allocated with a partition corresponding to a second specified partition number; the master node is allocated with a partition corresponding to a third appointed partition number; the method further comprises the following steps: executing the step of determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in the method through the first node, so as to load the file data corresponding to the searching path and the file name from the partition corresponding to the first specified partition number; executing, by the second node, the step of determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map search request in the above method, so as to load the search path and the file data corresponding to the file name from the partition corresponding to the second specified partition number; and executing the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request by the master node, so as to load the file data corresponding to the searching path and the file name from the partition corresponding to the third specified partition number.
Further, the screening the data meeting the vehicle characteristics from the loaded file data and returning a screening result to the upper-layer device includes: screening data which accord with the vehicle characteristics from the file data loaded by the first node, and returning a first screening result to the main node; screening data which accord with the vehicle characteristics from the file data loaded by the second node, and returning a second screening result to the main node; screening data which accord with the vehicle characteristics from the file data loaded by the main node to obtain a third screening result; and screening a preset amount of data which accord with the vehicle characteristics from the first screening result, the second screening result and the third screening result through the main node, and returning the screening results to the upper-layer equipment.
The invention provides a picture searching device of a vehicle, which is applied to a server, wherein a picture characteristic index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the device comprises: the receiving module is used for receiving a vehicle map searching request sent by upper-layer equipment; the vehicle map searching request comprises a time condition, a vehicle brand, a vehicle model, an algorithm type and vehicle characteristics; the first acquisition module is used for determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request; the first screening module is used for screening a partial list which meets the algorithm type and the time condition in the vehicle map searching request from the image feature index library; the second acquisition module is used for determining a search path according to the algorithm type, the time condition and the partial list in the vehicle map search request; the loading module is used for loading the file data corresponding to the search path and the file name from the picture feature index library; and the second screening module is used for screening the data which accord with the vehicle characteristics from the loaded file data and returning the screening result to the upper-layer equipment.
Further, the directory structure of the picture feature index library further comprises partition numbers; the picture feature index library is divided into a plurality of partitions, and each partition is provided with a corresponding partition number; and file data distributed according to a preset distribution rule is stored in each partition.
Further, a main node, a first node and a second node are arranged in the server; the first node is allocated with a partition corresponding to a first designated partition number; the second node is allocated with a partition corresponding to a second specified partition number; the master node is allocated with a partition corresponding to a third appointed partition number; the device further comprises: a first executing module, configured to execute, by the first node, the step of determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in the above method, so as to load file data corresponding to the search path and the file name from a partition corresponding to the first specified partition number; a second executing module, configured to execute, by the second node, the step of determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in the above method, so as to load the file data corresponding to the search path and the file name from the partition corresponding to the second specified partition number; and the third execution module is used for executing the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in the method through the main node so as to load the file data corresponding to the searching path and the file name from the partition corresponding to the third specified partition number.
Further, the second screening module is further configured to: screening data which accord with the vehicle characteristics from the file data loaded by the first node, and returning a first screening result to the main node; screening data which accord with the vehicle characteristics from the file data loaded by the second node, and returning a second screening result to the main node; screening data which accord with the vehicle characteristics from the file data loaded by the main node to obtain a third screening result; and screening a preset amount of data which accord with the vehicle characteristics from the first screening result, the second screening result and the third screening result through the main node, and returning the screening results to the upper-layer equipment.
The invention provides a picture searching device of a vehicle, which comprises a memory and a processor, wherein a computer program capable of running on the processor is stored in the memory, and the processor realizes the picture searching method of the vehicle when executing the computer program.
The invention provides a machine-readable storage medium, which stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to realize the picture searching method of the vehicle.
The invention provides a picture searching method, a device and equipment for a vehicle, which are characterized in that firstly, a file name to be searched is determined according to a vehicle brand and a vehicle model in a vehicle picture searching request, then, a partial list which accords with an algorithm type and a time condition in the vehicle picture searching request is screened out from a picture characteristic index library, a searching path is determined, finally, file data corresponding to the searching path and the file name are loaded from the picture characteristic index library, data which accords with the vehicle characteristic are screened out and returned to upper-layer equipment, and the mode can directly acquire the file data by combining the file name and the searching path and complete the data screening, has less data comparison amount, and improves the efficiency and the accuracy of the picture searching of the vehicle.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a picture searching method for a vehicle according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for searching a vehicle image according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a vehicle image search device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a picture search device for a vehicle according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. 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.
