CN108875839A - Article reminding method, system and equipment and storage medium are lost in a kind of vehicle - Google Patents
Article reminding method, system and equipment and storage medium are lost in a kind of vehicle Download PDFInfo
- Publication number
- CN108875839A CN108875839A CN201810689246.2A CN201810689246A CN108875839A CN 108875839 A CN108875839 A CN 108875839A CN 201810689246 A CN201810689246 A CN 201810689246A CN 108875839 A CN108875839 A CN 108875839A
- Authority
- CN
- China
- Prior art keywords
- picture
- vehicle
- article
- lost
- image
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
Abstract
This application discloses article reminding method, system and equipment and computer readable storage medium is lost in a kind of vehicle, this method includes：The first picture and user before beginning to use vehicle by video collector acquisition user terminate using the second picture after the vehicle；First picture and the second picture are compared, and judges whether first picture and the similarity of the second picture are greater than preset value according to comparing result；Article reminding information is lost if it is not, then generating.Article reminding method is lost in vehicle provided by the present application, the second picture after the first picture and end use before being begun to use by comparison user, it can effectively improve and identify the accuracy for losing article, reduce risk, make car owner and passenger that can receive prompting in time, ensuring to lose article can timely be found and be returned in time to the owner of lost property, and user experience is improved.
Description
Technical field
This application involves automobile technical field, more specifically to losing article reminding method, system in a kind of vehicle
And equipment and a kind of computer readable storage medium.
Background technique
Currently, more more and more universal with private car and net about vehicle, user march into the arena get off after mobile phone, wallet etc. is important
Article is left in the car, brings very big inconvenience to the owner of lost property.In the prior art, generally driver passes through the vision of people every time
Checking back seat and front stall, in each lower Chinese herbaceous peony self-check, whether there is or not lose article whether there is or not article or passenger is lost.Artificial inspection
Look into cause to lose article inspection accuracy is lower, risk is higher.
Therefore, the accuracy that article inspection is lost in vehicle how is improved, reducing risk is those skilled in the art's needs
It solves the problems, such as.
Summary of the invention
A kind of being designed to provide in vehicle for the application loses article reminding method, system and equipment and a kind of computer
Readable storage medium storing program for executing improves the accuracy for losing article inspection in vehicle, reduces risk.
To achieve the above object, this application provides losing article reminding method in a kind of vehicle, including：
The first picture and user before beginning to use vehicle by video collector acquisition user terminate using the vehicle
Second picture afterwards；
It compares first picture and the second picture, and first picture and described the is judged according to comparing result
Whether the similarity of two pictures is greater than preset value；
Article reminding information is lost if it is not, then generating.
Wherein, the generation loses article reminding information, including：
The diff area in the second picture is extracted according to the comparing result；
Identify the article in the diff area, and according to recognition result generate described in lose article reminding information.
Wherein, the article in the diff area is identified, including：
The diff area is inputted in the disaggregated model that training is completed, to obtain recognition result.
Wherein, before the diff area being inputted in the disaggregated model that training is completed, further include：
Using training sample train classification models, to obtain the disaggregated model of training completion；Wherein, the training sample
Image-region including known recognition result.
Wherein, compare first picture and the second picture, and according to comparing result judge first picture and
Whether the similarity of the second picture is greater than preset value, including：
The first brightness of image of the first pixel of first picture is calculated, and calculates the second picture of the second picture
Second brightness of image of vegetarian refreshments；Wherein second pixel is first pixel corresponding position in the second picture
Pixel；
Judge whether the first image brightness and the difference of second brightness of image are greater than brightness preset value, if so,
Second pixel is then determined as candidate pixel point；
Judge whether the quantity of the candidate pixel point is greater than the first preset value, if so, first picture with it is described
The similarity of second picture is less than preset value.
Wherein, formula is calculated according to brightness of image and calculates the first image brightness and second brightness of image；Wherein,
Described image brightness calculation formula is specially：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)
For the brightness of image of the pixel.
Wherein, extracting the diff area in the second picture according to the comparing result includes：
It determines that the candidate pixel point quantity is greater than the unit area of the second preset value, and is generated according to the unit area
The diff area.
To achieve the above object, this application provides losing article reminding system in a kind of vehicle, including：
Module is obtained, for beginning to use the first picture before vehicle and user to terminate by video collector acquisition user
Use the second picture after the vehicle；
Contrast module judges described for comparing first picture and the second picture, and according to comparing result
Whether the similarity of one picture and the second picture is greater than preset value；
Generation module, for generating when the similarity of first picture and the second picture is not more than preset value
Lose article reminding information.
Wherein, the generation module includes：
Extraction unit, for extracting the diff area in the second picture according to the comparing result；
Recognition unit, the article in the diff area for identification, and according to recognition result generate described in lose article
Prompting message.
Wherein, the recognition unit is specially to input the diff area in the disaggregated model that training is completed, so as to
To recognition result, and according to the recognition result generate described in lose the unit of article reminding information.
Wherein, further include：
Training unit, for utilizing training sample train classification models, to obtain the disaggregated model of training completion；Its
In, the training sample includes the image-region of known recognition result.
Wherein, the contrast module includes：
Computing unit, the first brightness of image of the first pixel for calculating first picture, and calculate described
Second brightness of image of the second pixel of two pictures；Wherein second pixel is first pixel described second
The pixel of corresponding position in picture；
First judging unit, for judging whether the first image brightness and the difference of second brightness of image are greater than
Brightness preset value, if so, second pixel is determined as candidate pixel point；
Second judgment unit, for judging whether the quantity of the candidate pixel point is greater than the first preset value, if so, institute
The similarity for stating the first picture and the second picture is less than preset value.
Wherein, the computing unit is specially and calculates formula according to brightness of image to calculate the first image brightness and described
The unit of second brightness of image；Wherein, described image brightness calculation formula is specially：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)
For the brightness of image of the pixel.
Wherein, the extraction unit is specially to determine that the candidate pixel point quantity is greater than the unit area of the second preset value
Domain, and generate according to the unit area unit of the diff area.
To achieve the above object, this application provides losing article reminding equipment in a kind of vehicle, including：
Memory, for storing computer program；
Processor realizes the step as lost article reminding method in above-mentioned vehicle when for executing the computer program
Suddenly.
To achieve the above object, this application provides a kind of computer readable storage medium, the computer-readable storages
It is stored with computer program on medium, realizes when the computer program is executed by processor and is mentioned as lost article in above-mentioned vehicle
The step of method of waking up.
By above scheme it is found that losing article reminding method in a kind of vehicle provided by the present application, including：Pass through video
Collector obtains user and the first picture before vehicle and user is begun to use to terminate using the second picture after the vehicle；Comparison
First picture and the second picture, and judge that first picture is similar to the second picture according to comparing result
Whether degree is greater than preset value；Article reminding information is lost if it is not, then generating.
Article reminding method is lost in vehicle provided by the present application, by compare user begin to use before the first picture and
Second picture after terminating use illustrates exist and the in second picture when the similarity of two pictures is not more than preset value
The different article of one picture, user exists in vehicle loses article, issues the user with prompting.Pass through image comparison, Ke Yiyou
Effect, which improves, identifies the accuracy for losing article, reduces risk, makes car owner and passenger that can receive prompting in time, it is ensured that lose object
Product can timely be found and be returned in time to the owner of lost property, and user experience is improved.Disclosed herein as well is lose in a kind of vehicle
Junk product system for prompting and equipment and a kind of computer readable storage medium, are equally able to achieve above-mentioned technical effect.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart that article reminding method is lost in a kind of vehicle disclosed in the embodiment of the present application；
Fig. 2 is the flow chart that article reminding method is lost in another kind vehicle disclosed in the embodiment of the present application；
Fig. 3 is that the application implements to lose the flow chart that article reminding method example is applied to net about vehicle in disclosed vehicle；
Fig. 4 is that the application implements to lose the flow chart that article reminding method example is applied to private car in disclosed vehicle；
Fig. 5 is the structure chart that article reminding system is lost in a kind of vehicle disclosed in the embodiment of the present application；
Fig. 6 is the structure chart that article reminding system is lost in another kind vehicle disclosed in the embodiment of the present application；
Fig. 7 is the structure chart that article reminding equipment is lost in a kind of vehicle disclosed in the embodiment of the present application；
Fig. 8 is the structure chart that article reminding equipment is lost in another kind vehicle disclosed in the embodiment of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The embodiment of the present application discloses in a kind of vehicle and loses article reminding method, improves and loses article inspection in vehicle
Accuracy, reduce risk.
Referring to Fig. 1, the flow chart of article reminding method is lost in a kind of vehicle disclosed in the embodiment of the present application, such as Fig. 1 institute
Show, including：
S101：The first picture and user before beginning to use vehicle by video collector acquisition user terminate using described
Second picture after vehicle；
The first picture in this step is that user begins to use the picture before vehicle, and second picture is that user terminates using vehicle
Picture after.This step is not defined the specific acquisition time of the first picture and second picture, can by taking net about vehicle as an example
To be acquired interior image as the first picture after passenger is reserved successfully by client, stroke is got in client
Interior image is acquired as second picture after the information of end.By taking private car as an example, acquired when flame-out with the last time
Image is as the first picture, this image acquired when flame-out is as second picture, and certainly to promote user experience, user can also
To set the first fixed picture.In short, the purpose of this step is that acquisition user uses the two images before and after vehicle, so as to
Subsequent step compares two images to obtain the testing result for losing article.
It is understood that above-mentioned first picture and the second figure can be obtained by video collector (such as camera)
Piece, the video collector can be installed on interior rearview mirror, naturally it is also possible to directly utilize the camera on user mobile phone
As video collector, in this embodiment, need to fix the position of the camera so that subsequent step carries out image pair
Than.
S102：Compare first picture and the second picture, and according to comparing result judge first picture with
Whether the similarity of the second picture is greater than preset value；If so, terminating process, if it is not, then entering S103；
In specific implementation, it can be detected by way of comparing the first picture and second picture in vehicle with the presence or absence of something lost
Junk product, and illustrate to have no in vehicle when similarity is greater than preset value according to the similarity of comparing result two width pictures of generation
Article is lost, process is terminated.When similarity is not more than preset value, into S103.It should be noted that herein not to similarity
Specific generating mode be defined, those skilled in the art can according to actual detection accuracy select suitably to analogy
Formula.
S103：Generation loses article reminding information.
In specific implementation, when detecting in vehicle in the presence of article is lost, generation loses article reminding information, and prompts
Driver or passenger is not defined specific prompting mode herein, for example, to driver or being multiplied by way of vibration or jingle bell
The mobile phone terminal of visitor sends prompting message, reminds driver or passenger etc. by way of car broadcast.
It is understood that herein lose article reminding information can only prompt user's vehicle in exist lose article,
The specific article lost is voluntarily determined by user.Certainly, system directly can lose object to this as a preferred implementation manner,
Product are identified, and user is prompted specifically to lose article (such as mobile phone, wallet).Specifically, according to the first picture and second
The comparing result of picture extracts the diff area in second picture, and the article in Recognition Different region, raw according to recognition result
Article reminding information is lost at described.
It should be noted that be not defined to the concrete mode of article identification herein, image such as is customized using EasyDL
Identification technology etc..As an implementation, it can use the article in disaggregated model Recognition Different region.Specifically, by institute
It states in the disaggregated model that diff area input training is completed, obtained classification results are the result of article identification.The classification mould
Type can be common disaggregated model, such as decision-tree model, supporting vector machine model, Random Forest model, logistic regression mould
Type etc..
It is understood that should also include training point before the diff area is inputted in the disaggregated model that training is completed
The step of class model.Specifically, obtaining training sample, which is the set of the image-region of known recognition result, benefit
With the training sample train classification models, to obtain the disaggregated model of training completion.
Article reminding method is lost in vehicle provided by the embodiments of the present application, first before beginning to use by comparison user
Second picture after picture and end use illustrates to deposit in second picture when the similarity of two pictures is not more than preset value
In the article different from the first picture, user exists in vehicle loses article, issues the user with prompting.By image comparison,
It can effectively improve and identify the accuracy for losing article, reduce risk, make car owner and passenger that can receive prompting in time, it is ensured that
Losing article can timely be found and be returned in time to the owner of lost property, and user experience is improved.
The embodiment of the present application discloses in a kind of vehicle and loses article reminding method, relative to a upper embodiment, this implementation
Example has made further instruction and optimization to technical solution.Specifically：
Referring to fig. 2, the flow chart of article reminding method, such as Fig. 2 are lost in another vehicle provided by the embodiments of the present application
It is shown, including：
S201：The first picture and user before beginning to use vehicle by video collector acquisition user terminate using described
Second picture after vehicle；
S221：The first brightness of image of the first pixel of first picture is calculated, and calculates the second picture
Second brightness of image of the second pixel；Wherein second pixel is that first pixel is right in the second picture
Answer the pixel of position；
S222：Judge whether the first image brightness and the difference of second brightness of image are greater than brightness preset value,
If so, second pixel is determined as candidate pixel point；
In specific implementation, the brightness of image of all pixels point of the first picture and second picture, the brightness of image are calculated
It can be the gray value of the pixel, naturally it is also possible to be that other indicate the value of pixel brightness, be not specifically limited herein.Than
Illustrate the pixel in user when difference is greater than preset value compared with the brightness of image of the corresponding pixel in position in two width pictures
Using being changed before and after vehicle, using the pixel in second picture as candidate pixel point.
It should be noted that the present embodiment is not defined the specific calculation of brightness of image, those skilled in the art
Member can flexible choice according to the actual situation.Formula can be calculated according to brightness of image as a preferred implementation manner, to calculate
The first image brightness and second brightness of image；Wherein, brightness of image, which calculates formula, to be specially：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)
For the brightness of image of the pixel.
S223：Judge whether the quantity of the candidate pixel point is greater than the first preset value, if so, determining the candidate pixel
Point quantity is greater than the unit area of the second preset value, and generates the diff area according to the unit area；
In specific implementation, it can be judged whether there is according to the quantity of candidate pixel point and lose article.Specifically, when waiting
When selecting the quantity of pixel no more than the first preset value, illustrate that the variation of two width picture respective pixel point brightness is made for objective factor
At error, can be neglected.But when the quantity of candidate pixel point is greater than the first preset value, illustrate two width picture pixels points
Brightness change is not objective factor, and user loses article.
When the quantity of candidate pixel point is greater than the first preset value, generated according to the candidate pixel point quantity in unit area
Diff area.Specifically, picture in its entirety is divided into multiple unit areas by preset standard first, those skilled in the art can
To define the size and the criteria for classifying of unit area according to actual required precision, it is not specifically limited herein.Count each list
Candidate pixel point quantity in the region of position illustrates that the unit area is the portion for losing article when quantity is greater than the second preset value
Partial image.After the unit area that all candidate pixel point quantity are met the requirements has been determined, difference is generated according to these unit areas
Adjacent unit area is merged into diff area by region.
S203：Identify the article in the diff area, and according to recognition result generate described in lose article reminding information.
In specific implementation, it can use EasyDL customization image recognition technology after extracting diff area or train completion
The article in disaggregated model Recognition Different region, and article reminding information is lost using described in the generation of the information of the article, it prompts to use
Family, which exists, loses article.
Below by taking net about vehicle as an example, a kind of specific application scenarios embodiment is introduced, as shown in figure 3, specifically：
Step 1：(determination can be arrived at the destination in reservation APP click by driver) after a upper passenger getting off car, after vehicle is interior
Camera on visor acquires pic1, and is uploaded to server；
Step 2：This is about after the passenger getting off car of vehicle, and driver is after reservation APP click arrives at the destination, backsight in vehicle
Camera on mirror acquires pic2, and is uploaded to server；
Step 3：Server compares pic1 and pic2, and the diff area in pic2 is extracted when similarity is less than preset value,
And specific article is identified using EasyDL customization image recognition technology；
Step 4：The picture of the diff area is respectively sent to the terminal where passenger and driver by server, and both sides are true
When recognizing that the article is non-to lose article, terminate process, either one determines that the article is that can pass through reservation APP notice when losing article
Other side, if passenger has got off at this time, both sides can give back mode by reservation APP negotiation.
Below by taking private car as an example, another specific application scenarios embodiment is introduced, as shown in figure 4, specifically：
Step 1：After the completion of last switch-off operation, the camera on rear-viewing mirror in vehicle acquires pic1, and uploads
It is saved to server；
Step 2：After receiving this flame-out information, the camera on rear-viewing mirror in vehicle acquires pic2, and is uploaded to clothes
Business device；
Step 3：Server compares pic1 and pic2, and the diff area in pic2 is extracted when similarity is less than preset value,
And specific article is identified using EasyDL customization image recognition technology；
Step 4：The picture of the diff area is respectively sent to the terminal where user by server, and passes through car
Voice prompting reminds user to exist and loses article.
It is introduced below to losing article reminding system in a kind of vehicle provided by the embodiments of the present application, it is described below
Lost in a kind of vehicle lose article reminding method in article reminding system and a kind of above-described vehicle can be cross-referenced.
Referring to Fig. 5, the structure chart of article reminding system is lost in a kind of vehicle provided by the embodiments of the present application, such as Fig. 3 institute
Show, including：
Module 501 is obtained, for beginning to use the first picture before vehicle and user by video collector acquisition user
Terminate using the second picture after the vehicle；
Contrast module 502, for comparing first picture and the second picture, and described in being judged according to comparing result
Whether the similarity of the first picture and the second picture is greater than preset value；
Generation module 503, for giving birth to when the similarity of first picture and the second picture is not more than preset value
At losing article reminding information.
Article reminding system is lost in vehicle provided by the embodiments of the present application, first before beginning to use by comparison user
Second picture after picture and end use illustrates to deposit in second picture when the similarity of two pictures is not more than preset value
In the article different from the first picture, user exists in vehicle loses article, issues the user with prompting.By image comparison,
It can effectively improve and identify the accuracy for losing article, reduce risk, make car owner and passenger that can receive prompting in time, it is ensured that
Losing article can timely be found and be returned in time to the owner of lost property, and user experience is improved.
The embodiment of the present application discloses in a kind of vehicle and loses article reminding system, relative to a upper embodiment, this implementation
Example has made further instruction and optimization to technical solution.Specifically：
Referring to Fig. 6, the structure chart of article reminding system, such as Fig. 6 are lost in another kind vehicle provided by the embodiments of the present application
It is shown, including：
Module 601 is obtained, for beginning to use the first picture before vehicle and user by video collector acquisition user
Terminate using the second picture after the vehicle；
Computing unit 621, the first brightness of image of the first pixel for calculating first picture, and described in calculating
Second brightness of image of the second pixel of second picture；Wherein second pixel is first pixel described the
The pixel of corresponding position in two pictures；
First judging unit 622, for judge the first image brightness and second brightness of image difference whether
Greater than brightness preset value, if so, second pixel is determined as candidate pixel point；
Second judgment unit 623, for judging whether the quantity of the candidate pixel point is greater than the first preset value, if so,
Then start the workflow of extraction unit.
The extraction unit 631, for determining that the candidate pixel point quantity is greater than the unit area of the second preset value, and
The diff area is generated according to the unit area；
Recognition unit 632, the article in the diff area for identification, and according to recognition result generate described in lose object
Product prompting message.
Present invention also provides article reminding equipment is lost in a kind of vehicle, referring to Fig. 7, provided by the embodiments of the present application one
The structure chart of article reminding equipment is lost in kind vehicle, as shown in fig. 7, comprises：
Memory 100, for storing computer program；
Step provided by above-described embodiment may be implemented in processor 200 when for executing the computer program.
Specifically, memory 100 includes non-volatile memory medium, built-in storage.Non-volatile memory medium storage
There are operating system and computer-readable instruction, which is that the operating system and computer in non-volatile memory medium can
The operation of reading instruction provides environment.Processor 200 provides calculating and control ability to lose article reminding equipment in vehicle, executes
When the computer program saved in the memory 100, following steps may be implemented：User is obtained by video collector to start
Using before vehicle the first picture and user terminate using the second picture after the vehicle；Compare first picture with it is described
Second picture, and judge whether first picture and the similarity of the second picture are greater than preset value according to comparing result；
Article reminding information is lost if it is not, then generating.
Article reminding equipment is lost in vehicle provided by the embodiments of the present application, first before beginning to use by comparison user
Second picture after picture and end use illustrates to deposit in second picture when the similarity of two pictures is not more than preset value
In the article different from the first picture, user exists in vehicle loses article, issues the user with prompting.By image comparison,
It can effectively improve and identify the accuracy for losing article, reduce risk, make car owner and passenger that can receive prompting in time, it is ensured that
Losing article can timely be found and be returned in time to the owner of lost property, and user experience is improved.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：The diff area in the second picture is extracted according to the comparing result；Identify the object in the diff area
Product, and according to recognition result generate described in lose article reminding information.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：The diff area is inputted in the disaggregated model that training is completed, to obtain recognition result.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：Using training sample train classification models, to obtain the disaggregated model of training completion；Wherein, the trained sample
This includes the image-region of known recognition result.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：The first brightness of image of the first pixel of first picture is calculated, and calculates the second of the second picture
Second brightness of image of pixel；Wherein second pixel is that first pixel corresponds to position in the second picture
The pixel set；Judge whether the first image brightness and the difference of second brightness of image are greater than brightness preset value, if
It is that second pixel is then determined as candidate pixel point；It is pre- to judge whether the quantity of the candidate pixel point is greater than first
If value, if so, the similarity of first picture and the second picture is less than preset value.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：Formula, which is calculated, according to brightness of image calculates the first image brightness and second brightness of image；Wherein, described
Brightness of image calculates formula：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)
For the brightness of image of the pixel.
Preferably, it when the processor 200 executes the computer subprogram saved in the memory 100, may be implemented
Following steps：Determine that the candidate pixel point quantity is greater than the unit area of the second preset value, and raw according to the unit area
At the diff area.
On the basis of the above embodiments, preferably, referring to Fig. 8, article reminding is lost in the vehicle
Equipment further includes：
Input interface 300 is connected with processor 200, for obtaining computer program, parameter and the instruction of external importing,
It saves through the control of processor 200 into memory 100.The input interface 300 can be connected with input unit, and it is manual to receive user
The parameter or instruction of input.The input unit can be the touch layer covered on display screen, be also possible to be arranged in terminal enclosure
Key, trace ball or Trackpad, be also possible to keyboard, Trackpad or mouse etc..
Display unit 400 is connected with processor 200, the data sent for video-stream processor 200.The display unit 400
It can be display screen, liquid crystal display or the electric ink display screen etc. in PC machine.Specifically, in this example it is shown that
Unit 400 shows picture and the recognition result of article etc. of diff area to user.
The network port 500 is connected with processor 200, for being communicatively coupled with external each terminal device.The communication link
The communication technology used by connecing can be cable communicating technology or wireless communication technique, and such as mobile high definition chained technology (MHL) leads to
It is blue with universal serial bus (USB), high-definition media interface (HDMI), adopting wireless fidelity technology (WiFi), Bluetooth Communication Technology, low-power consumption
The tooth communication technology, communication technology based on IEEE802.11s etc..Specifically, in the present embodiment, by the network port 500 to
Processor 200 imports the disaggregated model etc. that training is completed.
Video collector 600 is connected with processor 200, for obtaining video data, then sends video data to place
It manages device 200 and carries out Data Analysis Services, processing result can be sent to display unit 400 and shown by subsequent processor 200,
Or it is transmitted to processor 100 and is saved, or preset data receiver end can be sent to by the network port 500
End.Specifically, in the present embodiment, the first picture before user begins to use vehicle can be obtained by video collector 600
Terminate with user using the second picture after vehicle.
Present invention also provides a kind of computer readable storage medium, which may include：USB flash disk, mobile hard disk,
Read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic
The various media that can store program code such as dish or CD.Computer program, the calculating are stored on the storage medium
Machine program realizes following steps when being executed by processor：The first figure before user begins to use vehicle is obtained by video collector
Piece and user terminate using the second picture after the vehicle；First picture and the second picture are compared, and according to right
Judge whether first picture and the similarity of the second picture are greater than preset value than result；Object is lost if it is not, then generating
Product prompting message.
The embodiment of the present application by compare user begin to use before the first picture and terminate use after second picture, when
When the similarity of two pictures is not more than preset value, illustrate there is the article different from the first picture, Yong Hu in second picture
Exist in vehicle and lose article, issues the user with prompting.By image comparison, it can effectively improve and identify the standard for losing article
Exactness reduces risk, makes car owner and passenger that can receive prompting in time, it is ensured that losing article can timely be found and timely
The owner of lost property is returned to, user experience is improved.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：The diff area in the second picture is extracted according to the comparing result；Identify the difference section
Article in domain, and according to recognition result generate described in lose article reminding information.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：The diff area is inputted in the disaggregated model that training is completed, to obtain recognition result.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：Using training sample train classification models, to obtain the disaggregated model of training completion；Wherein, institute
State the image-region that training sample includes known recognition result.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：The first brightness of image of the first pixel of first picture is calculated, and calculates second figure
Second brightness of image of the second pixel of piece；Wherein second pixel is first pixel in the second picture
The pixel of middle corresponding position；It is pre- to judge whether the difference of the first image brightness and second brightness of image is greater than brightness
If value, if so, second pixel is determined as candidate pixel point；Judge whether the quantity of the candidate pixel point is greater than
First preset value, if so, the similarity of first picture and the second picture is less than preset value.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：Formula, which is calculated, according to brightness of image calculates the first image brightness and second brightness of image；
Wherein, described image brightness calculation formula is specially：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)
For the brightness of image of the pixel.
Preferably, when the computer subprogram stored in the computer readable storage medium is executed by processor, specifically
Following steps may be implemented：Determine that the candidate pixel point quantity is greater than the unit area of the second preset value, and according to the list
Diff area described in the Area generation of position.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
The foregoing description of the disclosed embodiments makes professional and technical personnel in the field can be realized or use the application.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the application.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.It should be pointed out that for those skilled in the art, under the premise of not departing from the application principle, also
Can to the application, some improvement and modification can also be carried out, these improvement and modification also fall into the protection scope of the claim of this application
It is interior.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. losing article reminding method in a kind of vehicle, which is characterized in that including：
The first picture and user before beginning to use vehicle by video collector acquisition user terminate using after the vehicle
Second picture；
First picture and the second picture are compared, and first picture and second figure are judged according to comparing result
Whether the similarity of piece is greater than preset value；
Article reminding information is lost if it is not, then generating.
2. article reminding method is lost in vehicle according to claim 1, which is characterized in that the generation loses article reminding
Information, including：
The diff area in the second picture is extracted according to the comparing result；
Identify the article in the diff area, and according to recognition result generate described in lose article reminding information.
3. article reminding method is lost in vehicle according to claim 2, which is characterized in that identify in the diff area
Article, including：
The diff area is inputted in the disaggregated model that training is completed, to obtain recognition result.
4. article reminding method is lost in vehicle according to claim 3, which is characterized in that input the diff area and instruct
Before practicing in the disaggregated model completed, further include：
Using training sample train classification models, to obtain the disaggregated model of training completion；Wherein, the training sample includes
The image-region of known recognition result.
5. according to article reminding method is lost in any one of the claim 2-4 vehicle, which is characterized in that comparison described first
Picture and the second picture, and judge whether the similarity of first picture and the second picture is big according to comparing result
In preset value, including：
The first brightness of image of the first pixel of first picture is calculated, and calculates the second pixel of the second picture
The second brightness of image；Wherein second pixel is the picture of the first pixel corresponding position in the second picture
Vegetarian refreshments；
Judge whether the first image brightness and the difference of second brightness of image are greater than brightness preset value, if so, will
Second pixel is determined as candidate pixel point；
Judge whether the quantity of the candidate pixel point is greater than the first preset value, if so, first picture and described second
The similarity of picture is less than preset value.
