CN105957341A - Wide area traffic jam detection method based on unmanned plane airborne platform - Google Patents
Wide area traffic jam detection method based on unmanned plane airborne platform Download PDFInfo
- Publication number
- CN105957341A CN105957341A CN201610367802.5A CN201610367802A CN105957341A CN 105957341 A CN105957341 A CN 105957341A CN 201610367802 A CN201610367802 A CN 201610367802A CN 105957341 A CN105957341 A CN 105957341A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detection
- unmanned plane
- traffic jam
- wide area
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
Abstract
The invention discloses a wide area traffic jam detection method based on an unmanned plane airborne platform and belongs to the technical field of video images. The method comprises steps that 1, the GPS technology is utilized to acquire height of an unmanned plane to the ground, whether jam detection can be carried out is determined, if not, the spatial position of the unmanned plane is adjusted; 2, positive and negative samples of infrared vehicle images are acquired in an offline mode, HOG characteristics of the samples are extracted, and an SVM model is trained; 3, an infrared image signal is acquired by utilizing an infrared camera; 4, sliding window sampling of the infrared images is carried out, HOG characteristics of a sliding window zone are extracted, a SVM model is utilized to carry out vehicle detection, statistics of a total number N of vehicles in a present vision field is carried out; and 5, according to the height H of the unmanned plane and the total number N of the vehicles, a jam index C is calculated, and the detection result is returned. Through the method, detection on a traffic jam state under the condition of bad weather and low visibility can be accomplished by utilizing the infrared camera, moreover, detection zones can be dynamically selected by the unmanned plane airborne platform, and a detection system is made to be more flexible.
Description
Technical field
The invention belongs to video image technology and technical field of intelligent traffic, relate to a kind of wide area based on unmanned aerial vehicle onboard platform and hand over
Logical detection method of blocking up.
Background technology
Along with economic development, the quickening of urbanization process and city size constantly expand, vehicle guaranteeding organic quantity is on the increase.According to
Traffic Administration Bureau of Ministry of Public Security statistical data shows, by the end of the year 2015, whole nation vehicle guaranteeding organic quantity reaches 2.79 hundred million, wherein automobile 1.72
Hundred million, new-energy automobile 58.32 ten thousand;Whole nation private car recoverable amount has reached 1.24 hundred million, and average every one hundred houses family has 31.
Additionally, vehicle driver has reached 3.27 hundred million people, wherein motorist is more than 2.8 hundred million people.Vehicle guaranteeding organic quantity and road are handed over
Through-flow sharply increases so that urban traffic blocking is the most serious.
Traffic congestion does not only result in increasing of vehicle accident, brings loss economically, the most also injures the life security of people.
Showing according to Ministry of Communications's statistical data, the economic loss that traffic congestion is brought accounts for the 20% of urban population disposable income, is equivalent to every
The 5-8% of year GDP, reaches 250,000,000,000 yuans every year.According to World Health Organization's statistics, China hands over every year
Logical death tolls surpasses 250,000.Traffic jam issue brings great life, property loss to China, it has also become restrict me
The Main Bottleneck that state's big and medium-sized cities economic development and people's living standard improve.
Intelligent transportation system (IntelligentTransportation System, ITS) is the most effective means solving traffic jam issue
One of, it is by technological means such as various awareness apparatus and data communication, electronic sensor, Electronic Control, to various traffic feelings
Condition carries out perception, analyzes and processes and coordinate, and finally sets up a kind of real-time, accurate and efficient multi-transportation management system.?
During ITS systematic difference, in real time, effectively obtain transport information and seem particularly significant.Road traffic congestion can be realized
The detection of state, serves highly important supporting role to solving urban traffic blocking.
At present, conventional traffic jam detection method mainly have Data mining, geomagnetism detecting, electromagnetic detection, microwave detection,
The methods such as ultrasound examination, microwave detection and video images detection.Wherein, detection method is or not magnetic induction (electromagnetism, earth magnetism)
Affected by weather, illumination etc., stable performance and being widely used, but it is typically required and is embedded in fixed bottom boundary, to vehicle anon-normal
The situations such as normal traveling are easily generated erroneous judgement, and there is fault rate height, are difficult to the deficiencies such as maintenance;Ripple frequency (ultrasound wave, microwave) detection
Method can decay with propagation distance in communication process because of it, therefore its echo-signal is fainter, is easily submerged in noise, with
Time there is also that installation is complicated, block, the shortcomings such as inconvenience maintenance;Comparatively speaking, video detecting method has application model because of it
Enclose wide, installation process easy, accuracy relatively advantages of higher, be increasingly becoming Current traffic and block up the main stream approach of detection.
But, current video detecting method is many carries out flow detection based on coloured image principle, and it is disliked in night, weather condition
Easily producing vehicle missing inspection when bad, visibility is relatively low, accuracy of detection of blocking up is extremely low.Additionally, be used for gathering traffic data
Picture pick-up device be commonly installed more fixing, lack motility.Infrared signal is affected relatively by weather conditions, illumination variation, block etc.
Little, particularly thermal camera is installed on unmanned aerial vehicle platform, detects for traffic congestion, have that the detection ken is wide, detection
The features such as region is flexible, for dynamically obtaining traffic state information, solve traffic congestion and are extremely important.Therefore,
It is badly in need of a kind of wide area traffic jam detection method based on unmanned aerial vehicle onboard platform at present.
Summary of the invention
In view of this, it is an object of the invention to the defect overcoming existing traffic flow detection method based on video to exist, carry
For a kind of robust, flexibly traffic flow detection method, the method is calculated based on airborne platform, infrared camera technology and target detection
Method, can, visibility severe in night, weather conditions relatively low in the case of the vehicle in section, local is detected, and can spirit
Live and choose detection region, calculate current location traffic flow status.For reaching above-mentioned purpose, the present invention provides following technical scheme:
Traffic flow detection method based on airborne platform under a kind of wide area visual angle.Comprise the following steps:
Step one: utilize GPS location technology to obtain unmanned plane to ground level H, and judge whether present level can carry out traffic and gather around
Stifled detection, if then carrying out vehicle target detection, if being otherwise adjusted unmanned plane locus;
Step 2: off-line collection, for the positive negative sample of infrared image of vehicle target detection, extracts its histogram of gradients feature respectively
(HOG), it is supported vector machine (SVM) classifier training, obtains the SVM classifier model for online vehicle detection.
Step 3: utilize infrared camera to carry out infrared pick-up, obtain video signal;
Step 4: sample absorbed infrared image sequence under the sliding window of different scale, extracts sliding window region HOG
Feature, sends into this feature in the sorter model obtained in step 2, classifies vehicle target region, and detection is current wide
Vehicle under visual angle, territory, and add up the vehicle fleet N in the current ken;
Step 5: according to unmanned plane to ground level H and vehicle fleet N, calculates index C of blocking up, and by this index and setting threshold
Value compares, and more than setting threshold value, then returns traffic congestion state;Less than setting threshold value, then return traffic and pass through normal shape
State.
Further, step one specifically includes following steps: 11: utilize GPS location technology to obtain unmanned plane to ground level H;
12: if present level meets formula Hmin≤H≤Hmax, then carry out vehicle target detection, otherwise adjust unmanned plane locus.
Further, described step 3 specifically includes following steps: 21: off-line collection is used for the positive negative sample of vehicle detection, its
In positive sample refer to the sample containing vehicle to be checked, choosing of negative sample is relatively random, but need to be unrelated with vehicle target;22: respectively
Extract the HOG feature of positive negative sample, collecting sample is mapped to a characteristic vector space, and just correspondingly carries out sample
Negative label;23: by the characteristic vector extracted and respective labels input SVM training algorithm, obtain one for infrared image
The sorter model of vehicle target detection.
Further, described step 4 specifically includes following steps: 41: enterprising to the infrared image different scale size gathered
Line slip window sample, extracts the HOG feature in sliding window region;42: characteristic vector extraction obtained sends into claim 1
The disaggregated model obtained in described step 3, carries out detection classification to vehicle target;43: when detecting that vehicle target is by vehicle
Total counter N adds 1, adds up the vehicle target sum under the current ken.
Further, described step 5 specifically includes following steps: 51: index C of blocking up calculates as the following formula:
Wherein, N is vehicle fleet, H be unmanned plane to ground level, α is unmanned plane visual angle, and n is through lane number;52: if
Index C of blocking up more than setting threshold value, then returns traffic congestion state;52: if index C of blocking up is less than setting threshold value, then return
Traffic is passed through normal condition.
The beneficial effects of the present invention is: the method for the invention based on unmanned aerial vehicle onboard platform and infrared image processing technology, its
In, infrared photography function detects thermal target exactly, overcomes the harmful effect of background and severe weather conditions, is therefore suitable for model
Enclosing wide, robustness is stronger;Additionally, compared with the traffic jam detection method of current existing fixed test position, unmanned plane is not
Only can choose detection region flexibly, it is achieved detection equipment " a tractor serves several purposes ", it is possible to reduce testing cost to a certain extent, and
And unmanned plane has higher detection visual angle, testing result is the most accurately and reliably.
Accompanying drawing explanation
In order to make the purpose of the present invention, technical scheme and beneficial effect clearer, the present invention provides drawings described below to illustrate:
Fig. 1 is the flow chart of the method for the invention;
Fig. 2 is that schematic diagram is disposed in unmanned plane locus.
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
Fig. 1 is the flow chart of the method for the invention, and this method comprises the following steps:
S1: unmanned aerial vehicle onboard platform space position is carried out pretreatment, is adjusted to detectable altitude range.Unmanned plane
Locus adjusts and specifically comprises the following steps that
S11: utilize GPS location technology to obtain unmanned plane to ground level H;
S12: judge whether unmanned plane current spatial height meets formula Hmin≤H≤HmaxIf then carrying out vehicle target detection,
Otherwise adjust unmanned plane locus to meet above-mentioned space constraints.
S2: off-line collection, for the positive negative sample of infrared image of vehicle target detection, extracts its histogram of gradients (HOG) respectively
Feature, is supported vector machine (SVM) classifier training, obtains the SVM classifier model for online vehicle detection.Tool
Body step is as follows:
S21: off-line collection is for the positive negative sample of vehicle detection, and wherein positive sample refers to the sample containing vehicle to be checked, negative sample
Choose relatively random, but need to be unrelated with vehicle target;
S22: extract the HOG feature of positive negative sample respectively, maps to a characteristic vector space by collecting sample, and correspondingly
Carry out the positive and negative label of sample;
S23: by the characteristic vector extracted and respective labels input SVM training algorithm, obtain one for infrared image vehicle
The sorter model of target detection.
S3: utilize infrared camera to carry out infrared pick-up, obtain Infrared video image signal.
S4: the infrared image signal being absorbed described step S3 carries out vehicle target detection, and calculating vehicle sum.Vehicle mesh
Mark detection specifically comprises the following steps that with counting statistics
S41: to the infrared image gathered at different scale size enterprising line slip window sample, extract the HOG in sliding window region
Feature;
S42: characteristic vector extraction obtained sends into the disaggregated model obtained in described step S23, detects vehicle target
Classification;
S43: when detecting that vehicle target is to add 1 by vehicle fleet enumerator N, adds up the vehicle target sum under the current ken.
S5: calculate and pass through the index of blocking up of state for passing judgment on traffic, obtains traffic and passes through state.Specifically comprise the following steps that
S51: the unmanned plane traffic congestion detection scheme schematic diagram shown in 2 with reference to the accompanying drawings, according to triangle Computing Principle, can calculate
Go out the average spacing of current road segment, the index of blocking up of state of can passing through as judge traffic.Wherein, index C of blocking up is as the following formula
Calculate:
Wherein, N is vehicle fleet, H be unmanned plane to ground level, α is unmanned plane visual angle, and n is through lane number;
S52: if index C of blocking up is more than setting threshold value, then return traffic congestion state;
S52: if blocking up index C less than setting threshold value, then return traffic and pass through normal condition.
Finally illustrating, preferred embodiment above is only in order to illustrate technical scheme and unrestricted, although by above-mentioned
The present invention is described in detail by preferred embodiment, it is to be understood by those skilled in the art that can in form and
In details, it is made various change, without departing from claims of the present invention limited range.
Claims (5)
1. a wide area traffic jam detection method based on unmanned aerial vehicle onboard platform, it is characterised in that: comprise the following steps:
Step one: utilize GPS location technology to obtain unmanned plane to ground level H, and judge whether present level can carry out traffic and gather around
Stifled detection, if then carrying out vehicle target detection, if being otherwise adjusted unmanned plane locus;
Step 2: off-line collection, for the positive negative sample of infrared image of vehicle target detection, extracts its histogram of gradients (HOG) respectively
Feature, is supported vector machine (SVM) classifier training, obtains dividing for the SVM of online vehicle detection
Class device model.
Step 3: utilize infrared camera to carry out infrared pick-up, obtain video signal;
Step 4: sample absorbed infrared image sequence under the sliding window of different scale, extracts sliding window region HOG
Feature, sends into this feature in the sorter model obtained in step 2, classifies vehicle target region,
Vehicle under detection current wide visual angle, and add up the vehicle fleet N in the current ken;
Step 5: according to unmanned plane to ground level H and vehicle fleet N, calculates index C of blocking up, and by this index and setting threshold
Value compares, and more than setting threshold value, then returns traffic congestion state;Less than setting threshold value, then return friendship
Row normal condition all.
A kind of wide area traffic jam detection method based on unmanned aerial vehicle onboard platform the most according to claim 1, it is characterised in that:
Following steps are specifically included: 11: utilize GPS location technology to obtain unmanned plane to ground level H in step one;12: if
Present level meets formula Hmin≤H≤Hmax, then carry out vehicle target detection, otherwise adjust unmanned plane locus.
A kind of wide area traffic jam detection method based on unmanned aerial vehicle onboard platform the most according to claim 1, it is characterised in that:
Following steps are specifically included: 21: off-line collection is for the positive negative sample of vehicle detection, and wherein positive sample is in step 2
Referring to the sample containing vehicle to be checked, choosing of negative sample is relatively random, but need to be unrelated with vehicle target;22: just extracting respectively
The HOG feature of negative sample, maps to collecting sample a characteristic vector space, and correspondingly carries out the positive and negative mark of sample
Sign;23: by the characteristic vector extracted and respective labels input SVM training algorithm, obtain one for infrared image car
The sorter model of target detection.
A kind of wide area traffic jam detection method based on unmanned aerial vehicle onboard platform the most according to claim 1, it is characterised in that:
Following steps are specifically included: 41: to the infrared image different scale size enterprising line slip window gathered in step 4
Sampling, extracts the HOG feature in sliding window region;42: characteristic vector extraction obtained sends into step described in claim 1
The disaggregated model obtained in three, carries out detection classification to vehicle target;43: when detecting that vehicle target is by vehicle fleet
Enumerator N adds 1, adds up the vehicle target sum under the current ken.
A kind of wide area traffic jam detection method based on unmanned aerial vehicle onboard platform the most according to claim 1, it is characterised in that:
Following steps are specifically included: 51: index C of blocking up calculates as the following formula in step 5:
Wherein, N is vehicle fleet, H be unmanned plane to ground level, α is unmanned plane visual angle, and n is through lane number;52: if
Index C of blocking up more than setting threshold value, then returns traffic congestion state;52: if index C of blocking up is less than setting threshold value, then return
Traffic is passed through normal condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610367802.5A CN105957341A (en) | 2016-05-30 | 2016-05-30 | Wide area traffic jam detection method based on unmanned plane airborne platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610367802.5A CN105957341A (en) | 2016-05-30 | 2016-05-30 | Wide area traffic jam detection method based on unmanned plane airborne platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105957341A true CN105957341A (en) | 2016-09-21 |
Family
ID=56910875
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610367802.5A Pending CN105957341A (en) | 2016-05-30 | 2016-05-30 | Wide area traffic jam detection method based on unmanned plane airborne platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105957341A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108364466A (en) * | 2018-02-11 | 2018-08-03 | 金陵科技学院 | A kind of statistical method of traffic flow based on unmanned plane traffic video |
CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
CN109887276A (en) * | 2019-01-30 | 2019-06-14 | 北京同方软件股份有限公司 | The night traffic congestion detection method merged based on foreground extraction with deep learning |
CN110599781A (en) * | 2019-09-23 | 2019-12-20 | 潍坊畅讯交通设施工程有限公司 | Traffic flow statistics and recognition system for intelligent city |
CN111833601A (en) * | 2020-06-28 | 2020-10-27 | 北京邮电大学 | Macroscopic traffic law modeling method with low communication cost |
JP2022073894A (en) * | 2020-10-29 | 2022-05-17 | 中国汽車技術研究中心有限公司 | Driving scene classification method, device, apparatus, and readable storage medium |
CN114944072A (en) * | 2022-07-22 | 2022-08-26 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070002138A1 (en) * | 2005-07-01 | 2007-01-04 | The Boeing Company | Method for generating a synthetic perspective image |
CN102654940A (en) * | 2012-05-23 | 2012-09-05 | 上海交通大学 | Traffic information acquisition system based on unmanned aerial vehicle and processing method of traffic information acquisition system |
US20130191014A1 (en) * | 2012-01-24 | 2013-07-25 | Xerox Corporation | Vehicle speed determination via infrared imaging |
CN103413444A (en) * | 2013-08-26 | 2013-11-27 | 深圳市川大智胜科技发展有限公司 | Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video |
CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
CN104269054A (en) * | 2014-09-20 | 2015-01-07 | 无锡北斗星通信息科技有限公司 | Road segment traffic index estimation system based on unmanned aerial vehicle measurement |
CN105574488A (en) * | 2015-12-07 | 2016-05-11 | 北京航空航天大学 | Low-altitude aerial infrared image based pedestrian detection method |
-
2016
- 2016-05-30 CN CN201610367802.5A patent/CN105957341A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070002138A1 (en) * | 2005-07-01 | 2007-01-04 | The Boeing Company | Method for generating a synthetic perspective image |
US20130191014A1 (en) * | 2012-01-24 | 2013-07-25 | Xerox Corporation | Vehicle speed determination via infrared imaging |
CN102654940A (en) * | 2012-05-23 | 2012-09-05 | 上海交通大学 | Traffic information acquisition system based on unmanned aerial vehicle and processing method of traffic information acquisition system |
CN103413444A (en) * | 2013-08-26 | 2013-11-27 | 深圳市川大智胜科技发展有限公司 | Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video |
CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
CN104269054A (en) * | 2014-09-20 | 2015-01-07 | 无锡北斗星通信息科技有限公司 | Road segment traffic index estimation system based on unmanned aerial vehicle measurement |
CN105574488A (en) * | 2015-12-07 | 2016-05-11 | 北京航空航天大学 | Low-altitude aerial infrared image based pedestrian detection method |
Non-Patent Citations (1)
Title |
---|
翁松伟 等: ""基于小型四旋翼无人机的道路交通巡检系统"", 《电子设计工程》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108364466A (en) * | 2018-02-11 | 2018-08-03 | 金陵科技学院 | A kind of statistical method of traffic flow based on unmanned plane traffic video |
CN108364466B (en) * | 2018-02-11 | 2021-01-26 | 金陵科技学院 | Traffic flow statistical method based on unmanned aerial vehicle traffic video |
CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
CN109887276A (en) * | 2019-01-30 | 2019-06-14 | 北京同方软件股份有限公司 | The night traffic congestion detection method merged based on foreground extraction with deep learning |
CN109887276B (en) * | 2019-01-30 | 2020-11-03 | 北京同方软件有限公司 | Night traffic jam detection method based on fusion of foreground extraction and deep learning |
CN110599781A (en) * | 2019-09-23 | 2019-12-20 | 潍坊畅讯交通设施工程有限公司 | Traffic flow statistics and recognition system for intelligent city |
CN111833601A (en) * | 2020-06-28 | 2020-10-27 | 北京邮电大学 | Macroscopic traffic law modeling method with low communication cost |
JP2022073894A (en) * | 2020-10-29 | 2022-05-17 | 中国汽車技術研究中心有限公司 | Driving scene classification method, device, apparatus, and readable storage medium |
JP7236488B2 (en) | 2020-10-29 | 2023-03-09 | 中国汽車技術研究中心有限公司 | Driving scene classification method, device, equipment and readable storage medium |
CN114944072A (en) * | 2022-07-22 | 2022-08-26 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
CN114944072B (en) * | 2022-07-22 | 2022-11-01 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105957341A (en) | Wide area traffic jam detection method based on unmanned plane airborne platform | |
CN106652468B (en) | The detection and from vehicle violation early warning alarm set and method in violation of rules and regulations of road vehicle front truck | |
CN106373394B (en) | Vehicle detection method and system based on video and radar | |
CN105512720B (en) | A kind of public transit vehicle passenger flow statistics method and system | |
Huang et al. | On-board vision system for lane recognition and front-vehicle detection to enhance driver's awareness | |
CN103164958B (en) | Method and system for vehicle monitoring | |
Fernández-Caballero et al. | Road-traffic monitoring by knowledge-driven static and dynamic image analysis | |
CN105427614A (en) | Model classification system and method | |
CN106373426A (en) | Computer vision-based parking space and illegal lane occupying parking monitoring method | |
CN104851295A (en) | Method and system for acquiring road condition information | |
CN106951879A (en) | Multiple features fusion vehicle checking method based on camera and millimetre-wave radar | |
CN105551264A (en) | Speed detection method based on license plate characteristic matching | |
CN111833598B (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
CN104616502A (en) | License plate identification and positioning system based on combined type vehicle-road video network | |
CN106096504A (en) | A kind of model recognizing method based on unmanned aerial vehicle onboard platform | |
Borkar et al. | An efficient method to generate ground truth for evaluating lane detection systems | |
CN104794906A (en) | Vehicle management platform of outdoor parking lot exit | |
CN106448223B (en) | Expressway driving speed early warning device and method capable of automatically adapting to haze | |
CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method | |
Larsen et al. | Traffic monitoring using very high resolution satellite imagery | |
CN204825605U (en) | Discernment of road environment and detection device based on image | |
CN104766337A (en) | Aircraft landing vision enhancement method based on runway boundary enhancement | |
CN207473847U (en) | Night intersection pedestrian's street crossing safety signal system | |
CN103149603A (en) | Road weather detection method based on video | |
CN202911633U (en) | Dynamic detection device based on multi-information fusion for hybrid electric vehicle lane identification lines |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160921 |
|
WD01 | Invention patent application deemed withdrawn after publication |