By using the technology of searching pictures, a user can acquire information of articles in the pictures at any time and any place by means of photographing, recording and the like, or search similar commodities and the like. The image searching technology also plays an important auxiliary role in the criminal investigation and security protection field, can be distributed and controlled in real time, and reduces the investigation range, thereby reducing the manpower for searching suspicious targets, improving the working efficiency and accuracy of public security departments, even predicting the occurrence in a short time, early warning in advance, and reducing the occurrence of criminal events.
The existing image searching technology needs to load a large amount of image data into a memory for similarity comparison, occupies memory space, and has difficulty in meeting user requirements on image searching efficiency and accuracy.
Based on this, the embodiments of the present invention provide a method, an apparatus, and a device for searching a picture of a vehicle, where the technology may be applied to a server, and the technology may be implemented by using related software or hardware, which is described below by way of an embodiment.
The embodiment of the invention provides a flow chart of a picture searching method of a vehicle, and as shown in fig. 1, the method is applied to a server, and a picture characteristic index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the method comprises the following steps:
step S101, receiving a vehicle image searching request sent by upper-layer equipment; the vehicle map search request includes a time condition, a vehicle brand, a vehicle model, an algorithm type, and a vehicle characteristic.
Specifically, after a user transmits a picture to be retrieved and initiates a vehicle image searching request, the webpage end calls the analysis server to analyze the vehicle brand, the vehicle model, the algorithm type and the vehicle characteristics of the picture, and the user can set corresponding time conditions according to requirements to search images.
And S102, determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request.
In order to improve the efficiency and accuracy of searching the images, the file names to be searched are combined by the vehicle brands and the vehicle models analyzed by the analysis server.
And step S103, screening a partial list which meets the algorithm type and time condition in the vehicle map searching request from the image feature index library.
Further, the server screens out a partial list meeting the required algorithm type and time condition by setting the required algorithm type and time condition in the search parameter by the user.
And step S104, determining a search path according to the algorithm type, the time condition and the partial list in the vehicle map search request.
The server determines a search path according to the algorithm type and the time condition set by the user in the search parameter and the partial list satisfying the condition.
Step S105, loading file data corresponding to the search path and the file name from the picture feature index library.
The server determines an absolute path through the search path and the file name to be searched, loads file data corresponding to the absolute path into the memory, screens out a large part of data through determining the absolute path, only needs to load a small amount of data into the memory, has a small data comparison amount, saves a large amount of memory, and saves hardware cost by loading a small amount of data.
And step S106, screening data which accord with the vehicle characteristics from the loaded file data, and returning a screening result to upper-layer equipment.
Traversing the data loaded into the memory, screening the data meeting the conditions through a vehicle comparison function, determining similarity comparison results, sequencing according to the results, generally limiting a certain quantity of screening results, selecting a preset quantity of file data with higher similarity from the screened data meeting the conditions, and returning the file data to upper-layer equipment, wherein the vehicle comparison function generally uses a cosine similarity algorithm, and in addition, only the data of the corresponding date can be screened, and the data at a specific moment cannot be screened, so that the data at the specific moment needs to be screened for the data at the first day and the last two days.
The embodiment of the invention provides a picture searching method, a device and equipment for a vehicle, which comprises the steps of firstly determining a file name to be searched according to a vehicle brand and a vehicle model in a vehicle picture searching request, then screening a partial list which meets algorithm types and time conditions in the vehicle picture searching request from a picture characteristic index library, determining a searching path, finally loading file data corresponding to the searching path and the file name from the picture characteristic index library, screening data which meets vehicle characteristics, and returning the data to upper-layer equipment.
The embodiment of the invention also provides a flow chart of another picture searching method of the vehicle, which is applied to a server, wherein the server stores a picture characteristic index library in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the directory structure of the picture characteristic index library also comprises partition numbers, a plurality of partitions are divided in the picture characteristic index library, and each partition is provided with a corresponding partition number; each partition stores file data distributed according to a preset distribution rule, and it should be noted that the number of partitions is initialized according to the performance measured in service, and may also be set according to the user requirement.