6. article reminding method is lost in vehicle according to claim 5, which is characterized in that calculate formula according to brightness of image
Calculate the first image brightness and second brightness of image；Wherein, described image brightness calculation formula is specially：
L(x,y)=0.3R(x,y)+0.59G(x,y)+0.11B(x,y)；
Wherein, (x, y) is the coordinate value of pixel, R(x,y)、G(x,y)And B(x,y)For the pixel value of the pixel, L(x,y)For institute
State the brightness of image of pixel.
7. article reminding method is lost in vehicle according to claim 5, which is characterized in that extracted according to the comparing result
Diff area in the second picture includes：
Determine that the candidate pixel point quantity is greater than the unit area of the second preset value, and according to unit area generation
Diff area.
8. losing article reminding system in a kind of vehicle, which is characterized in that including：
Obtain module, for by video collector acquisition user begin to use the first picture before vehicle and user terminate using
Second picture after the vehicle；
Contrast module judges first figure for comparing first picture and the second picture, and according to comparing result
Whether the similarity of piece and the second picture is greater than preset value；
Generation module, for when the similarity of first picture and the second picture is not more than preset value, generation to be lost
Article reminding information.
9. losing article reminding equipment in a kind of vehicle, which is characterized in that including：
Memory, for storing computer program；
Processor is realized when for executing the computer program and loses article in vehicle as described in any one of claim 1 to 7
The step of based reminding method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes that losing article in vehicle as described in any one of claim 1 to 7 mentions when the computer program is executed by processor
The step of method of waking up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689246.2A CN108875839A (en) | 2018-06-28 | 2018-06-28 | Article reminding method, system and equipment and storage medium are lost in a kind of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689246.2A CN108875839A (en) | 2018-06-28 | 2018-06-28 | Article reminding method, system and equipment and storage medium are lost in a kind of vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108875839A true CN108875839A (en) | 2018-11-23 |
Family
ID=64296548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810689246.2A Pending CN108875839A (en) | 2018-06-28 | 2018-06-28 | Article reminding method, system and equipment and storage medium are lost in a kind of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875839A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978371A (en) * | 2019-03-26 | 2019-07-05 | 北京三快在线科技有限公司 | A kind of order allocation method and device |
| CN110796017A (en) * | 2019-09-30 | 2020-02-14 | 北京三快在线科技有限公司 | Method and device for determining article drop-out and method and device for training model |
| CN111931734A (en) * | 2020-09-25 | 2020-11-13 | 深圳佑驾创新科技有限公司 | Method and device for identifying lost object, vehicle-mounted terminal and storage medium |
| CN111982372A (en) * | 2020-07-09 | 2020-11-24 | 深圳市元征科技股份有限公司 | Method for detecting vehicle missing object, vehicle-mounted device and computer storage medium |
| CN112069901A (en) * | 2020-08-06 | 2020-12-11 | 南京领行科技股份有限公司 | In-vehicle article monitoring method, electronic device, and storage medium |
| CN112492276A (en) * | 2020-11-27 | 2021-03-12 | 大陆投资(中国)有限公司 | Passenger leaving reminding system of online car reservation |
| CN112560546A (en) * | 2019-09-10 | 2021-03-26 | 杭州海康威视数字技术股份有限公司 | Throwing behavior detection method and device and storage medium |
| CN112785359A (en) * | 2019-11-05 | 2021-05-11 | 北京地平线机器人技术研发有限公司 | Method and apparatus for controlling mobile device, and computer-readable storage medium |
| CN113065425A (en) * | 2021-03-19 | 2021-07-02 | 东风汽车集团股份有限公司 | Method and system for reminding objects left in vehicle based on environmental information and storage medium |
| CN114648829A (en) * | 2022-03-14 | 2022-06-21 | 上海齐感电子信息科技有限公司 | Intelligent access control method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520938A (en) * | 2008-12-31 | 2009-09-02 | 上海序参量科技发展有限公司 | Object identification based reminder for forgotten articles and realization method thereof |
| CN105696253A (en) * | 2015-01-04 | 2016-06-22 | 海信（山东）冰箱有限公司 | A washing machine control method and a washing machine |
| CN205486689U (en) * | 2015-12-30 | 2016-08-17 | 江苏穿越金点信息科技有限公司 | Legacy intelligent monitoring alarm system in bus |
| US20180053398A1 (en) * | 2016-08-16 | 2018-02-22 | Shareef Kharbawi | Method and System which integrated with Doors Handle that Alert Against Forgetting Objects in the Car |
| CN108189753A (en) * | 2017-12-15 | 2018-06-22 | 信利光电股份有限公司 | A kind of vehicle carried method and system |
-
2018
- 2018-06-28 CN CN201810689246.2A patent/CN108875839A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520938A (en) * | 2008-12-31 | 2009-09-02 | 上海序参量科技发展有限公司 | Object identification based reminder for forgotten articles and realization method thereof |
| CN105696253A (en) * | 2015-01-04 | 2016-06-22 | 海信（山东）冰箱有限公司 | A washing machine control method and a washing machine |
| CN205486689U (en) * | 2015-12-30 | 2016-08-17 | 江苏穿越金点信息科技有限公司 | Legacy intelligent monitoring alarm system in bus |
| US20180053398A1 (en) * | 2016-08-16 | 2018-02-22 | Shareef Kharbawi | Method and System which integrated with Doors Handle that Alert Against Forgetting Objects in the Car |
| CN108189753A (en) * | 2017-12-15 | 2018-06-22 | 信利光电股份有限公司 | A kind of vehicle carried method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978371A (en) * | 2019-03-26 | 2019-07-05 | 北京三快在线科技有限公司 | A kind of order allocation method and device |
| CN112560546A (en) * | 2019-09-10 | 2021-03-26 | 杭州海康威视数字技术股份有限公司 | Throwing behavior detection method and device and storage medium |
| CN110796017A (en) * | 2019-09-30 | 2020-02-14 | 北京三快在线科技有限公司 | Method and device for determining article drop-out and method and device for training model |
| CN112785359A (en) * | 2019-11-05 | 2021-05-11 | 北京地平线机器人技术研发有限公司 | Method and apparatus for controlling mobile device, and computer-readable storage medium |
| CN112785359B (en) * | 2019-11-05 | 2024-03-05 | 北京地平线机器人技术研发有限公司 | Method, apparatus and computer readable storage medium for controlling a removable device |
| CN111982372A (en) * | 2020-07-09 | 2020-11-24 | 深圳市元征科技股份有限公司 | Method for detecting vehicle missing object, vehicle-mounted device and computer storage medium |
| CN112069901A (en) * | 2020-08-06 | 2020-12-11 | 南京领行科技股份有限公司 | In-vehicle article monitoring method, electronic device, and storage medium |
| CN112069901B (en) * | 2020-08-06 | 2022-07-08 | 南京领行科技股份有限公司 | In-vehicle article monitoring method, electronic device, and storage medium |
| CN111931734A (en) * | 2020-09-25 | 2020-11-13 | 深圳佑驾创新科技有限公司 | Method and device for identifying lost object, vehicle-mounted terminal and storage medium |
| CN112492276A (en) * | 2020-11-27 | 2021-03-12 | 大陆投资(中国)有限公司 | Passenger leaving reminding system of online car reservation |
| CN113065425A (en) * | 2021-03-19 | 2021-07-02 | 东风汽车集团股份有限公司 | Method and system for reminding objects left in vehicle based on environmental information and storage medium |
| CN114648829A (en) * | 2022-03-14 | 2022-06-21 | 上海齐感电子信息科技有限公司 | Intelligent access control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875839A (en) | Article reminding method, system and equipment and storage medium are lost in a kind of vehicle | |
| JP6874150B2 (en) | Picture-based vehicle damage assessment methods and equipment, as well as electronic devices | |
| Li et al. | Content-partitioned structural similarity index for image quality assessment | |
| US11379955B2 (en) | Electronic device, image processing method thereof, and computer-readable recording medium | |
| US11195261B2 (en) | Image processing apparatus and image processing method | |
| CN110023964B (en) | Training and/or using neural network models to generate intermediate outputs of spectral images | |
| CN111814520A (en) | Skin type detection method, skin type grade classification method, and skin type detection device | |
| CN107633237B (en) | Image background segmentation method, device, equipment and medium | |
| CN111652087B (en) | Car inspection method, device, electronic equipment and storage medium | |
| KR20170088174A (en) | Method for providing information on scalp diagnosis based on image | |
| CN109145766A (en) | Model training method, device, recognition methods, electronic equipment and storage medium | |
| CN110827236B (en) | Brain tissue layering method, device and computer equipment based on neural network | |
| CN110414428A (en) | A method of generating face character information identification model | |
| KR101955919B1 (en) | Method and program for providing tht region-of-interest in image by deep-learing algorithm | |
| CN104077597B (en) | Image classification method and device | |
| CN110334753A (en) | Video classification methods, device, electronic equipment and storage medium | |
| EP3651061A1 (en) | Method and device for evaluating the result of an automatic parking operation, corresponding device and storage medium | |
| KR102267739B1 (en) | Method for dental diagnostic and computing device for executing the method | |
| CN111695615A (en) | Vehicle damage assessment method and device based on artificial intelligence, electronic equipment and medium | |
| US11257186B2 (en) | Image processing apparatus, image processing method, and computer-readable recording medium | |
| KR20180111242A (en) | Electronic device and method for providing colorable content | |
| KR101961462B1 (en) | Object recognition method and the device thereof | |
| MX2012001664A (en) | Recognition of objects. | |
| CN110197459B (en) | Image stylization generation method and device and electronic equipment | |
| KR20180001259A (en) | Apparatus and Method of Processing for Interior Information |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |