CN111243223A - Automobile anti-scratch monitoring alarm method and system - Google Patents
Automobile anti-scratch monitoring alarm method and system Download PDFInfo
- Publication number
- CN111243223A CN111243223A CN202010121224.3A CN202010121224A CN111243223A CN 111243223 A CN111243223 A CN 111243223A CN 202010121224 A CN202010121224 A CN 202010121224A CN 111243223 A CN111243223 A CN 111243223A
- Authority
- CN
- China
- Prior art keywords
- human body
- image
- automobile
- scratch
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R11/04—Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The invention relates to an automobile anti-scratch monitoring alarm method and system, comprising the following steps: step S1: judging whether the distance between the human body and the vehicle body is smaller than a preset value or not, if so, entering a step S2; otherwise, repeating the step S1; step S2: collecting discontinuous K frames of images around the vehicle body in unit time, and respectively carrying out the following operations on each frame of image: and extracting the human body image after image processing, taking the extracted human body image as the input of a neural network model, and identifying whether the human body image has scraping behaviors or not through the neural network model. If the K recognition results all indicate that scraping behaviors exist, the step S3 is carried out, otherwise, the step S1 is returned; step S3: and performing scraping alarm and returning to the step S2. The invention can effectively identify and alarm the scraping action.
Description
Technical Field
The invention relates to the technical field of car networking, in particular to a method and a system for monitoring and alarming scratch prevention of an automobile.
Background
From the invention and mass production of automobiles, automobiles have come into common families today. Nowadays, an automobile is a common vehicle in daily life, and the quality of life of people is greatly improved. So far, the quantity of automobiles in our country is 2.4 hundred million, however, with the progress of urbanization and the popularization of automobiles, the problem of safety management of automobiles has become the focus of people's attention increasingly. The occurrence of manual and deliberate automobile scraping in the society is frequent, and becomes a great problem which puzzles the majority of automobile owners. Therefore, in order to maintain social stability and guarantee legal property of citizens, it is necessary to design an anti-scratch monitoring alarm system for automobiles.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for monitoring and alarming scratch prevention of an automobile, which can effectively identify and alarm a scratch behavior.
The invention is realized by adopting the following scheme: an automobile anti-scratch monitoring alarm method comprises the following steps:
step S1: judging whether the distance between the human body and the vehicle body is smaller than a preset value or not, if so, entering a step S2; otherwise, repeating the step S1;
step S2: collecting discontinuous K frames of images around the vehicle body in unit time, and respectively carrying out the following operations on each frame of image: and extracting the human body image after image processing, taking the extracted human body image as the input of a neural network model, and identifying whether the human body image has scraping behaviors or not through the neural network model. If the K recognition results all indicate that scraping behaviors exist, the step S3 is carried out, otherwise, the step S1 is returned; k is an integer greater than 1;
step S3: and performing scraping alarm and returning to the step S2.
Further, step S1 is specifically:
the human body infrared sensor and the distance sensor which are arranged on the vehicle body work together, and when the human body infrared sensor detects that a human body is around the vehicle body, and the distance sensor detects that the distance between the human body and the vehicle body is smaller than a preset threshold value, the step S2 is carried out.
Further, in step S2, a human body image around the vehicle body is captured by a CMOS image capturing module provided on the vehicle body.
Further, in step S2, the frame of the neural network model is Fast R-CNN network, and the sample set used in the training phase of the neural network model is made by collecting human behavior image samples and performing label processing on the scratch behavior.
Further, the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 fully-connected layers, and 2 hierarchical layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
Further, step S3 is specifically: and sending the alarm information to the vehicle owner through a wireless communication module, and storing the image judged to have the scraping behavior.
The invention also provides an automobile anti-scratch monitoring alarm system, which comprises a human body infrared sensor, a distance sensor and a CMOS image acquisition module which are arranged outside the automobile body, and a central processing unit, a wireless communication module and a storage module which are arranged inside or outside the automobile body; the central processing unit is electrically connected with each module and each sensor;
when the system is in a dormant state, only the human body infrared sensor and the distance sensor work, and when the human body infrared sensor detects that a human body is around the vehicle body and the distance between the human body and the vehicle body detected by the distance sensor is smaller than a preset threshold value, the system is awakened from the dormant state;
after the system is awakened, the CMOS image acquisition module acquires human body images around discontinuous K frames of vehicle bodies, extracts the human body images after image processing of each frame of image, takes the extracted human body images as input of a neural network model, and identifies whether the human body images have scraping behaviors or not through the neural network model; if the K recognition results indicate that the scraping action exists, the alarm information is transmitted to the vehicle owner through the wireless communication module, and otherwise, the system is restored to the dormant state.
Furthermore, a Fast R-CNN network is adopted in a framework of the neural network model, and a sample set adopted in a training stage of the neural network model is manufactured by collecting human behavior image samples and performing label processing on scraping behaviors; the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 full-link layers and 2 level layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
Further, the vehicle body scraping alarm device further comprises a buzzer module and an LED lamp module which are arranged outside the vehicle body, and when the scraping action is identified, the alarm device gives an alarm through buzzer buzzing and LED lamp flickering.
Furthermore, the human body infrared sensors and the distance sensors are respectively arranged in pairs and are respectively arranged around the periphery of the vehicle body; the CMOS image acquisition module comprises more than one CMOS image acquisition device which is respectively arranged at the top of the vehicle body and the positions of the left rearview mirror and the right rearview mirror.
Compared with the prior art, the invention has the following beneficial effects: the invention monitors the condition around the automobile in real time, rapidly, effectively and accurately identifies harmful behaviors of scraping the automobile by human bodies through detecting the surrounding environment of the automobile, automatically gives an alarm through short messages by a wireless communication technology, collects the evidence of images on site, effectively improves the rate of solving the case of the scraping event, reduces the occurrence of the event to the maximum extent and ensures the property safety of the automobile owner. Meanwhile, the monitoring system is in a dormant state under the condition that no person approaches, and the standby time can be effectively prolonged.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of system hardware configuration according to an embodiment of the present invention.
In the figure, 1 to 4 are human body infrared sensing modules, 5 to 8 are distance sensors, 9 is a main camera, 10 to 11 are auxiliary cameras, 12 to 13 are buzzer modules, 14 to 15 are LED modules, 16 is a GSM wireless communication module, and 17 is a central processing unit.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the embodiment provides an automobile anti-scratch monitoring and alarming method, which includes the following steps:
step S1: judging whether the distance between the human body and the vehicle body is smaller than a preset value or not, if so, entering a step S2; otherwise, repeating the step S1;
step S2: collecting discontinuous K frames of images around the vehicle body in unit time, and respectively carrying out the following operations on each frame of image: and extracting the human body image after image processing, taking the extracted human body image as the input of a neural network model, and identifying whether the human body image has scraping behaviors or not through the neural network model. If the K recognition results all indicate that scraping behaviors exist, the step S3 is carried out, otherwise, the step S1 is returned; k is an integer greater than 1;
step S3: and performing scraping alarm and returning to the step S2.
In this embodiment, step S1 specifically includes:
the human body infrared sensor and the distance sensor which are arranged on the vehicle body work together, and when the human body infrared sensor detects that a human body is around the vehicle body, and the distance sensor detects that the distance between the human body and the vehicle body is smaller than a preset threshold value, the step S2 is carried out.
In the present embodiment, in step S2, a human body image around the vehicle body is captured by a CMOS image capturing module provided on the vehicle body.
Preferably, the image processing includes algorithms such as gray level transformation, gaussian filtering, inter-frame difference, expansion and corrosion, connected domain analysis and the like, and the moving human body image is extracted for human body behavior recognition.
In this embodiment, in step S2, the frame of the neural network model is Fast R-CNN network, and the sample set used in the training phase of the neural network model is made by collecting human behavior image samples and performing label processing on the scratch behavior.
In this embodiment, the Fast R-CNN network includes 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 fully-connected layers, and 2 hierarchical layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
Wherein the training phase of the neural network model comprises the steps of:
a. collecting human behavior images;
b. marking a human behavior image;
c. making a sample data set, and dividing the sample data set into a training sample and a test sample;
d. training a model by adopting a convolutional neural network framework;
e. and training to obtain a human behavior recognition model.
The convolutional neural network framework adopts a Fast R-CNN network, and the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 full-link layers and 2 level layers. Original layer parameters need to be initialized in a training mode, and the full-connected layers for classification are initialized by Gaussian distribution with the mean value of 0 and the standard deviation of 0.01; the fully connected layers for regression were initialized with a gaussian distribution with a mean of 0 and a standard deviation of 0.001, and the offsets were all initialized to 0.
During tuning training, N complete pictures are added firstly, and then R candidate frames selected from the N pictures are added. The R/N candidate frame convolutions of the same image share calculation and memory, and operation cost is reduced. The constitution of the R candidate frames is as follows: a candidate box overlapping a true value by [0.5,1] is defined as a foreground, accounting for 25% of the total; candidate boxes with a maximum value of [0.1,0.5] that overlap with the true value are defined as background and account for 75% of the total.
The method for identifying human body behaviors by the Fast R-CNN network comprises the following steps: inputting a human behavior image to be identified into a FastR-CNN network, and obtaining a characteristic diagram through a plurality of convolution layers and pooling layers; finding a feature frame corresponding to each candidate frame in the feature map by adopting a feature map mapping relation, and pooling each feature frame to a fixed size in an ROI pooling layer; the feature frame is processed by a full connection layer to obtain feature vectors with fixed size, and the feature vectors are processed by respective full connection layers to respectively obtain two output vectors of classification scores and window regression; and performing non-maximum suppression processing on all the results to generate a final human behavior recognition result.
In an embodiment, step S3 specifically includes: and sending the alarm information to the vehicle owner through a wireless communication module, and storing the image judged to have the scraping behavior.
As shown in fig. 2, the embodiment further provides an automobile anti-scratch monitoring alarm system, which includes a human body infrared sensor, a distance sensor, a CMOS image acquisition module, a central processing unit, a wireless communication module and a storage module, wherein the human body infrared sensor, the distance sensor and the CMOS image acquisition module are arranged outside the automobile body, and the central processing unit, the wireless communication module and the storage module are arranged inside or outside the automobile body; the central processing unit is electrically connected with each module and each sensor;
when the system is in a dormant state, only the human body infrared sensor and the distance sensor work, and when the human body infrared sensor detects that a human body is around the vehicle body and the distance between the human body and the vehicle body detected by the distance sensor is smaller than a preset threshold value, the system is awakened from the dormant state;
after the system is awakened, the CMOS image acquisition module acquires human body images around discontinuous K frames of vehicle bodies, extracts the human body images after image processing of each frame of image, takes the extracted human body images as input of a neural network model, and identifies whether the human body images have scraping behaviors or not through the neural network model; if the K recognition results indicate that the scraping action exists, the alarm information is transmitted to the vehicle owner through the wireless communication module, and otherwise, the system is restored to the dormant state.
In this embodiment, a frame of the neural network model adopts a FastR-CNN network, and a sample set adopted in a training stage of the neural network model is manufactured by collecting human behavior image samples and performing label processing on scraping behaviors; the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 full-link layers and 2 level layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
In this embodiment, still include the buzzer module and the LED lamp module of setting in the automobile body outside, when discerning the scraping action, report to the police through buzzer buzzing and LED lamp scintillation.
In this embodiment, the human body infrared sensor and the distance sensor each include a plurality of sensors and are arranged in pairs, and are respectively arranged around the periphery of the vehicle body; the CMOS image acquisition module comprises more than one CMOS image acquisition device which is respectively arranged at the top of the vehicle body and the positions of the left rearview mirror and the right rearview mirror.
Preferably, in the present embodiment, the image processing apparatus further includes a DDR3 memory for storing the image acquired by the image acquisition module and performing image processing with the central processing unit. And the device also comprises an external SD card storage module which is used for storing the identified image with the scraping behavior and is used for obtaining evidence in the future.
Preferably, the central processor can adopt but is not limited to XC7Z015-2CLG485I FPGA. The wireless communication module can adopt a GSM wireless communication module, and when the scraping action is identified, the central processing unit can inform a vehicle owner through a remote short message of the GSM wireless communication module.
Specifically, fig. 2 is a schematic diagram of a specific device layout of the present embodiment. The human body infrared sensing modules 1-4 and the distance sensors 5-8 are arranged around the automobile, so that real-time detection of human bodies around the automobile is realized, and the human body infrared sensing modules are used for standby awakening of the whole system; the main camera 9 is arranged at the top of the automobile, the cradle head control device is arranged at the bottom of the main camera 9, and the cradle head drives the main camera 9 to rotate at a certain speed, so that the main camera 9 can collect image information around the automobile, and when the main camera 9 detects a human body, the central processing unit controls the cradle head to rotate to realize tracking identification of the main camera 9 on the human body; the auxiliary cameras 10-11 are installed at the positions of left and right rearview mirrors of the automobile to assist in recognizing human behaviors. An image acquisition subsystem consisting of the main camera 9 and the auxiliary cameras 10-11 can complete all-around image acquisition of human body behaviors around the automobile. Buzzer 12~13 and LED14~15 are installed at the left and right rear-view mirror position of car, and GSM wireless communication module 16 is installed at the automobile tail portion (also can inside the car), and central processing unit 17 installs inside the driver's cabin, and when the system discerned that there is the scraping action to take place, central processing unit 17 control buzzer 12~13 report to the police, LED14~15 scintillation, and central processing unit 17 notifies the car owner through the 16 long-range SMS of GSM wireless communication module simultaneously.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (10)
1. An automobile anti-scratch monitoring alarm method is characterized by comprising the following steps:
step S1: judging whether the distance between the human body and the vehicle body is smaller than a preset value or not, if so, entering a step S2; otherwise, repeating the step S1;
step S2: collecting discontinuous K frames of images around the vehicle body in unit time, and respectively carrying out the following operations on each frame of image: extracting a human body image after image processing, taking the extracted human body image as the input of a neural network model, and identifying whether the human body image has scraping behaviors or not through the neural network model; if the K recognition results all indicate that scraping behaviors exist, the step S3 is carried out, otherwise, the step S1 is returned; k is an integer greater than 1;
step S3: and performing scraping alarm and returning to the step S2.
2. The automobile anti-scratch monitoring alarm method according to claim 1, wherein the step S1 is specifically:
the human body infrared sensor and the distance sensor which are arranged on the vehicle body work together, and when the human body infrared sensor detects that a human body is around the vehicle body, and the distance sensor detects that the distance between the human body and the vehicle body is smaller than a preset threshold value, the step S2 is carried out.
3. The automobile anti-scratch monitoring alarm method as claimed in claim 1, wherein in step S2, the human body image around the automobile body is collected through a CMOS image collection module disposed on the automobile body.
4. The automobile anti-scratch monitoring and alarming method as claimed in claim 1, wherein in step S2, a Fast R-CNN network is adopted as a framework of a neural network model, and a sample set adopted in a training phase of the neural network model is made by collecting human behavior image samples and labeling scratch behaviors.
5. The automobile anti-scratch monitoring alarm method according to claim 4, wherein the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 fully-connected layers and 2 flat layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
6. The automobile anti-scratch monitoring alarm method according to claim 1, wherein the step S3 is specifically: and sending the alarm information to the vehicle owner through a wireless communication module, and storing the image judged to have the scraping behavior.
7. An automobile anti-scratch monitoring alarm system is characterized by comprising a human body infrared sensor, a distance sensor and a CMOS image acquisition module which are arranged outside an automobile body, and a central processing unit, a wireless communication module and a storage module which are arranged inside or outside the automobile body; the central processing unit is electrically connected with each module and each sensor;
when the system is in a dormant state, only the human body infrared sensor and the distance sensor work, and when the human body infrared sensor detects that a human body is around the vehicle body and the distance between the human body and the vehicle body detected by the distance sensor is smaller than a preset threshold value, the system is awakened from the dormant state;
after the system is awakened, the CMOS image acquisition module acquires human body images around discontinuous K frames of vehicle bodies, extracts the human body images after image processing of each frame of image, takes the extracted human body images as input of a neural network model, and identifies whether the human body images have scraping behaviors or not through the neural network model; if the K recognition results indicate that the scraping action exists, the alarm information is transmitted to the vehicle owner through the wireless communication module, and otherwise, the system is restored to the dormant state.
8. The automobile anti-scratch monitoring and alarming system as recited in claim 7, wherein a Fast R-CNN network is adopted as a framework of the neural network model, and a sample set adopted in a training stage of the neural network model is manufactured by collecting human behavior image samples and performing label processing on scratch behaviors; the Fast R-CNN network comprises 13 convolutional layers, 4 pooling layers, 1 ROI pooling layer, 2 full-link layers and 2 level layers; wherein the 2 fully connected layers output a cls _ score layer for classification and a bbox _ pred layer for adjusting candidate box positions.
9. The automobile scratch prevention monitoring and alarming system as claimed in claim 7, further comprising a buzzer module and an LED lamp module arranged outside the automobile body, wherein when a scratch behavior is recognized, the alarm is given through the buzzer buzzing and the LED lamp flashing.
10. The automobile anti-scratch monitoring alarm system as claimed in claim 7, wherein the human body infrared sensor and the distance sensor are respectively provided in a plurality of pairs and are respectively arranged around the periphery of the automobile body; the CMOS image acquisition module comprises more than one CMOS image acquisition device which is respectively arranged at the top of the vehicle body and the positions of the left rearview mirror and the right rearview mirror.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010121224.3A CN111243223B (en) | 2020-02-26 | 2020-02-26 | Automobile anti-scratch monitoring alarm method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010121224.3A CN111243223B (en) | 2020-02-26 | 2020-02-26 | Automobile anti-scratch monitoring alarm method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111243223A true CN111243223A (en) | 2020-06-05 |
| CN111243223B CN111243223B (en) | 2022-05-10 |
Family
ID=70875053
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010121224.3A Active CN111243223B (en) | 2020-02-26 | 2020-02-26 | Automobile anti-scratch monitoring alarm method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111243223B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005117574A (en) * | 2003-10-10 | 2005-04-28 | Mitsubishi Electric Corp | Image communication type crime prevention system, monitor, multi-point video communication device, and tv telephone terminal |
| KR20100011180A (en) * | 2008-07-24 | 2010-02-03 | 주식회사 현대오토넷 | External image sensing system and control method thereof |
| CN102320279A (en) * | 2011-06-27 | 2012-01-18 | 赖李鑫 | The scraping autoalarm |
| CN102881058A (en) * | 2012-06-19 | 2013-01-16 | 浙江吉利汽车研究院有限公司杭州分公司 | System for pre-warning scraping of automobiles and recording evidences |
| CN203472784U (en) * | 2013-08-19 | 2014-03-12 | 北京汽车股份有限公司 | Pedestrian safety warning device and motor vehicle |
| CN103661270A (en) * | 2012-09-21 | 2014-03-26 | 北京酷信通科技有限公司 | Car panoramic intelligent safeguard system |
| CN203909861U (en) * | 2014-06-10 | 2014-10-29 | 吉林工商学院 | Real-time monitor for vehicle |
| CN105459954A (en) * | 2015-12-16 | 2016-04-06 | 方正宽带网络服务有限公司 | Automobile alarming method and device |
| CN107633568A (en) * | 2017-09-11 | 2018-01-26 | 太仓史瑞克工业设计有限公司 | A kind of Intelligent road patrol method and its system based on teaching unmanned plane |
| CN107985242A (en) * | 2017-11-28 | 2018-05-04 | 成都力鑫科技有限公司 | A kind of automobile rearview mirror for preventing from scraping |
| KR20180052887A (en) * | 2016-11-11 | 2018-05-21 | 황인호 | none |
| CN108275114A (en) * | 2018-02-27 | 2018-07-13 | 苏州清研微视电子科技有限公司 | A kind of Security for fuel tank monitoring system |
| CN208715087U (en) * | 2018-06-26 | 2019-04-09 | 杭州车厘子智能科技有限公司 | Vehicle panoramic viewing system |
| CN109871873A (en) * | 2019-01-17 | 2019-06-11 | 重庆邮电大学 | Millimeter-wave image object detection and recognition method based on Fast R-CNN |
| JP2019089519A (en) * | 2017-11-17 | 2019-06-13 | アルパイン株式会社 | On-vehicle camera device and attachment method of the same |
-
2020
- 2020-02-26 CN CN202010121224.3A patent/CN111243223B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005117574A (en) * | 2003-10-10 | 2005-04-28 | Mitsubishi Electric Corp | Image communication type crime prevention system, monitor, multi-point video communication device, and tv telephone terminal |
| KR20100011180A (en) * | 2008-07-24 | 2010-02-03 | 주식회사 현대오토넷 | External image sensing system and control method thereof |
| CN102320279A (en) * | 2011-06-27 | 2012-01-18 | 赖李鑫 | The scraping autoalarm |
| CN102881058A (en) * | 2012-06-19 | 2013-01-16 | 浙江吉利汽车研究院有限公司杭州分公司 | System for pre-warning scraping of automobiles and recording evidences |
| CN103661270A (en) * | 2012-09-21 | 2014-03-26 | 北京酷信通科技有限公司 | Car panoramic intelligent safeguard system |
| CN203472784U (en) * | 2013-08-19 | 2014-03-12 | 北京汽车股份有限公司 | Pedestrian safety warning device and motor vehicle |
| CN203909861U (en) * | 2014-06-10 | 2014-10-29 | 吉林工商学院 | Real-time monitor for vehicle |
| CN105459954A (en) * | 2015-12-16 | 2016-04-06 | 方正宽带网络服务有限公司 | Automobile alarming method and device |
| KR20180052887A (en) * | 2016-11-11 | 2018-05-21 | 황인호 | none |
| CN107633568A (en) * | 2017-09-11 | 2018-01-26 | 太仓史瑞克工业设计有限公司 | A kind of Intelligent road patrol method and its system based on teaching unmanned plane |
| JP2019089519A (en) * | 2017-11-17 | 2019-06-13 | アルパイン株式会社 | On-vehicle camera device and attachment method of the same |
| CN107985242A (en) * | 2017-11-28 | 2018-05-04 | 成都力鑫科技有限公司 | A kind of automobile rearview mirror for preventing from scraping |
| CN108275114A (en) * | 2018-02-27 | 2018-07-13 | 苏州清研微视电子科技有限公司 | A kind of Security for fuel tank monitoring system |
| CN208715087U (en) * | 2018-06-26 | 2019-04-09 | 杭州车厘子智能科技有限公司 | Vehicle panoramic viewing system |
| CN109871873A (en) * | 2019-01-17 | 2019-06-11 | 重庆邮电大学 | Millimeter-wave image object detection and recognition method based on Fast R-CNN |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111243223B (en) | 2022-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119676B (en) | Driver fatigue detection method based on neural network | |
| CN109686109B (en) | Parking lot safety monitoring management system and method based on artificial intelligence | |
| EP3373243B1 (en) | Object detection method and object detection system | |
| CN109571468B (en) | Security inspection robot and security inspection method | |
| CN110866427A (en) | Vehicle behavior detection method and device | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
| CN109803127A (en) | Urban safety building site monitoring system and method based on big data and technology of Internet of things | |
| KR102174556B1 (en) | Apparatus for monitoring image to control traffic information employing Artificial Intelligence and vehicle number | |
| US11200435B1 (en) | Property video surveillance from a vehicle | |
| CN111599140A (en) | Vehicle rear-row living body monitoring system and method | |
| CN112289031A (en) | Method and device for detecting and alarming abnormal conditions in bus driving process | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| US11482012B2 (en) | Method for driving assistance and mobile device using the method | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| CN112949439A (en) | Method and system for monitoring invasion of personnel in key area of oil tank truck | |
| CN115171260A (en) | Intelligent access control system based on face recognition | |
| KR101337554B1 (en) | Apparatus for trace of wanted criminal and missing person using image recognition and method thereof | |
| CN111243223B (en) | Automobile anti-scratch monitoring alarm method and system | |
| CN111881322B (en) | Target searching method and device, electronic equipment and storage medium | |
| CN114092885A (en) | High-speed service area vehicle protection method and system based on video analysis | |
| CN105206060B (en) | A kind of vehicle type recognition device and its method based on SIFT feature | |
| CN111469765A (en) | Detection system with function of removing vehicle body shadows and method thereof | |
| KR20210149448A (en) | Apparatus for monitoring image employing to detect of vehicle number and cotrolling device | |
| CN108873097B (en) | Safety detection method and device for parking of vehicle carrying plate in unmanned parking garage |
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 |