The data in the picture feature index library is continuously updated, and the specific updating and storing process is as follows: through IPC equipment such as a gunlock, a camera and the like, pictures and videos of passing vehicles are captured and pushed to an analysis server in real time to analyze structured data such as vehicle brands, vehicle models, vehicle colors and the like, vehicle features are extracted at the same time, the analyzed data are sent to a message middleware such as kafka, consumption groups of the kafka are divided into 2 groups, two groups consume the same data at the same time, one group of consumption data are written into the kafka, the group serves as a data forwarding unit, the data written into the group do not need to be processed, and other devices needing the data can be accessed into the consumption group and read. The other group of consumption data is written into a memory of a server firstly, the data in the memory is updated in real time, the data in the memory of the server is written into a hard disk once every 5 minutes, vehicle characteristics and part of necessary data (structured data identification ID, time condition, equipment ID, algorithm type, vehicle brand and vehicle model) are stored according to a directory structure of algorithm type/kafkaPartion number/time condition (year, month and day)/vehicle brand/vehicle model, and the structured data are stored into a database, wherein the structured data identification ID is a unique identification automatically generated when the server analyzes the structured data of pictures or videos, is in one-to-one correspondence with the structured data, and is used for inquiring the corresponding structured data in the database according to the structured data identification ID in the subsequent picture searching process; the device ID is a device ID for inputting a picture or a video, and in the present embodiment, the structured data corresponds to the file data.
A main node, a first node and a second node are arranged in the server; the first node is allocated with a partition corresponding to the first appointed partition number; the second node is distributed with a partition corresponding to a second specified partition number; it should be noted that the number of nodes set in the server may be set according to user requirements, if a user needs to adopt a distributed cluster mode, multiple nodes need to be configured, under multiple nodes, the master node may request other nodes to search the graph at the same time, and finally returns the graph to the master node to perform screening and sorting, the directory structure of the multiple nodes is changed compared with that of a single node, that is, the directory hierarchy of the "kafka Partition number" may store data of different partitions on each node according to the allocation proportion set by the preset allocation rule of the program. The final comparison result is only obtained when all data are summarized. As shown in fig. 2, the method comprises the steps of:
step S201, receiving a vehicle map searching request sent by upper-layer equipment; the vehicle map search request includes a time condition, a vehicle brand, a vehicle model, an algorithm type, and a vehicle characteristic.
When an IPC device such as a gunlock and a camera captures a past vehicle picture and a video, or a user transmits a picture to be retrieved to initiate a vehicle Image search request, a web page first calls an Analysis server to analyze a vehicle brand, a vehicle model, an algorithm type, vehicle characteristics and the like of the picture or video stream, wherein the algorithm type includes an algorithm version, the vehicle characteristics are characteristic values extracted after Image Analysis (IA for short), and the characteristic values supplement a query comparison algorithm, that is: if a picture to be retrieved is related data analyzed by a certain algorithm, the same algorithm is also needed to be used for matching with related data in server hardware or a database when the picture is used for searching the picture, and in the embodiment, the algorithm used for analyzing the data is provided by C + +. The user can set corresponding time conditions according to requirements to search the images.
And step S202, determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request.
In order to reduce unnecessary comparison, reduce comparison times and improve searching efficiency, the vehicle brand and the vehicle model analyzed by the analysis server are combined to form a file name to be searched.
And step S203, screening a partial list which meets the algorithm type and time condition in the vehicle map searching request from the image feature index library.
And (3) setting the required algorithm type and time condition in the search parameter by the user, and screening out the partition list meeting the condition by the server.
And step S204, determining a search path according to the algorithm type, the time condition and the partial list in the vehicle map search request.
And the server determines a search path according to the algorithm type and the time condition set in the search parameter by the user and the partition list meeting the condition.
In step S205, file data corresponding to the search path and the file name is loaded from the picture feature index library.
And determining an absolute path according to the search path and the file name to be searched, and loading the feature data corresponding to the absolute path from the picture feature index library to a server memory.
When the map is searched by using the map, firstly, according to the determined absolute path, comparing data in the vehicle map searching request with characteristic data in a hard disk directory through a C + + algorithm, returning a similarity comparison result and a structural data identification ID obtained after comparison to a Java layer, and then associating the returned structural data identification ID with structural data in a database by the Java layer to inquire corresponding structural data.
Step S206, the first node executes the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request, so as to load the file data corresponding to the searching path and the file name from the partition corresponding to the first specified partition number.
By performing steps S201 to S205 on the file data of the different partition numbers assigned in the first node, the structured data and the similarity comparison result corresponding to the absolute path in the first node are determined.
Step S207, the second node executes the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request, so as to load the file data corresponding to the searching path and the file name from the partition corresponding to the second specified partition number.
By performing steps S201 to S205 on the file data of the different partition numbers assigned in the second node, the structured data and the similarity comparison result corresponding to the absolute path in the second node are determined.
Step S208, the main node executes the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request, so as to load the searching path and the file data corresponding to the file name from the partition corresponding to the third specified partition number.
And determining the structured data and the similarity comparison result corresponding to the absolute path in the main node by executing the steps S201 to S205 on the file data of different partition numbers distributed in the main node.
Step S209, the data meeting the vehicle characteristics is screened from the file data loaded by the first node, and the first screening result is returned to the master node.
The structured data corresponding to the absolute path in the first node determined in the step S206 is sorted according to the similarity comparison result, a preset number of structured data with higher similarity are selected from the screened data meeting the condition, and the preset number of structured data meeting the vehicle characteristics are returned to the master node.
Step S210, screening data that meets the vehicle characteristics from the file data loaded by the second node, and returning a second screening result to the master node.
The structured data corresponding to the absolute path in the second node determined in step S207 is sorted according to the similarity comparison result, a preset number of structured data having a higher similarity and conforming to the vehicle characteristics are selected from the screened data conforming to the conditions, and the preset number of structured data are returned to the master node.
And step S211, screening data which accord with the vehicle characteristics from the file data loaded by the main node to obtain a third screening result.
The structured data corresponding to the absolute path in the master node determined in the step S208 is sorted according to the similarity comparison result, and a preset number of structured data meeting the vehicle characteristics with higher similarity are selected from the screened data meeting the conditions.
Step S212, a preset number of data that meet the vehicle characteristics are screened out from the first screening result, the second screening result, and the third screening result by the master node, and the screening result is returned to the upper-layer device.
And summarizing the preset quantity of structured data determined in the main node, the first node and the second node in the main node, sequencing the data again according to the similarity comparison result, selecting the preset quantity of structured data which has higher similarity and accords with the vehicle characteristics from the screened data which accords with the conditions, taking the selected data as a final screening result, and returning the result to the upper-layer equipment or the user side.
The embodiment of the invention provides another vehicle image searching method, which is characterized in that a file name to be searched is determined by analyzing the brand and the model of a vehicle through an analysis server, an image searching mode combining the file name to be searched and a searching path is adopted, a data storage mode in an image feature index library is optimized, the transverse expansion capability of service is improved by adopting a mode of partition storage and multi-node expansion, and meanwhile, a multi-algorithm parallel mode is adopted for searching, so that the image searching efficiency and the accuracy of the vehicle are further improved.
The structural schematic diagram of the image searching device for the vehicle provided by the embodiment of the invention is as shown in fig. 3, the device is applied to a server, and an image feature index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the device includes:
the receiving module 10 is configured to receive a vehicle map searching request sent by an upper layer device; the vehicle map searching request comprises a time condition, a vehicle brand, a vehicle model, an algorithm type and vehicle characteristics; the first obtaining module 20 is configured to determine a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request; the first screening module 30 is configured to screen a partial list, which meets the algorithm type and time condition in the vehicle map search request, from the image feature index library; the second acquisition module 40 is used for determining a search path according to the algorithm type, the time condition and the partial list in the vehicle map search request; a loading module 50, configured to load file data corresponding to the search path and the file name from the picture feature index library; and the second screening module 60 is used for screening the data which accord with the vehicle characteristics from the loaded file data and returning the screening result to the upper-layer equipment.
Further, the directory structure of the picture feature index library also comprises partition numbers; the picture characteristic index library is divided into a plurality of partitions, and each partition is provided with a corresponding partition number; and file data distributed according to a preset distribution rule is stored in each partition.
In this embodiment, a server is provided with a master node, a first node and a second node; the first node is allocated with a partition corresponding to the first appointed partition number; the second node is distributed with a partition corresponding to a second specified partition number; the master node is allocated with a partition corresponding to the third appointed partition number; the device still includes: the first execution module is used for executing the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request through the first node so as to load the file data corresponding to the search path and the file name from the partition corresponding to the first specified partition number; the second execution module is used for executing the step of determining the file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request through the second node so as to load the file data corresponding to the search path and the file name from the partition corresponding to the second specified partition number; a third executing module, configured to execute, by the master node, the step of determining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map search request in the foregoing embodiment, so as to load the file data corresponding to the search path and the file name from the partition corresponding to the third specified partition number.
Specifically, the second screening module is further configured to screen data that meets the vehicle characteristics from the file data loaded by the first node, and return the first screening result to the master node; screening data which accord with the vehicle characteristics from the file data loaded by the second node, and returning a second screening result to the main node; screening data which accord with the vehicle characteristics from the file data loaded by the main node to obtain a third screening result; and screening out a preset amount of data which accord with the characteristics of the vehicle from the first screening result, the second screening result and the third screening result through the main node, and returning the screening results to upper-layer equipment.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
The embodiment of the present invention provides a schematic structural diagram of a picture search device for a vehicle, as shown in fig. 4, the device includes a memory 71 and a processor 72, a computer program operable on the processor 72 is stored in the memory 71, and the processor 72 implements the steps of the picture search method for a vehicle when executing the computer program.
As shown in fig. 4, the picture search apparatus further includes: a bus 73 and a communication interface 74, the processor 72, the communication interface 74 and the memory 71 being connected by the bus 73; the processor 72 is arranged to execute executable modules, such as computer programs, stored in the memory 71.
The Memory 71 may include a high-speed Random Access Memory (RAM) and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 74 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 73 can be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
The memory 71 is configured to store a program, and the processor 72 executes the program after receiving an execution instruction, and the method performed by the apparatus defined by the process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 72, or implemented by the processor 72.
The processor 72 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by instructions in the form of hardware, integrated logic circuits, or software in the processor 72. The Processor 72 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 71, and the processor 72 reads the information in the memory 71 and performs the steps of the above method in combination with the hardware thereof.
The embodiment of the present invention further provides a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the above-mentioned image search method for the vehicle, and specific implementation may refer to method implementation manners, which are not described herein again.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The picture searching method of the vehicle is characterized in that the method is applied to a server, and a picture characteristic index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the method comprises the following steps:
receiving a vehicle image searching request sent by upper-layer equipment; the vehicle map searching request comprises a time condition, a vehicle brand, a vehicle model, an algorithm type and vehicle characteristics; the algorithm type and the time condition in the vehicle map searching request are obtained through user setting; the vehicle features are obtained by extracting the algorithm type; the vehicle brand and the vehicle model are obtained through analysis by an analysis server;
combining file names to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request;
screening a partition list which meets the algorithm type and the time condition in the vehicle image searching request from the image feature index library; the partition list is a partition list adopting a distributed cluster storage mode;
determining a search path according to the algorithm type, the time condition and the storage form of the directory structure of the partition list in the vehicle map search request;
determining an absolute path according to the search path and the file name; loading feature data corresponding to the absolute path from the picture feature index library;
and screening data which accord with the vehicle characteristics from the loaded characteristic data according to a similarity matching mode, and returning a screening result to the upper-layer equipment.
2. The method according to claim 1, wherein the directory structure of the picture feature index library further comprises partition numbers;
the picture feature index library is divided into a plurality of partitions, and each partition is provided with a corresponding partition number; and each partition is stored with characteristic data distributed according to a preset distribution rule.
3. The method according to claim 2, wherein a master node, a first node and a second node are provided in the server; the first node is allocated with a partition corresponding to a first designated partition number; the second node is allocated with a partition corresponding to a second specified partition number; the master node is allocated with a partition corresponding to a third appointed partition number;
the method further comprises the following steps:
the first node executes the step of combining the file names to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in claim 1, so as to load the feature data corresponding to the absolute path from the partition corresponding to the first specified partition number;
executing, by the second node, the step of combining, according to the vehicle brand and the vehicle model in the vehicle map search request, the file name to be searched in claim 1, so as to load feature data corresponding to the absolute path from the partition corresponding to the second specified partition number;
the step of combining the file names to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in claim 1 is executed by the master node, so as to load the feature data corresponding to the absolute path from the partition corresponding to the third designated partition number.
4. The method according to claim 3, wherein the step of screening the loaded feature data for data meeting the vehicle features in a similarity matching manner and returning the screening result to the upper-layer equipment comprises the following steps:
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the first node, and returning a first screening result to the main node;
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the second node, and returning a second screening result to the main node;
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the main node to obtain a third screening result;
and screening a preset amount of data which accord with the vehicle characteristics from the first screening result, the second screening result and the third screening result through the main node, and returning the screening results to the upper-layer equipment.
5. The picture searching device for the vehicle is applied to a server, and a picture feature index library is stored in the server in advance; the directory structure of the picture feature index library comprises an algorithm type, a time condition, a vehicle brand and a vehicle model; the device comprises:
the receiving module is used for receiving a vehicle map searching request sent by upper-layer equipment; the vehicle map searching request comprises a time condition, a vehicle brand, a vehicle model, an algorithm type and vehicle characteristics; the algorithm type and the time condition in the vehicle map searching request are obtained through user setting; the vehicle features are obtained by extracting the algorithm type; the vehicle brand and the vehicle model are obtained through analysis by an analysis server;
the first acquisition module is used for combining a file name to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request;
the first screening module is used for screening a partition list which meets the algorithm type and the time condition in the vehicle map searching request from the image feature index library; the partition list is a partition list adopting a distributed cluster storage mode;
the second acquisition module is used for determining a search path according to the algorithm type, the time condition and the storage form of the directory structure of the partition list in the vehicle map search request;
the loading module is used for determining an absolute path through the search path and the file name; loading feature data corresponding to the absolute path from the picture feature index library;
and the second screening module is used for screening data which accord with the vehicle characteristics from the loaded characteristic data according to a similarity matching mode and returning a screening result to the upper-layer equipment.
6. The apparatus of claim 5, wherein the directory structure of the picture feature index library further comprises partition numbers;
the picture feature index library is divided into a plurality of partitions, and each partition is provided with a corresponding partition number; and each partition is stored with characteristic data distributed according to a preset distribution rule.
7. The apparatus according to claim 6, wherein the server is provided with a master node, a first node and a second node; the first node is allocated with a partition corresponding to a first designated partition number; the second node is allocated with a partition corresponding to a second specified partition number; the master node is allocated with a partition corresponding to a third appointed partition number;
the device further comprises:
a first executing module, configured to execute, by the first node, the step of combining the file names to be searched according to the vehicle brand and the vehicle model in the vehicle map searching request in claim 1, so as to load feature data corresponding to the absolute path from the partition corresponding to the first specified partition number;
a second executing module, configured to execute, by the second node, the step of combining, according to the vehicle brand and the vehicle model in the vehicle map searching request, the file name to be searched in claim 1, so as to load feature data corresponding to the absolute path from the partition corresponding to the second specified partition number;
a third executing module, configured to execute, by the master node, the step of combining, according to the vehicle brand and the vehicle model in the vehicle map search request, the file name to be searched in claim 1, so as to load the feature data corresponding to the absolute path from the partition corresponding to the third specified partition number.
8. The apparatus of claim 7, wherein the second screening module is further configured to:
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the first node, and returning a first screening result to the main node;
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the second node, and returning a second screening result to the main node;
according to a similarity matching mode, screening data which accord with the vehicle characteristics from the characteristic data loaded by the main node to obtain a third screening result;
and screening a preset amount of data which accord with the vehicle characteristics from the first screening result, the second screening result and the third screening result through the main node, and returning the screening results to the upper-layer equipment.
9. A picture search device for a vehicle, comprising a memory, a processor, in which a computer program is stored which is executable on the processor, characterized in that the processor realizes the steps of the method according to any of the preceding claims 1 to 4 when executing the computer program.
10. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520157.XA CN110209853B (en) | 2019-06-14 | 2019-06-14 | Image searching method, device and equipment for vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520157.XA CN110209853B (en) | 2019-06-14 | 2019-06-14 | Image searching method, device and equipment for vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110209853A CN110209853A (en) | 2019-09-06 |
| CN110209853B true CN110209853B (en) | 2021-08-06 |
Family
ID=67793030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910520157.XA Active CN110209853B (en) | 2019-06-14 | 2019-06-14 | Image searching method, device and equipment for vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209853B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401466A (en) * | 2020-03-26 | 2020-07-10 | 广州紫为云科技有限公司 | Traffic sign detection and identification marking method and device and computer equipment |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077199B (en) * | 2012-12-26 | 2016-07-13 | 北京思特奇信息技术股份有限公司 | A kind of file resource Search and Orientation method and device |
| KR101612483B1 (en) * | 2015-02-17 | 2016-04-15 | 이노뎁 주식회사 | Recording server, integrated control system having the same analyzing camera images in real time and operating method thereof |
| CN105205169B (en) * | 2015-10-12 | 2018-06-15 | 中国电子科技集团公司第二十八研究所 | A kind of distributed image index and search method |
| CN105574192A (en) * | 2015-12-24 | 2016-05-11 | 张梅云 | Computer document retrieval method |
| CN105513360B (en) * | 2016-01-28 | 2017-09-22 | 浪潮软件股份有限公司 | A kind of method and device of vehicle data processing |
| CN106021276A (en) * | 2016-04-28 | 2016-10-12 | 泰华智慧产业集团股份有限公司 | Method and system for checkpoint vehicle search based on distributed full-text retrieval system |
| CN106339415B (en) * | 2016-08-12 | 2019-08-23 | 北京奇虎科技有限公司 | Querying method, the apparatus and system of data |
| CN106649847A (en) * | 2016-12-30 | 2017-05-10 | 南威软件股份有限公司 | A large data real-time processing system based on Hadoop |
| CN107145502A (en) * | 2017-03-20 | 2017-09-08 | 中山大学 | A kind of method of mass picture storage and search |
| CN107330040B (en) * | 2017-06-27 | 2021-01-26 | 李博 | Learning question searching method and system |
| CN107480618A (en) * | 2017-08-02 | 2017-12-15 | 深圳微品时代网络技术有限公司 | A kind of data analysing method of big data platform |
| CN109669929A (en) * | 2018-12-14 | 2019-04-23 | 江苏瑞中数据股份有限公司 | Method for storing real-time data and system based on distributed parallel database |
-
2019
- 2019-06-14 CN CN201910520157.XA patent/CN110209853B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110209853A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106534344B (en) | Cloud platform video processing system and application method thereof | |
| US20170235767A1 (en) | System and method for multiresolution and multitemporal image search | |
| US10515117B2 (en) | Generating and reviewing motion metadata | |
| CN107092686B (en) | File management method and device based on cloud storage platform | |
| CN110134738B (en) | Distributed storage system resource estimation method and device | |
| WO2014006903A1 (en) | Content control method, content control apparatus, and program | |
| CN112527843B (en) | Data query method, device, terminal equipment and storage medium | |
| CN108389394B (en) | Method and system for analyzing initial city entry of vehicle | |
| CN111090822A (en) | Business object pushing method and device | |
| CN110209853B (en) | Image searching method, device and equipment for vehicle | |
| CN106815223B (en) | Mass picture management method and device | |
| CN111026709A (en) | Data processing method and device based on cluster access | |
| CN111506750B (en) | Picture retrieval method and device and electronic equipment | |
| CN107798450B (en) | Service distribution method and device | |
| CN112836124A (en) | Image data acquisition method and device, electronic equipment and storage medium | |
| CN115269519A (en) | Log detection method and device and electronic equipment | |
| CN111737371B (en) | Data flow detection classification method and device capable of dynamically predicting | |
| CN114443595A (en) | Method and device for processing file | |
| CN111104528B (en) | Picture acquisition method and device and client | |
| CN111552740A (en) | Data processing method and device | |
| CN112927004A (en) | Information cloud computing analysis method and information push server for big data portrait | |
| CN111198900A (en) | Data caching method and device for industrial control network, terminal equipment and medium | |
| CN112714033B (en) | Method and device for determining characteristic information of video set | |
| CN111598053B (en) | Image data processing method and device, medium and system thereof | |
| CN116719584B (en) | Data processing method, apparatus, computer, storage medium, and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |