CN107886711A - A kind of pedestrian running red light caution system and implementation method - Google Patents
A kind of pedestrian running red light caution system and implementation method Download PDFInfo
- Publication number
- CN107886711A CN107886711A CN201711140202.6A CN201711140202A CN107886711A CN 107886711 A CN107886711 A CN 107886711A CN 201711140202 A CN201711140202 A CN 201711140202A CN 107886711 A CN107886711 A CN 107886711A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- server
- pedestrian
- processor
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/005—Traffic control systems for road vehicles including pedestrian guidance indicator
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of pedestrian running red light caution system and implementation method, the system comprises at least following device:Traffic grade module, for obtaining the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color;The camera module, for the data information acquisition view data according to traffic light signals rule or pedestrian crosswalk signal lamp light color;The processor, for obtaining described image data and server will be uploaded to;The server, for carrying out human face detection and recognition and data comparison according to described image data to obtain violation results;The crossing display screen, for showing the violation results.The present invention by view data by carrying out recognition of face to obtain the process that the violation results of pedestrian are shown again, pedestrian can not only be warned to reduce the behavior that pedestrian ignores traffic rules and made a dash across the red light, the working strength of law enfrocement official can be also reduced to a certain extent, so as to ensure road traffic order and traffic safety, road efficiency is improved.
Description
Technical field
The present invention relates to intelligent traffic safety technical field, more particularly to a kind of pedestrian running red light caution system and realization side
Method.
Background technology
With the fast development of Chinese Urbanization, urban traffic safety problem is increasingly subject to the attention of people, particularly people
Intensive the intensive traffic section is flowed, the phenomenon of pedestrian running red light emerges in an endless stream, and has thereby resulted in the loss of some life and property.
Because management and control is weak, and also no related measure rushes the behavior of crossing for pedestrian at present, big except putting into
The law enfrocement official of amount is manually supervised at the scene, is prevented and is educated if finding pedestrian running red light behavior, but the management
Mode need to put into substantial amounts of manpower, and control and monitoring and the efficiency of management be not high, can not effectively contain that the illegal of pedestrian makes a dash across the red light
Behavior.
Therefore, by information-based, intelligent means come realize to the automatic detection of pedestrian running red light behavior and publicity with up to
The purpose taken care to warning pedestrian.The work that law enfrocement official can be significantly reduced using unattended traffic management modes is strong
Degree, ensure road traffic order and traffic safety, improve road efficiency.
The content of the invention
The shortcomings that present invention is directed to existing way, proposes a kind of pedestrian running red light caution system and implementation method, to solve
Certainly above mentioned problem existing for prior art.
According to an aspect of the invention, there is provided a kind of pedestrian running red light caution system, including at least processor, shooting
Head mould group, crossing display screen, traffic grade module and server:
The traffic grade module, for obtaining the data letter of traffic light signals rule or pedestrian crosswalk signal lamp light color
Breath;
The camera module, the data information acquisition picture number for the acquisition according to the traffic grade module
According to;
The processor, for obtaining described image data and view data being uploaded into server;
The server, for carrying out human face detection and recognition and data comparison according to described image data to obtain in violation of rules and regulations
As a result;
The crossing display screen, for showing the violation results;
The processor by embedded Control node respectively with camera module, crossing display screen and traffic grade mould
Block is connected to carry out data transmission, and the processor is by network communicating system connection server to carry out data transmission.
Further, the camera module, it is to work as traffic in the data message of the acquisition of the traffic grade module
When modulating signal rule is the data message that non-pedestrian passes through or the data message that pedestrian crosswalk signal lamp is red status, adopt
Collect view data.
Further, the pedestrian crosswalk signal lamp is obtained for the data message of red status by color sensor.
Further, the server is long-range deep learning calculation server.
Further, the system also includes database, and the database is used to store history violation results.
Further, described violation results comprise at least facial image and violation number.
Preferably, the server operation Ubuntu operating systems;The database is LFW and/or YFW human face datas
Storehouse.
Further, the server coordinates Opencv Face datections algorithm and Caffe+GPU depth frameworks, and is carried in
Human face recognition model of the VggNet depth convolutional neural networks that LFW and/or YFW face databases train as system.
Preferably, the processor by network communicating system connection server to carry out data transmission referring to:The place
Device is managed by interchanger log equipment connection server to carry out data transmission.
The implementation method of the system, including at least following steps:
S101:Start the system, detecting system whether normal operation;
S102:If the system normal operation, traffic grade module obtains traffic light signals rule or crossing letter
The data message of signal lamp light color, and the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color is uploaded to
Processor;
S103:The data message of the processor analysis traffic light signals rule or pedestrian crosswalk signal lamp light color, works as friendship
When logical modulating signal rule is the data message that non-pedestrian passes through or the data message that pedestrian crosswalk signal lamp is red status, instruction
Camera module gathers view data;
S104:The camera module gathers view data, and described image data are sent into the processor;
S105:Described image data are sent to server by the processor by interchanger log equipment;
S106:The server carries out human face detection and recognition and data comparison to obtain in violation of rules and regulations according to described image data
As a result, and by the violation results it is sent to processor;
S107:Violation results are sent to display screen crossing by the processor, and the crossing display screen shows violation results.
Compared with prior art, the beneficial effects of the invention are as follows:
1st, the present invention gathers view data by camera module, and server carries out recognition of face further according to the view data
To obtain violation results, crossing display screen shows the process of the violation results again, can not only warn pedestrian to reduce row
People ignores the behavior that traffic rules are made a dash across the red light, and the working strength of law enfrocement official can be also reduced to a certain extent, so as to ensure
Road traffic order and traffic safety, improve road efficiency;
2nd, present system synthesis is using Ubuntu operating systems, LFW and YFW face databases, Opencv Face datections
Algorithm, Caffe+GPU depth framework and VggNet depth convolutional neural networks, can quick obtaining be true, complete data.
The additional aspect of the present invention and advantage will be set forth in part in the description, and these will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein:
Fig. 1 is a kind of pedestrian running red light caution system structure chart of the embodiment of the present invention;
Fig. 2 is a kind of implementation method flow chart of pedestrian running red light caution system of one embodiment of the invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described.
In some flows of description in description and claims of this specification and above-mentioned accompanying drawing, contain according to
Particular order occur multiple operations, but it should be clearly understood that these operation can not occur herein according to it is suitable
Sequence is performed or performed parallel, the sequence number such as 101,102 etc. of operation, is only used for distinguishing each different operation, sequence number
Any execution sequence is not represented for itself.In addition, these flows can include more or less operations, and these operations can
To perform or perform parallel in order.It should be noted that the description such as " first " herein, " second ", is to be used to distinguish not
Message together, equipment, module etc., do not represent sequencing, it is different types also not limit " first " and " second ".
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only the embodiment of a part of example of the present invention, implementation rather than whole.It is based on
Embodiment in the present invention, the every other implementation that those skilled in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the general understanding identical meaning with the those of ordinary skill in art of the present invention.Should also
Understand, those terms defined in such as general dictionary, it should be understood that have with the context of prior art
The consistent meaning of meaning, and unless by specific definitions as here, idealization or the implication of overly formal otherwise will not be used
To explain.
Embodiment
As shown in Figure 1, there is provided a kind of pedestrian running red light caution system of one embodiment of the invention, including at least processing
Device, camera module, crossing display screen, traffic grade module and server:
Traffic grade module, for obtaining the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color;
Camera module, the data information acquisition view data for the acquisition according to the traffic grade module;
Specifically, camera module, is when traffic light signals rule in the data message of the acquisition of traffic grade module
When the data message or pedestrian crosswalk signal lamp passed through for non-pedestrian is the data message of red status, picture number is gathered
According to;
Specifically, at the traffic lights place of display color sensor can be set to obtain traffic lights color data, the color sensor
The sensor of solid color can be arranged to only detect according to demand;Thus pedestrian crosswalk signal lamp is the data message of red status
Obtained by color sensor.
Processor, for obtaining view data and view data being uploaded into server;
Server, for carrying out human face detection and recognition and data comparison according to view data to obtain violation results;Clothes
Business device is long-range deep learning calculation server;Server runs Ubuntu operating systems;
Ubuntu (friend side open up, it is excellent as figure, Wu Bantu) be one based on desktop application increase income GNU/Linux operation system
System, Ubuntu is to be based on Debian GNU/Linux, x86, amd64 (i.e. x64) and ppc frameworks is supported, by the specialty to globalize
Development teams (Canonical Ltd) are made.
Crossing display screen, for showing violation results.
Processor is connected with camera module, crossing display screen and traffic grade module respectively by embedded Control node
Connect to carry out data transmission, processor is by network communicating system connection server to carry out data transmission.
Preferably, processor by interchanger log equipment connection server to carry out data transmission.
Certainly, processor by network communicating system connection server to carry out data transmission can also be:Processor is extremely
It is few by the mobile communication based on 3GPP, LTE, WIMAX, based on TCP/IP, udp protocol computer network communication and be based on
Bluetooth, the low coverage wireless transmission method connection server of Infrared Transmission standard are to carry out data transmission.
The system also includes database, and database is LFW and/or YFW face databases.Database is disobeyed for storing history
Advise result;Violation results comprise at least facial image and violation number;
Facial image database has LFW (Labelled Faces in the Wild) and YFW (Youtube Faces in the
Wild).Present experimental data set substantially derives from LFW, and the precision of current image recognition of face has reached
99%.Illustrated below by taking LFW as an example:
LFW:After carrying out recognition of face network training by caffe, caffemodel is obtained.Generally everybody is in LFW faces
Precision test is carried out to the model on data set.Verification process is combed below:
(1) in original LFW data sets, intercept facial image and preserve.(such as:Can use increase income Face datection pair
Face crop is come out and preserved by neat seetaface, it is proposed that adds a suffix name facial image with original image title);
(2) by python, matlab, or C++, build network structure when training and load caffemodel;
(3) face of interception is sent into network, each face can be obtained before network to the final result of computing, typically
For a N-dimensional vector, and preserve, it is proposed that a suffix name is added with original image title;
(4) LFW provides 6000 pairs of face verification txt files, lfw_pairs.txt, wherein the 1st 300 people are same
Two personal width facial images;2nd 300 people are the facial images of two different peoples.According to the list, in the number that (3) preserve
In, N-dimensional characteristic vector corresponding to contrast face is found;
(5) similarity of two faces is calculated by cosine distance/Euclidean distances.It is saved in respectively respectively with face and different face
In self-corresponding score vector;
(6) with face score vector according to sorting from small to large, different face vector according to sorting from big to small;
(7) FAR (false acceptance rate), according to the unit of a ten thousandth, using the vector after sequence, asks FRR (wrong from 0~1
False rejection rate) or TPR (true positive ratio);
(8) ROC curve can be drawn according to 7.
Such as:Threshold value is defined below:
(1) test face for threshold value and is verified into intensive reading to being divided into 10 groups.
(2) a recognition of face similarity threshold scope oneself is drafted, is confirmed one by one in a certain threshold value in the range of this
Under, wherein 1 group of data statistics is chosen with face misjudgment and the number of different face decision error;
(3) that minimum threshold value of number of errors is selected, with 9 groups of residue, judges accuracy of identification;
(4) the step of above-mentioned threshold value determines (2) and (3) are performed 10 times, and the precision that each (3) obtain is added up and asked
It is average, obtain final judgement precision.
Threshold value determines to be replaced with following manner:
A recognition of face similarity threshold scope oneself is drafted, is confirmed one by one under a certain threshold value in the range of this,
For all faces to counting with face misjudgment and the number of different face decision error, so as to which judgement precision be calculated.
YFW:
Server coordinates Opencv Face datections algorithm and Caffe+GPU depth frameworks, and is carried in LFW, YFW face number
Human face recognition model of the VggNet depth convolutional neural networks trained according to storehouse as system.
Opencv:OpenCV is a cross-platform computer vision library based on BSD licenses (increasing income) distribution, can be run
In Linux, Windows, Android and Mac OS operating systems.Its lightweight and efficiently --- by a series of C functions and
A small amount of C++ class is formed, while provides the interface of the language such as Python, Ruby, MATLAB, realizes image procossing and computer
Many general-purpose algorithms of visual aspects.
OpenCV is write with C Plus Plus, and its primary interface is also C Plus Plus, but still remains substantial amounts of C language
Interface.Also there are substantial amounts of Python, Java and MATLAB/OCTAVE (version 2 .5) interface in the storehouse.The API of these language
Interface function can be obtained by online document.
OpenCV is directed to the real-time application of real world, by the C code of optimization write it is performed speed band come
Considerable lifting, and can be by buying Intel IPP high-performance multimedia function libraries (Integrated
Performance Primitives) obtain faster processing speed.
Caffe+GPU:Caffe it is relative with the advantages of other DL frameworks and shortcoming:
Advantage is that speed is fast.Google Protocol Buffer data standards are that Caffe improves efficiency;And renewal
It hurry up, in constantly improving, later function also can be more and more.
Below from introducing caffe following aspects:
Caffe code levels:Blob:Be the data structure on basis, passed for preserving the parameter learnt and network
The class of data is produced during defeated;
Layer:It is the elementary cell of network, has thus derived various layer classes.The people for changing this part mainly studies
Feature representation direction;
Net:It is building for network, Layer is derived into a layer class is combined into network.
GPU:Graphics processor, full name Graphics Processing Unit, also known as show core, vision processor,
Display chip is one kind specially in PC, work station, game machine and some mobile device (such as tablet personal computers, smart mobile phone
Deng) microprocessor of epigraph operation.Purposes is that the display information required for computer system is carried out into conversion driving, and
Line scan signals are provided to display, control the correct display of display, are connect display and PC mainboard important
Element, and one of the visual plant of " human-computer dialogue ".
Therefore, Caffe+GPU combination can efficiently utilize GPU memory bandwidth and unnecessary parallel advantage, from
And can efficiently processing array multiplication and convolution, to obtain faster result.
VggNet is proposed by Oxonian visual geometric group (Visual Geometry Group), is ILSVRC-2014
Middle location tasks first place and classification task second place.Its outstanding contributions is to prove the convolution (3*3) using very little, increase net
Network depth can effective lift scheme effect, and VGGNet has good generalization ability to other data sets.Nowadays, roll up
Product neutral net has become the common tool of computer vision field.
During training, input is the RGB image that size is 224*224, and * pretreatments are in each pixel only in training set
Subtract RGB average.
Image is handled by a series of convolutional layers, and very small receptive field (receptive has been used in convolutional layer
field):3*3, or even some places use 1*1 convolution, and this 1*1 convolution can be seen as to input channel
The linear transformation of (input channel).
Convolution step-length (stride) is arranged to 1 pixel, and the filling (padding) of 3*3 convolutional layers is arranged to 1 pixel.
Pond layer uses max-pooling, is of five storeys altogether, and after a part of convolutional layer, max-pooling window is 2*2, and step-length is
2。
A series of convolutional layers followed by full articulamentum (fully-connected layers).The full articulamentum of the first two is equal
There are 4096 passages.3rd full articulamentum has 1000 passages, for classifying.The full articulamentum configuration of all-network is identical.
All hidden layers all use ReLu.VGGNet is standardized (LRN) without using local acknowledgement, and this standardization can not
The improving performance on ILSVRC data sets, but cause more memory consumptions and calculate the time.
In summary, the system is a kind of embedded system, then controls other assemblies by embedded node, and foundation is worked as
Preceding traffic light status gather the image of crossing data in real time, are remotely taken if being uploaded if having multiple image after JPEG compression compression algorithm
Business device is identified, and server combination database carries out deep search, calculating and matching to obtain the recognition result (people detected
Face frame, matching make a dash across the red light number, this progress of making a dash across the red light, whether be sensitive personnel etc.), and recognition result passed back to local embedding
Embedded system is handled and real-time display recognition result, and by block chain node updating maintenance pedestrian's data, and be included in
In credit system.
The implementation method of the system, including at least following steps:
S101:Activation system, detecting system whether normal operation;
S102:If system normal operation, traffic grade module obtains traffic light signals rule or pedestrian crosswalk signal lamp
The data message of light color, and the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color is uploaded to processor;
S103:The data message of processor analysis traffic light signals rule or pedestrian crosswalk signal lamp light color, works as traffic lights
During the data message that signal instructions are the data message that non-pedestrian passes through or pedestrian crosswalk signal lamp is red status, instruction shooting
Head mould group gathers view data;
S104:Camera module gathers view data, and view data is sent into processor;
S105:View data is sent to server by processor by interchanger log equipment;
S106:Server carries out human face detection and recognition and data comparison to obtain violation results according to view data, and
Violation results are sent to processor;
S107:Violation results are sent to display screen crossing by processor, and crossing display screen shows violation results.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of module and related work unit, the corresponding process in preceding method embodiment is may be referred to, herein no longer
Repeat.
In embodiment provided herein, it should be understood that disclosed method and system or device or module or
Unit, it can realize by another way.For example, embodiment of the method described above is only schematical, for example, institute
The division of module is stated, only a kind of division of logic function, can there is other dividing mode, such as multiple moulds when actually realizing
Block or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.The conduct
The unit that separating component illustrates can be or may not be it is physically separate, can be as the part that unit is shown or
Person may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can root
Factually border needs to select some or all of unit therein realize the purpose of this embodiment scheme.
Described above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
- A kind of 1. pedestrian running red light caution system, it is characterised in that including at least processor, camera module, crossing display screen, Traffic grade module and server:The traffic grade module, for obtaining the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color;The camera module, the data information acquisition view data for the acquisition according to the traffic grade module;The processor, for obtaining described image data and view data being uploaded into server;The server, tied in violation of rules and regulations for carrying out human face detection and recognition and data comparison according to described image data with obtaining Fruit;The crossing display screen, for showing the violation results;The processor is connected with camera module, crossing display screen and traffic grade module respectively by embedded Control node Connect to carry out data transmission, the processor is by network communicating system connection server to carry out data transmission.
- 2. system according to claim 1, it is characterised in that the camera module, in the traffic grade module The data message of acquisition be when traffic light signals rule is the data message that non-pedestrian passes through or pedestrian crosswalk signal lamp is red When the data message of color state, view data is gathered.
- 3. system according to claim 1, it is characterised in that the pedestrian crosswalk signal lamp is believed for the data of red status Breath is obtained by color sensor.
- 4. system according to claim 1, it is characterised in that the server is long-range deep learning calculation server.
- 5. system according to claim 1, it is characterised in that also including database, the database is used to store history Violation results.
- 6. system according to claim 1 or 5, it is characterised in that described violation results comprise at least facial image and Violation number.
- 7. system according to claim 5, it is characterised in that the server runs Ubuntu operating systems;The number It is LFW and/or YFW face databases according to storehouse.
- 8. system according to claim 7, it is characterised in that the server coordinate Opencv Face datections algorithm and Caffe+GPU depth frameworks, and it is carried in the VggNet depth convolutional neural networks that LFW and/or YFW face databases train Human face recognition model as system.
- 9. system according to claim 1, it is characterised in that the processor passes through network communicating system connection server To carry out data transmission referring to:The processor is by interchanger log equipment connection server to carry out data transmission.
- 10. according to the implementation method of system described in claim 1-9 any one, it is characterised in that including at least following steps:S101:Start the system, detecting system whether normal operation;S102:If the system normal operation, traffic grade module obtains traffic light signals rule or pedestrian crosswalk signal lamp The data message of light color, and the data message of traffic light signals rule or pedestrian crosswalk signal lamp light color is uploaded to processing Device;S103:The data message of the processor analysis traffic light signals rule or pedestrian crosswalk signal lamp light color, works as traffic lights During the data message that signal instructions are the data message that non-pedestrian passes through or pedestrian crosswalk signal lamp is red status, instruction shooting Head mould group gathers view data;S104:The camera module gathers view data, and described image data are sent into the processor;S105:Described image data are sent to server by the processor by interchanger log equipment;S106:The server carries out human face detection and recognition and data comparison according to described image data and tied in violation of rules and regulations with obtaining Fruit, and the violation results are sent to processor;S107:Violation results are sent to display screen crossing by the processor, and the crossing display screen shows violation results.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711140202.6A CN107886711A (en) | 2017-11-16 | 2017-11-16 | A kind of pedestrian running red light caution system and implementation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711140202.6A CN107886711A (en) | 2017-11-16 | 2017-11-16 | A kind of pedestrian running red light caution system and implementation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107886711A true CN107886711A (en) | 2018-04-06 |
Family
ID=61777565
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711140202.6A Pending CN107886711A (en) | 2017-11-16 | 2017-11-16 | A kind of pedestrian running red light caution system and implementation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107886711A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961782A (en) * | 2018-08-21 | 2018-12-07 | 北京深瞐科技有限公司 | Traffic intersection control method and device |
CN109376686A (en) * | 2018-11-14 | 2019-02-22 | 睿云联(厦门)网络通讯技术有限公司 | A kind of various dimensions human face data acquisition scheme, acquisition system and acquisition method |
CN109508659A (en) * | 2018-10-31 | 2019-03-22 | 绍兴文理学院 | A kind of face identification system and method for crossing |
CN111311901A (en) * | 2020-02-19 | 2020-06-19 | 深圳市博远科技创新发展有限公司 | Multifunctional warning system applied to traffic zebra crossing |
CN111325998A (en) * | 2018-12-17 | 2020-06-23 | 熊生银 | Red light with dignity |
CN114973717A (en) * | 2022-05-13 | 2022-08-30 | 北京百度网讯科技有限公司 | Intelligent signal lamp and image processing method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739809A (en) * | 2008-11-04 | 2010-06-16 | 上海经达实业发展有限公司 | Automatic alarm and monitoring system for pedestrian running red light |
CN103366565A (en) * | 2013-06-21 | 2013-10-23 | 浙江理工大学 | Method and system of detecting pedestrian running red light based on Kinect |
CN104299411A (en) * | 2014-09-08 | 2015-01-21 | 天津恒远达科技有限公司 | Device for monitoring jaywalking of pedestrians at intersections |
US9436877B2 (en) * | 2013-04-19 | 2016-09-06 | Polaris Sensor Technologies, Inc. | Pedestrian right of way monitoring and reporting system and method |
CN106340179A (en) * | 2016-09-30 | 2017-01-18 | 南京蓝泰交通设施有限责任公司 | Pedestrian crossing signal lamp system with red light running evidence obtaining function and method |
-
2017
- 2017-11-16 CN CN201711140202.6A patent/CN107886711A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739809A (en) * | 2008-11-04 | 2010-06-16 | 上海经达实业发展有限公司 | Automatic alarm and monitoring system for pedestrian running red light |
US9436877B2 (en) * | 2013-04-19 | 2016-09-06 | Polaris Sensor Technologies, Inc. | Pedestrian right of way monitoring and reporting system and method |
CN103366565A (en) * | 2013-06-21 | 2013-10-23 | 浙江理工大学 | Method and system of detecting pedestrian running red light based on Kinect |
CN104299411A (en) * | 2014-09-08 | 2015-01-21 | 天津恒远达科技有限公司 | Device for monitoring jaywalking of pedestrians at intersections |
CN106340179A (en) * | 2016-09-30 | 2017-01-18 | 南京蓝泰交通设施有限责任公司 | Pedestrian crossing signal lamp system with red light running evidence obtaining function and method |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961782A (en) * | 2018-08-21 | 2018-12-07 | 北京深瞐科技有限公司 | Traffic intersection control method and device |
CN109508659A (en) * | 2018-10-31 | 2019-03-22 | 绍兴文理学院 | A kind of face identification system and method for crossing |
CN109376686A (en) * | 2018-11-14 | 2019-02-22 | 睿云联(厦门)网络通讯技术有限公司 | A kind of various dimensions human face data acquisition scheme, acquisition system and acquisition method |
CN111325998A (en) * | 2018-12-17 | 2020-06-23 | 熊生银 | Red light with dignity |
CN111311901A (en) * | 2020-02-19 | 2020-06-19 | 深圳市博远科技创新发展有限公司 | Multifunctional warning system applied to traffic zebra crossing |
CN111311901B (en) * | 2020-02-19 | 2020-12-11 | 深圳市博远科技创新发展有限公司 | Multifunctional warning system applied to traffic zebra crossing |
CN114973717A (en) * | 2022-05-13 | 2022-08-30 | 北京百度网讯科技有限公司 | Intelligent signal lamp and image processing method |
CN114973717B (en) * | 2022-05-13 | 2024-05-10 | 北京百度网讯科技有限公司 | Intelligent signal lamp and image processing method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107886711A (en) | A kind of pedestrian running red light caution system and implementation method | |
CN110163236B (en) | Model training method and device, storage medium and electronic device | |
CN111723786B (en) | Method and device for detecting wearing of safety helmet based on single model prediction | |
CN109166094A (en) | A kind of insulator breakdown positioning identifying method based on deep learning | |
CN103325259B (en) | A kind of parking offense detection method based on multi-core parallel concurrent | |
CN105740758A (en) | Internet video face recognition method based on deep learning | |
CN105205453B (en) | Human eye detection and localization method based on depth self-encoding encoder | |
CN110414400B (en) | Automatic detection method and system for wearing of safety helmet on construction site | |
CN107133569A (en) | The many granularity mask methods of monitor video based on extensive Multi-label learning | |
CN110532925B (en) | Driver fatigue detection method based on space-time graph convolutional network | |
Cao et al. | CNN-based intelligent safety surveillance in green IoT applications | |
CN110163069A (en) | Method for detecting lane lines for assisting driving | |
CN109670517A (en) | Object detection method, device, electronic equipment and target detection model | |
Hu et al. | UAV remote sensing monitoring of pine forest diseases based on improved Mask R-CNN | |
Tran et al. | Pp-linknet: Improving semantic segmentation of high resolution satellite imagery with multi-stage training | |
CN103279753B (en) | A kind of English scene text block identifying method instructed based on tree construction | |
Fan et al. | A deep learning-based ensemble method for helmet-wearing detection | |
CN112308093B (en) | Air quality perception method based on image recognition, model training method and system | |
Ma et al. | Deconvolution Feature Fusion for traffic signs detection in 5G driven unmanned vehicle | |
Gajjar et al. | Intersection over Union based analysis of Image detection/segmentation using CNN model | |
Firoze et al. | Tree instance segmentation with temporal contour graph | |
CN104851102B (en) | A kind of infrared small target detection method based on human visual system | |
CN116977725A (en) | Abnormal behavior identification method and device based on improved convolutional neural network | |
CN115114480A (en) | Data processing method, device, equipment, readable storage medium and program product | |
CN114359578A (en) | Application method and system of pest and disease damage identification intelligent terminal |
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: 20180406 |