CN103761832B - A kind of wearable human body anti-collision warning preventer - Google Patents
A kind of wearable human body anti-collision warning preventer Download PDFInfo
- Publication number
- CN103761832B CN103761832B CN201410031151.3A CN201410031151A CN103761832B CN 103761832 B CN103761832 B CN 103761832B CN 201410031151 A CN201410031151 A CN 201410031151A CN 103761832 B CN103761832 B CN 103761832B
- Authority
- CN
- China
- Prior art keywords
- outfan
- input
- air bag
- master controller
- close
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Professional, Industrial, Or Sporting Protective Garments (AREA)
- Alarm Systems (AREA)
Abstract
The present invention relates to wearable human body anti-collision warning preventer, including belt body, multiple air bags are arranged at the middle position interval of belt body, the upper and lower being positioned at air bag in belt body installs multielement bar group, LLL night vision system and gyroscope, alarm unit, multielement bar group, LLL night vision system are connected with the input of master controller by cell controller with the outfan of gyroscope, and the outfan of master controller is connected with the input of air bag, alarm unit respectively by cell controller.The information gathered is contrasted with empirical data set by the present invention by master controller, provide suspicious close to thing number with close to distance, and assign and perform order, carry out audible alarm, and control airbag-releasing, by wireless messages transmitting element, short message set in advance is sent on the mobile phone specified, master controller Tactic selection two grades protection execution action simultaneously.
Description
Technical field
The present invention relates to anti-collision warning guard technology field, especially a kind of wearable human body anti-collision warning preventer.
Background technology
Motion detection is Data Detection about human body itself, and research at present is concentrated mainly on, and athlete's DATA REASONING, falls down detection etc., and Main Means is to realize applying monitoring system by video or Inertial Measurement Unit.Fast and effeciently obtain body motion information, special population can be made to obtain the relief of necessity, but, human body collision detection early warning and protection still one piece of blank towards pedestrian, the walking along the street of child and special population is safely safety in production, ensures socially harmonious necessary links, avoid pedestrian impact, there is important economy and social effect.
Along with the development and application of sensor technology, from the sensor of initial single channel to sensors such as modern optical, electrical, the sound of multichannel, the corresponding data volume obtained also increases accordingly.But, any technology for information acquisition, there is its precision and measure limitation, and signal is inevitably by environmental disturbances, to the multiple sensors from Same Scene, owing to the type of its sensor is different with measuring principle, the existence of scene Self-variation and various interference, there is distortion or malfunctioning in acquired information in varying degrees.
Summary of the invention
It is an object of the invention to provide that one comprises two-stage protection execution action, volume is little, be easy to carry, the wearable human body anti-collision warning preventer with may be worn on.
For achieving the above object, present invention employs techniques below scheme: a kind of wearable human body anti-collision warning preventer, including belt body, multiple air bags are arranged at the middle position interval of belt body, the upper and lower being positioned at air bag in belt body installs multielement bar group, LLL night vision system and gyroscope, alarm unit, multielement bar group, LLL night vision system are connected with the input of master controller by cell controller with the outfan of gyroscope, and the outfan of master controller is connected with the input of air bag, alarm unit respectively by cell controller；Described multielement bar group is made up of sonac, air pressure probe and infrared sensor, described cell controller by range cells, form close to judging unit, unstability judging unit and performance element, described belt body is positioned at installation wireless messages transmitting element above or below air bag；The outfan of sonac is connected with the input of range cells, the outfan of infrared sensor is connected with the input close to judging unit, the outfan of air pressure probe input with range cells, close to judging unit respectively is connected, LLL night vision system is connected with the input of unstability judging unit with the outfan of gyroscope, the outfan of described performance element respectively with air bag, alarm unit, wireless messages transmitting element input be connected；Described alarm unit adopts speaker；The number of described air bag is four to six, and each air bag is positioned on same centrage.
Described range cells, outfan close to judging unit, unstability judging unit are all connected with the input of master controller, and the outfan of master controller is connected with the input of performance element.
As shown from the above technical solution, the present invention is obtained ranging information, infrared sensor and air pressure probe obtained close to basis for estimation by sonac, air pressure probe, obtains unstability information by LLL night vision system and gyroscope；Circulation interaction is there is in range cells with close to judging unit, ranging information and close to information reporting to master controller, by contrasting with empirical data set, the in advance planning of design and decision making algorithm are suspicious close to thing number with close to distance by providing, and assign and perform order, control airbag-releasing, and carry out audible alarm, by wireless messages transmitting element, short message set in advance is sent on the mobile phone specified simultaneously, master controller judges status according to sensing data, and assigns corresponding protection execution action.The present invention adopts waistband designs, in that context it may be convenient to being worn on human body, volume is little, it is simple to carry.
Accompanying drawing explanation
Fig. 1 is that the present invention is worn on human body, the wearing schematic diagram that air bag is not switched on；
Fig. 2, the 3 respectively present invention structural representation；
Fig. 4 is the view of airbag-releasing in Fig. 1；
Fig. 5 is the collection of the present invention and performs block diagram；
Fig. 6 is the overall structure block diagram of the present invention；
Fig. 7 is the workflow diagram of the present invention.
Detailed description of the invention
nullA kind of wearable human body anti-collision warning preventer，Including belt body 1，Multiple air bags 2 are arranged at the middle position interval of belt body 1，Belt body 1 is positioned at the upper of air bag 2、Multielement bar group 3 mounted below、LLL night vision system and gyroscope 4、Alarm unit 5，Multielement bar group 3、LLL night vision system is connected by the input of cell controller 7 with master controller 8 with the outfan of gyroscope 4，The outfan of master controller 8 by cell controller 7 respectively with air bag 2、The input of alarm unit 5 is connected，As shown in Figure 1，By multielement bar group 3 to be similar to the wearable arrangement of belt，It is placed on human body，Separated by a distance，Place a kind of sensor，The coverage making various sensor and air bag 2 can expand 360 degree to，Realize omnibearing monitoring and protection.
As shown in Figure 2,3, 4, the number of described air bag 2 is four to six, and each air bag 2 is positioned on same centrage.Four protective air-bag each independent Hu Bu UNICOMs, are spacedly distributed in belt body 1.Air bag 2 is arranged in the top of sensor; human body belt place; when air bag 2 is opened time; the trunk that can protect human body avoids collision; also using alarm unit and wireless messages transmitting element, when air bag 2 is opened soon time, alarm unit begins to work simultaneously; meanwhile, wireless messages transmitting element sends information to predetermined mobile phone.
Such as Fig. 5, shown in 6, pass through sonac, air pressure probe obtains ranging information, obtain close to basis for estimation by infrared sensor and air pressure probe, unstability information is obtained by LLL night vision system and gyroscope 4, range cells and between judging unit exist circulation interaction, ranging information and close to information reporting to master controller 8, by contrasting with empirical data set, the in advance planning of design and decision making algorithm are suspicious close to thing number with close to distance by providing, and assign and perform intention, it is intended to send to performance element specifically perform order according to current state and execution, control air bag 2, alarm unit 5 and wireless messages transmitting element 6 action.Multielement bar group 3 is together with human body signal of intent, as the input of multielement bar data fusion, by multielement bar data fusion, state is differentiated, then produces acoustics early warning, and airbag restraint performs and be wirelessly transferred two-stage protection execution action.
As shown in Figure 6, described multielement bar group 3 is made up of sonac, air pressure probe and infrared sensor, described cell controller 7 by range cells, form close to judging unit, unstability judging unit and performance element, described belt body 1 is positioned at installation wireless messages transmitting element 6 above or below air bag 2；The outfan of sonac is connected with the input of range cells, the outfan of infrared sensor is connected with the input close to judging unit, the outfan of air pressure probe respectively with range cells, input close to judging unit is connected, LLL night vision system is connected with the input of unstability judging unit with the outfan of gyroscope 4, the outfan of described performance element respectively with air bag 2, alarm unit 5, the input of wireless messages transmitting element 6 is connected, described range cells, close to judging unit, the outfan of unstability judging unit is all connected with the input of master controller 8, the outfan of master controller 8 is connected with the input of performance element.Described alarm unit 5 adopts speaker, audio alert " to please note and dodge " and with specific identifier sound.This preventer can be divided into three layers: ground floor is sensing and right of execution, the primary responsibility sensing to real time data, and carries out the execution of three big tasks according to condition discrimination result；The second layer is cell controller 7；Third layer is master controller 8.
As it is shown in fig. 7, during this device busy, its specific works flow process is as follows:
The first step, power-up initializing；
Second step, the information that multielement bar group 3, LLL night vision system and gyroscope 4 are exported by master controller 8, acquiescence is in normal operating condition；
3rd step, the data sequence that sensor acquisition is arrived by master controller 8 extracts characteristic quantity, and judges whether namely to will appear from collision situation according to support vector machines, if the determination result is YES, then starts alarm unit 5 and reports to the police, continue collection information；Otherwise, second step is returned；
4th step, after alarm unit 5 is reported to the police, master controller 8 judges whether obvious collision status occur, if the determination result is YES, then opens air bag 2, and starts wireless messages transmitting element 6 and be wirelessly transferred；If judged result is no, then determine whether false-alarm.When false-alarm is judged, if the determination result is YES, then acquiescence is in normal operating condition, otherwise, it is determined whether namely will appear from collision situation.
In other words, when meeting empirical function close to information and ranging information or exceed reservation threshold value, system enters state 2, when unstability judges to set up, and abnormal close to after information and abnormal ranging information keeps a period of time, system enters state 3.Wherein, performing one is acoustics alarm；Perform two for airbag-releasing and to be wirelessly transferred；State one is up；State two is namely to will appear from the alert status of collision situation；State three is obvious collision status occurred.
Judge whether namely to will appear from the determination methods of collision situation particularly as follows:
(1) each sensor characteristics of multielement bar group is extracted, including temporal signatures, frequency domain character and time trend feature
A, the extraction of temporal signatures
Temporal signatures is the Time-domain Statistics characteristic obtained according to various kinds of sensors output waveform, adopts following index:
Absolute mean:
Root-mean-square value:
The degree of bias:
Kurtosis:
In formula, xiFor the discrete-time series of sensor signal, N is sequence samples number, and μ is average, and σ is variance；
B, the extraction of frequency domain character
Various kinds of sensors output sequence has each typical frequecy characteristic, it is carried out spectrum analysis, obtains amplitude-frequency sequence, extracts the range value in several particular frequencies in amplitude-frequency sequence；
C, the extraction of time trend feature
The state characteristic signal that the primary signal recorded by sensor is determined that superposes with random disturbances.The signal sequence being provided with original measurement is { xt, t=1,2 ..., N}, then this sequence can be expressed as a trend term and random entry and:
xt=dt+ξt
In formula, dtFor trend term, it is that a certain of time t determines function；ξtFor random entry, it reflects the random component of signal；
When extracting trend feature, it is necessary first to time series is carried out de-noising, remove random entry, retain trend term, then recycle various trend analysis and extract feature；
Adopt Mann-Kendall inspection that sensor is detected sequence variation trend to extract, for time series { xt, t=1,2 ..., the null hypothesis H of N}Mann-Kendall inspection0Independent with the time for stochastic variable, counting statistics amount T
In formula,At null hypothesis H0Under, if time series is absent from trend, when N is relatively larger, then the approximate Normal Distribution of statistic T, and have following two formulas to set up:
As n > 10 time, calculate statistic of test Z
If sequence calculates Z Sequence Trend characteristic quantity sometime；
(2) basic model of the SVM of limit risk classification is set up according to characteristic quantity
If namely the characteristic set obtained from sensor input be will appear from collision by two classes and is normally formed, if feature x [i] correspondence belongs to the 1st class, then y [i]=1, if feature x [i] correspondence belongs to the 2nd class, then y [i]=-1, so there is training sample set { x [i], y [i] }i=1,2,3 ..., n, seeks optimal classification surface wx-b=0, when for linearly inseparable, with core inner product K (x [i], x [j]), is mapped to, by kernel function, the inner product that in higher dimensional space, correspondence is vectorial, replaces x [i] x [j]；
Svm classifier training step is as follows:
A, training set is chosen as: T=(x1, y1), (x1, x2) ..., (xl, yl)}∈(Rn×Y)l, wherein, xi∈RnIt is a collection of marked safe or dangerous sensing data characteristic quantity corresponding amount, yi∈ Y={-1,1}, i=1 ..., l；yi=+1 represents it is be about to collide, yi=-1 numerical identity representing normal travel condition；In the i correspondence i-th moment, there is the characteristic quantity that the sensing sequence of the fixed number of continuous renewal obtains in each moment, and there is decision content y in each momentiProduce, be interval between i-th and i+1 moment；L represents element number in training set, by l training sample, obtains support vector machines, then passes through SVM and does decision-making judgement；
B, selects suitable punishment parameter C > 0 and kernel function K (x, x'), its Kernel Function can select several typical case kernel function in any one；
C, constructs and solves convex quadratic programming problem:MeetMust solve
D, calculates b*: choose the α being positioned in open interval (0, C)*ComponentCalculate
E, structure decision function F (x)=sgn (g (x)), wherein
After training completes, bring current sensor data characteristic quantity into decision function, judge that obtaining present case is dangerous or safe judgement according to decision function result of calculation, if decision function be on the occasion of, then represent safety, if decision function is negative value, then it represents that namely will appear from collision.
Judge whether the method that obvious collision status occurs particularly as follows: obtain temporal signatures and frequency domain character according to sensor time sequence, obtained decision-making by temporal signatures and frequency domain character through support vector machines again to judge, the wherein time series of Main Basis LLL night vision system and gyroscope；
(1) the time series feature of LLL night vision system and gyroscope is extracted, including temporal signatures and frequency domain character
A, the extraction of temporal signatures
Temporal signatures is the Time-domain Statistics characteristic obtained according to various kinds of sensors output waveform, adopts following index:
Absolute mean:
Root-mean-square value:
The degree of bias:
In formula, xiFor the discrete-time series of sensor signal, N is sequence samples number, and μ is average, and σ is variance；
B, the extraction of frequency domain character
Various kinds of sensors output sequence has each typical frequecy characteristic, and it is carried out spectrum analysis, obtains frequency domain distribution and corresponding amplitude；
(2) basic model of the SVM of limit risk classification is set up according to characteristic quantity
If namely the characteristic set obtained from sensor input be will appear from colliding and occur that substantially collision forms by two classes, if feature x [i] correspondence belongs to the 1st class, then y [i]=1, if feature x [i] correspondence belongs to the 2nd class, then y [i]=-1, so there is training sample set { x [i], y [i] }i=1,2,3 ..., n, seeks optimal classification surface wx-b=0, when for linearly inseparable, with core inner product K (x [i], x [j]), is mapped to, by kernel function, the inner product that in higher dimensional space, correspondence is vectorial, replaces x [i] x [j]；
Svm classifier training step is as follows:
A, training set is chosen as: T=(x1, y1), (x1, x2) ..., (xl, yl)}∈(Rn×Y)l, wherein, xi∈RnIt is a collection of marked safe or dangerous sensing data characteristic quantity corresponding amount, yi∈ Y={-1,1}, i=1 ..., l；yi=+1 represents it is that substantially collision, y occuri=-1 represents the numerical identity being about to collide；In the i correspondence i-th moment, there is the characteristic quantity that the sensing sequence of the fixed number of continuous renewal obtains in each moment, and there is decision content y in each momentiProduce, be interval between i-th and i+1 moment；L represents element number in training set, by l training sample, obtains support vector machines, then passes through SVM and does decision-making judgement；
B, selects suitable punishment parameter C > 0 and kernel function K (x, x'), its Kernel Function can select several typical case kernel function in any one；
C, constructs and solves convex quadratic programming problem:MeetMust solve
D, calculates b*: choose the α being positioned in open interval (0, C)*ComponentCalculate
E, structure decision function F (x)=sgn (g (x)), wherein
After training completes, bring current sensor data characteristic quantity into decision function, judge that obtaining present case is dangerous or safe judgement according to decision function result of calculation, if decision function be on the occasion of, then represent and namely will appear from collision, if decision function is negative value, then it represents that substantially collision occurs
In a word, the present invention is obtained ranging information, infrared sensor and air pressure probe obtained close to basis for estimation by sonac, air pressure probe, obtains unstability information by LLL night vision system and gyroscope 4；Circulation interaction is there is in range cells with close to judging unit, ranging information and close to information reporting to master controller 8, by contrasting with empirical data set, the in advance planning of design and decision making algorithm are suspicious close to thing number with close to distance by providing, and assign and perform order, control air bag 2 to open, and carry out audible alarm, being sent on the mobile phone specified by wireless messages transmitting element by short message set in advance, two kinds of protection execution actions are judged decision-making by master controller according to field condition simultaneously.The present invention adopts waistband designs, in that context it may be convenient to being worn on human body, volume is little, it is simple to carry.
Claims (2)
1. a wearable human body anti-collision warning preventer, it is characterized in that: include belt body, multiple air bags are arranged at the middle position interval of belt body, the upper and lower being positioned at air bag in belt body installs multielement bar group, LLL night vision system and gyroscope, alarm unit, multielement bar group, LLL night vision system are connected with the input of master controller by cell controller with the outfan of gyroscope, and the outfan of master controller is connected with the input of air bag, alarm unit respectively by cell controller；Described multielement bar group is made up of sonac, air pressure probe and infrared sensor, described cell controller by range cells, form close to judging unit, unstability judging unit and performance element, described belt body is positioned at installation wireless messages transmitting element above or below air bag；The outfan of sonac is connected with the input of range cells, the outfan of infrared sensor is connected with the input close to judging unit, the outfan of air pressure probe input with range cells, close to judging unit respectively is connected, LLL night vision system is connected with the input of unstability judging unit with the outfan of gyroscope, the outfan of described performance element respectively with air bag, alarm unit, wireless messages transmitting element input be connected；Described alarm unit adopts speaker；The number of described air bag is four to six, and each air bag is positioned on same centrage.
2. wearable human body anti-collision warning preventer according to claim 1, it is characterized in that: described range cells, outfan close to judging unit, unstability judging unit are all connected with the input of master controller, and the outfan of master controller is connected with the input of performance element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410031151.3A CN103761832B (en) | 2014-01-22 | 2014-01-22 | A kind of wearable human body anti-collision warning preventer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410031151.3A CN103761832B (en) | 2014-01-22 | 2014-01-22 | A kind of wearable human body anti-collision warning preventer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103761832A CN103761832A (en) | 2014-04-30 |
| CN103761832B true CN103761832B (en) | 2016-07-06 |
Family
ID=50529063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410031151.3A Active CN103761832B (en) | 2014-01-22 | 2014-01-22 | A kind of wearable human body anti-collision warning preventer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103761832B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105580059B (en) * | 2014-09-03 | 2019-07-23 | 华为技术有限公司 | Wearable device, the method and device for ensureing user security |
| CN104269025B (en) * | 2014-09-29 | 2016-09-28 | 南京信息工程大学 | Wearable single node feature and the position choosing method of monitoring is fallen down towards open air |
| CN104504855B (en) * | 2015-01-13 | 2017-11-24 | 广东乐源数字技术有限公司 | A kind of intelligent waistband and intelligent tumble emergency warning system |
| CN106805346A (en) * | 2017-01-10 | 2017-06-09 | 南京信息工程大学 | A kind of crash helmet |
| CN108256418B (en) * | 2017-12-01 | 2022-01-21 | 轩辕智驾科技（深圳）有限公司 | Pedestrian early warning method and system based on infrared imaging |
| CN110823337B (en) * | 2018-08-10 | 2021-05-18 | 河南工业大学 | Granary state detection method and system based on bottom surface single-ring pressure sensor |
| CN111289984A (en) * | 2020-03-03 | 2020-06-16 | 陕西理工大学 | Infant behavior monitoring device and method |
| CN111416293B (en) * | 2020-04-27 | 2022-02-01 | 新疆紫金锌业有限公司 | Electric power inspection electric shock protection device |
| CN112085912A (en) * | 2020-09-20 | 2020-12-15 | 济宁山云宇内机电科技有限公司 | Human body distance monitoring prompter and working method |
| CN113345203A (en) * | 2021-06-07 | 2021-09-03 | 成都大学 | Wearable anti-falling environment danger identification alarm device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6433691B1 (en) * | 2001-02-27 | 2002-08-13 | The United States Of America As Represented By The Secretary Of The Navy | Personal collision warning and protection system |
| CN102117533A (en) * | 2011-03-11 | 2011-07-06 | 北京航空航天大学 | Human falling detection protection and alarming device |
| CN202650197U (en) * | 2012-07-09 | 2013-01-02 | 台州学院 | Fall prevention apparatus |
| CN103040547A (en) * | 2012-12-24 | 2013-04-17 | 中国科学院深圳先进技术研究院 | Portable fall protector |
| CN203894905U (en) * | 2014-01-22 | 2014-10-22 | 安徽科赫信息技术有限公司 | Wearable human body collision early warning protection device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005237576A (en) * | 2004-02-25 | 2005-09-08 | Kansai Electric Power Co Inc:The | Tumble judgment device |
-
2014
- 2014-01-22 CN CN201410031151.3A patent/CN103761832B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6433691B1 (en) * | 2001-02-27 | 2002-08-13 | The United States Of America As Represented By The Secretary Of The Navy | Personal collision warning and protection system |
| CN102117533A (en) * | 2011-03-11 | 2011-07-06 | 北京航空航天大学 | Human falling detection protection and alarming device |
| CN202650197U (en) * | 2012-07-09 | 2013-01-02 | 台州学院 | Fall prevention apparatus |
| CN103040547A (en) * | 2012-12-24 | 2013-04-17 | 中国科学院深圳先进技术研究院 | Portable fall protector |
| CN203894905U (en) * | 2014-01-22 | 2014-10-22 | 安徽科赫信息技术有限公司 | Wearable human body collision early warning protection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103761832A (en) | 2014-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103761832B (en) | A kind of wearable human body anti-collision warning preventer | |
| US10640131B2 (en) | Aberrant driver classification and reporting | |
| Lee et al. | Development of an enhanced threshold-based fall detection system using smartphones with built-in accelerometers | |
| KR101069001B1 (en) | Apparatus and method for detecting falldown | |
| CN105427518B (en) | A kind of dangerous decision system of digitization and method | |
| CN106846729A (en) | A kind of fall detection method and system based on convolutional neural networks | |
| KR102478383B1 (en) | System and the method for fall-down prediction | |
| CN106515725A (en) | Method and terminal for preventing vehicle collision | |
| Xu et al. | ER: Early recognition of inattentive driving leveraging audio devices on smartphones | |
| CN107320115B (en) | Self-adaptive mental fatigue assessment device and method | |
| WO2019185045A1 (en) | Transport device collision detection, alarm, and guard method | |
| JP7256086B2 (en) | Method, device, equipment and storage medium for identifying passenger status in unmanned vehicle | |
| Alluhaibi et al. | Driver behavior detection techniques: A survey | |
| US11042768B1 (en) | Deep learning-based object recognition system and method using PIR sensor | |
| Sultan Mahmud et al. | Smart fire detection system with early notifications using machine learning | |
| CN105139869A (en) | Baby crying detection method based on interval difference features | |
| CN110901385A (en) | Active speed limiting method based on fatigue state of driver | |
| CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
| EP2313814B1 (en) | A method, device, and computer program product for event detection while preventing misclassification | |
| CN203894905U (en) | Wearable human body collision early warning protection device | |
| CN107539038B (en) | Vehicle tire pressure state monitoring method and device | |
| Suman et al. | An approach to detect the accident in VANETs using acoustic signal | |
| KR20170004270A (en) | Apparatus and system for detecting falldown | |
| KR102216272B1 (en) | System for collecting and providing road traffic danger information using smart phone and cloud server, and method for the same | |
| CN114758326A (en) | Real-time traffic post working behavior state detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |