CN106203346A - A kind of road environment image classification method towards the switching of intelligent vehicle driving model - Google Patents
A kind of road environment image classification method towards the switching of intelligent vehicle driving model Download PDFInfo
- Publication number
- CN106203346A CN106203346A CN201610547060.4A CN201610547060A CN106203346A CN 106203346 A CN106203346 A CN 106203346A CN 201610547060 A CN201610547060 A CN 201610547060A CN 106203346 A CN106203346 A CN 106203346A
- Authority
- CN
- China
- Prior art keywords
- image
- environment
- described step
- road environment
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/88—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of road environment image classification method towards the switching of intelligent vehicle driving model, make vehicle view-based access control model information carry out outdoor traffic environment identification.This method carries out the key links such as illumination compensation, ambient image feature representation, characteristics of image classification around outdoor traffic environment image, make vehicle in the process of moving can constantly perception and judge environmental information around, thus carry out effective identification of the environment such as urban road, highway, backroad, wild environment.The present invention can be that the driving model switching of intelligent driving aid system and automatic driving vehicle provides technical support with autonomous thermoacoustic prime engine decision-making.
Description
Technical field
The present invention relates to intelligent automobile auxiliary driving technology field, particularly relate to a kind of towards intelligent vehicle driving mould
The road environment image classification method of formula switching.
Background technology
In recent years, vehicle intellectualized technology quickly grows.In the vehicle intellectualized skills classification standard that SAE formulates, auxiliary
Driving technology and part automatic Pilot technology is helped to have enter into the industrialization stage;Automatic Pilot with good conditionsi is driven with increasingly automated
Technology of sailing enters test Qualify Phase.And image procossing and identification technology are in intelligent driving aid system with automatic driving vehicle
Application gradually strengthens.View-based access control model sensor is obtained in that different kinds of roads environmental information.Vehicle by the perception to environmental information,
Different road scene can be identified;For different road scene, what vehicle can be autonomous switches different driving models, from
Adapt to the Decision Control scheme of change system, and then adjust the transport condition of vehicle self and perform grasp corresponding with road condition
Instruct, it is achieved efficient, the driving function of energy-saving and environmental protection.
Summary of the invention
Present invention is primarily targeted at a kind of road environment image towards the switching of intelligent vehicle driving model of invention to divide
Class method, it is intended to realizing vehicle road environment identification in motion, i.e. vehicle in the process of moving can constantly perception and judgement
The method of environmental information around, enables the vehicle to safer, efficient by corresponding road environment.
For achieving the above object, a kind of road environment image towards the switching of intelligent vehicle driving model that the present invention provides
Sorting technique, comprises the following steps:
Step one, road environment video image acquisition, it is thus achieved that the road ring of vehicle front and surrounding in vehicle travel process
Border image;
Step 2, the road environment image gathering described step one carry out pretreatment, and obtain the gray level image of correspondence;
Step 3, the texture extracting and expressing the gray level image that described step 2 obtains and Gradient Features information;
Step 4, characteristic information to the gray level image that described step 3 is extracted are classified and identify, carry out road ring
Effective identification in border.
Further, described step 2 includes procedure below:
2.1) utilizing the Gamma correction algorithm improved, the road environment image gathering described step one carries out illumination benefit
Repay;
2.2) image after illumination compensation is carried out gray proces, it is thus achieved that gray level image;
2.3) gray level image use gaussian filtering be filtered processing.
Further, described step 3 includes procedure below:
Image after processing based on described step 2, builds the multiple dimensioned local binary patterns expression characteristic of image, simultaneously
Build the integration direction histogram of gradients expression characteristic of image;Multiple dimensioned local binary patterns expression characteristic by the image of structure
It is combined with integration direction histogram of gradients expression characteristic and forms new characteristic vector, use principal component analytical method, extract
And build the feature representation vector of image.
Further, described step 3 specifically includes following steps:
3.1) image division after described step 2 being processed becomes the grid subregion of m*n, for each region of m*n,
Calculate multiple dimensioned local binary patterns feature, calculate the integration direction histogram of gradients feature in this region simultaneously;
3.2) further described multiple dimensioned local binary patterns feature is combined with integration direction histogram of gradients feature, structure
Build local grain and the gradient eigenvector of this subregion, the local grain of the grid subregion of this image m*n is special with gradient
Levy simultaneous, build the global characteristics vector of entire image;
3.3) the global characteristics vector using the principal component analytical method entire image to building carries out dimension-reduction treatment, to entirely
Office's characteristic vector carries out feature extraction, asks for spatial alternation eigenmatrix, from higher dimensional space, sample characteristics is mapped to low-dimensional empty
Between, the feature after converting is as the expression characteristic of image pattern.
Further, described step 4 includes procedure below:
4.1) for urban road, highway, backroad, wild environment four class environment, four kinds are gathered respectively
The road scene sample image of type, builds the road environment recognition training Sample Storehouse towards intelligent vehicle;
4.2) through described step one, step 2, step 3, sample image is processed, extract training sample image
Feature, as the grounding sample of SVM classifier model, and then builds sorter model;
4.3) use cross validation method that SVM classifier model parameter is optimized, it is achieved the optimization design of grader;
4.4) image pattern of vehicle-mounted pick-up equipment Real-time Collection carries out characteristic of correspondence expression be input to after extracting
In traffic scene sorter model, carry out the real-time environment of urban road, highway, backroad, wild environment
Identify classification.
The invention have the advantages that
The method that the present invention provides can realize the most automatically identifying of environment, can be intelligent driving aid system and nothing
People drives vehicle and carries out the switching of driving model for different road conditions, the Decision Control scheme of adaptive optimal system,
And then adjust the transport condition of vehicle self and perform operational order corresponding with road condition, it is achieved efficient, energy-saving and environmental protection
Drive function.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention.
Detailed description of the invention
Technical scheme it is discussed in detail below in conjunction with accompanying drawing:
A kind of road environment image classification method towards the switching of intelligent vehicle driving model, as it is shown in figure 1, include following
Step:
Step one, road environment video image acquisition, it is thus achieved that the road ring of vehicle front and surrounding in vehicle travel process
Border image.
Step 2, the road environment image gathering step one carry out pretreatment, and obtain the gray level image of correspondence.
(1) being round-the-clock collection environmental information due to Vehicular video, therefore image is bigger by illumination effect.By vehicle-mounted
Outdoor environment image that monocular vision collects also carries out illumination analysis, proposes illumination compensation method.For reducing illumination as far as possible
The impact of factor, improves the accuracy of image recognition and categorizing system, utilizes the Gamma correction algorithm improved, to uneven illumination
Even image carries out illumination compensation;
(2) image after illumination compensation is carried out further gray proces, it is thus achieved that gray level image;
(3) finally gray level image is used gaussian filtering, be filtered processing.
Step 3, the texture extracting and expressing the gray level image that described step 2 obtains and Gradient Features information.
(1) image after processing based on described step 2, builds the multiple dimensioned local binary patterns expression characteristic of image, with
Time build image integration direction histogram of gradients expression characteristic:
Image division after processing becomes the grid subregion of m*n, for each region of m*n, calculates multiple dimensioned office
Portion's binary pattern feature, calculates the integration direction histogram of gradients feature in this region simultaneously.
(2) the multiple dimensioned local binary patterns expression characteristic of the image built is expressed spy with integration direction histogram of gradients
Levy to be combined and form new characteristic vector:
Further the two is combined local grain and the gradient eigenvector building this subregion.Then by this image m*n
Local grain and the Gradient Features simultaneous of grid subregion, build the global characteristics vector of entire image.
(3) using principal component analytical method, the feature representation extracting and building image is vectorial:
Owing to multiple dimensioned local binary patterns feature and integration direction histogram of gradients feature are high-dimensional feature, simultaneously
Image comprises again the grid subregion of m*n, therefore the global characteristics vector of entire image be a high-dimensional feature obviously to
Amount.If as the expression characteristic of training sample and then building sorter model by this feature, will significantly increase computational burden.
Therefore use principal component analytical method to carry out dimension-reduction treatment, the global characteristics vector of image is carried out feature extraction, asks for space
Transform characteristics matrix, is mapped to lower dimensional space by sample characteristics from higher dimensional space.Using the feature after conversion as image pattern
Expression characteristic.
Step 4, the characteristic information of gray level image extracted classified and identified, carrying out effectively knowing of road environment
Not.
(1) for four class environment such as urban road, highway, backroad, wild environments, four types are gathered
Road scene sample image, build towards the road environment recognition training Sample Storehouse of intelligent vehicle.
(2) sample image is processed by the method combined in above-mentioned steps one to step 3, extracts training sample image
Feature, thus as the grounding sample of SVM (support vector machine) sorter model, and then builds sorter model.For reaching
To the most preferably classifying quality.
(3) use cross validation method that SVM classifier model parameter is optimized, it is achieved the optimization design of grader.
(4) carry out the image pattern of vehicle-mounted pick-up equipment Real-time Collection being input to hand over after characteristic of correspondence is expressed and extracted
In logical scene classifier model, carry out the knowledge of the environment in real time such as urban road, highway, backroad, wild environment
Do not classify.
This method can realize the most automatically identifying of environment, can be intelligent driving aid system and automatic driving vehicle
The switching of driving model is carried out for different road conditions, the Decision Control scheme of adaptive optimal system, and then adjust car
Self transport condition and perform operational order corresponding with road condition, it is achieved efficient, the driving function of energy-saving and environmental protection.
Claims (5)
1. the road environment image classification method towards the switching of intelligent vehicle driving model, it is characterised in that include following
Step:
Step one, road environment video image acquisition, it is thus achieved that the road environment figure of vehicle front and surrounding in vehicle travel process
Picture;
Step 2, the road environment image gathering described step one carry out pretreatment, and obtain the gray level image of correspondence;
Step 3, the texture extracting and expressing the gray level image that described step 2 obtains and Gradient Features information;
Step 4, characteristic information to the gray level image that described step 3 is extracted are classified and identify, carry out road environment
Effectively identify.
A kind of road environment image classification method towards the switching of intelligent vehicle driving model, its
Being characterised by, described step 2 includes procedure below:
2.1) utilizing the Gamma correction algorithm improved, the road environment image gathering described step one carries out illumination compensation;
2.2) image after illumination compensation is carried out gray proces, it is thus achieved that gray level image;
2.3) gray level image use gaussian filtering be filtered processing.
A kind of road environment image classification method towards the switching of intelligent vehicle driving model, its
Being characterised by, described step 3 includes procedure below:
Image after processing based on described step 2, builds the multiple dimensioned local binary patterns expression characteristic of image, builds simultaneously
The integration direction histogram of gradients expression characteristic of image;By the multiple dimensioned local binary patterns expression characteristic of the image of structure with long-pending
Divide histograms of oriented gradients expression characteristic to be combined and form new characteristic vector, use principal component analytical method, extract and structure
Build the feature representation vector of image.
A kind of road environment image classification method towards the switching of intelligent vehicle driving model, its
Being characterised by, described step 3 specifically includes following steps:
3.1) image division after described step 2 being processed becomes the grid subregion of m*n, for each region of m*n, calculates
Multiple dimensioned local binary patterns feature, calculates the integration direction histogram of gradients feature in this region simultaneously;
3.2) described multiple dimensioned local binary patterns feature being combined with integration direction histogram of gradients feature further, building should
The local grain of subregion and gradient eigenvector, join the local grain of the grid subregion of this image m*n with Gradient Features
Vertical, build the global characteristics vector of entire image;
3.3) the global characteristics vector using the principal component analytical method entire image to building carries out dimension-reduction treatment, special to the overall situation
Levy vector and carry out feature extraction, ask for spatial alternation eigenmatrix, sample characteristics is mapped to lower dimensional space from higher dimensional space, will
Feature after conversion is as the expression characteristic of image pattern.
A kind of road environment image classification method towards the switching of intelligent vehicle driving model, its
Being characterised by, described step 4 includes procedure below:
4.1) for urban road, highway, backroad, wild environment four class environment, four types are gathered respectively
Road scene sample image, build towards the road environment recognition training Sample Storehouse of intelligent vehicle;
4.2) through described step one, step 2, step 3, sample image is processed, extracts training sample image feature,
As the grounding sample of SVM classifier model, and then build sorter model;
4.3) use cross validation method that SVM classifier model parameter is optimized, it is achieved the optimization design of grader;
4.4) carry out the image pattern of vehicle-mounted pick-up equipment Real-time Collection being input to traffic after characteristic of correspondence is expressed and extracted
In scene classifier model, carry out the identification of the real-time environment of urban road, highway, backroad, wild environment
Classification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610547060.4A CN106203346A (en) | 2016-07-13 | 2016-07-13 | A kind of road environment image classification method towards the switching of intelligent vehicle driving model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610547060.4A CN106203346A (en) | 2016-07-13 | 2016-07-13 | A kind of road environment image classification method towards the switching of intelligent vehicle driving model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106203346A true CN106203346A (en) | 2016-12-07 |
Family
ID=57477487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610547060.4A Pending CN106203346A (en) | 2016-07-13 | 2016-07-13 | A kind of road environment image classification method towards the switching of intelligent vehicle driving model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106203346A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107392252A (en) * | 2017-07-26 | 2017-11-24 | 上海城诗信息科技有限公司 | Computer deep learning characteristics of image and the method for quantifying perceptibility |
CN107953888A (en) * | 2017-11-29 | 2018-04-24 | 北京经纬恒润科技有限公司 | A kind of road type recognition methods and system |
CN109017803A (en) * | 2018-07-14 | 2018-12-18 | 安徽中科美络信息技术有限公司 | A kind of car-mounted terminal operating mode control method and car-mounted terminal |
WO2019047656A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术(北京)有限公司 | Method and apparatus for use in controlling driverless vehicle |
CN109492597A (en) * | 2018-11-19 | 2019-03-19 | 深圳市元征科技股份有限公司 | The method for building up and device of driving behavior model based on SVM algorithm |
CN109808695A (en) * | 2019-02-28 | 2019-05-28 | 北京航空航天大学 | A kind of car travel mode method of adjustment and device |
CN109886199A (en) * | 2019-02-21 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | Information processing method, device, vehicle and mobile terminal |
CN110192232A (en) * | 2019-04-18 | 2019-08-30 | 京东方科技集团股份有限公司 | Traffic information processing equipment, system and method |
CN110222555A (en) * | 2019-04-18 | 2019-09-10 | 江苏图云智能科技发展有限公司 | The detection method and device of area of skin color |
CN110741379A (en) * | 2017-06-06 | 2020-01-31 | 标致雪铁龙汽车股份有限公司 | Method for determining the type of road on which a vehicle is travelling |
CN110785774A (en) * | 2017-06-06 | 2020-02-11 | 智加科技公司 | Method and system for closed loop sensing in autonomous vehicles |
WO2020029580A1 (en) * | 2018-08-08 | 2020-02-13 | 华为技术有限公司 | Method and apparatus for training control strategy model for generating automatic driving strategy |
CN111010545A (en) * | 2019-12-20 | 2020-04-14 | 深圳市中天安驰有限责任公司 | Vehicle driving decision method, system, terminal and storage medium |
CN111542834A (en) * | 2017-12-27 | 2020-08-14 | 大众汽车(中国)投资有限公司 | Processing method, processing device, control equipment and cloud server |
CN111613076A (en) * | 2020-04-09 | 2020-09-01 | 吉利汽车研究院(宁波)有限公司 | Driving assistance method, system, server and storage medium |
CN111767943A (en) * | 2020-05-20 | 2020-10-13 | 北京简巨科技有限公司 | Mulching film identification method and device, electronic equipment and storage medium |
CN113313126A (en) * | 2021-04-30 | 2021-08-27 | 杭州好安供应链管理有限公司 | Method, computing device, and computer storage medium for image recognition |
CN115716459A (en) * | 2022-11-02 | 2023-02-28 | 中国第一汽车股份有限公司 | Method and device for guaranteeing safety of personnel in vehicle during vehicle running |
US11790551B2 (en) | 2017-06-06 | 2023-10-17 | Plusai, Inc. | Method and system for object centric stereo in autonomous driving vehicles |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104091157A (en) * | 2014-07-09 | 2014-10-08 | 河海大学 | Pedestrian detection method based on feature fusion |
CN104091147A (en) * | 2014-06-11 | 2014-10-08 | 华南理工大学 | Near infrared eye positioning and eye state identification method |
-
2016
- 2016-07-13 CN CN201610547060.4A patent/CN106203346A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104091147A (en) * | 2014-06-11 | 2014-10-08 | 华南理工大学 | Near infrared eye positioning and eye state identification method |
CN104091157A (en) * | 2014-07-09 | 2014-10-08 | 河海大学 | Pedestrian detection method based on feature fusion |
Non-Patent Citations (2)
Title |
---|
ISABELLE TANG ETC.: ""Automatic Road Environment Classification"", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
张毅: ""融合二阶HOG与CS-LBP的头部姿态估计"", 《智能系统学报》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11790551B2 (en) | 2017-06-06 | 2023-10-17 | Plusai, Inc. | Method and system for object centric stereo in autonomous driving vehicles |
CN110741379A (en) * | 2017-06-06 | 2020-01-31 | 标致雪铁龙汽车股份有限公司 | Method for determining the type of road on which a vehicle is travelling |
CN110785774A (en) * | 2017-06-06 | 2020-02-11 | 智加科技公司 | Method and system for closed loop sensing in autonomous vehicles |
CN107392252A (en) * | 2017-07-26 | 2017-11-24 | 上海城诗信息科技有限公司 | Computer deep learning characteristics of image and the method for quantifying perceptibility |
WO2019047656A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术(北京)有限公司 | Method and apparatus for use in controlling driverless vehicle |
CN107953888A (en) * | 2017-11-29 | 2018-04-24 | 北京经纬恒润科技有限公司 | A kind of road type recognition methods and system |
CN111542834A (en) * | 2017-12-27 | 2020-08-14 | 大众汽车(中国)投资有限公司 | Processing method, processing device, control equipment and cloud server |
CN109017803B (en) * | 2018-07-14 | 2020-05-22 | 安徽中科美络信息技术有限公司 | Vehicle-mounted terminal working mode control method and vehicle-mounted terminal |
CN109017803A (en) * | 2018-07-14 | 2018-12-18 | 安徽中科美络信息技术有限公司 | A kind of car-mounted terminal operating mode control method and car-mounted terminal |
WO2020029580A1 (en) * | 2018-08-08 | 2020-02-13 | 华为技术有限公司 | Method and apparatus for training control strategy model for generating automatic driving strategy |
CN109492597A (en) * | 2018-11-19 | 2019-03-19 | 深圳市元征科技股份有限公司 | The method for building up and device of driving behavior model based on SVM algorithm |
CN109886199A (en) * | 2019-02-21 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | Information processing method, device, vehicle and mobile terminal |
CN109808695A (en) * | 2019-02-28 | 2019-05-28 | 北京航空航天大学 | A kind of car travel mode method of adjustment and device |
CN110222555A (en) * | 2019-04-18 | 2019-09-10 | 江苏图云智能科技发展有限公司 | The detection method and device of area of skin color |
CN110222555B (en) * | 2019-04-18 | 2022-12-20 | 灏图科技(上海)有限公司 | Method and device for detecting skin color area |
CN110192232A (en) * | 2019-04-18 | 2019-08-30 | 京东方科技集团股份有限公司 | Traffic information processing equipment, system and method |
CN111010545A (en) * | 2019-12-20 | 2020-04-14 | 深圳市中天安驰有限责任公司 | Vehicle driving decision method, system, terminal and storage medium |
CN111613076A (en) * | 2020-04-09 | 2020-09-01 | 吉利汽车研究院(宁波)有限公司 | Driving assistance method, system, server and storage medium |
CN111767943A (en) * | 2020-05-20 | 2020-10-13 | 北京简巨科技有限公司 | Mulching film identification method and device, electronic equipment and storage medium |
CN113313126A (en) * | 2021-04-30 | 2021-08-27 | 杭州好安供应链管理有限公司 | Method, computing device, and computer storage medium for image recognition |
CN115716459A (en) * | 2022-11-02 | 2023-02-28 | 中国第一汽车股份有限公司 | Method and device for guaranteeing safety of personnel in vehicle during vehicle running |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106203346A (en) | A kind of road environment image classification method towards the switching of intelligent vehicle driving model | |
CN109460709B (en) | RTG visual barrier detection method based on RGB and D information fusion | |
CN109753890B (en) | Intelligent recognition and sensing method for road surface garbage and implementation device thereof | |
CN109284669A (en) | Pedestrian detection method based on Mask RCNN | |
CN100495438C (en) | Method for detecting and identifying moving target based on video monitoring | |
US10467482B2 (en) | Method and arrangement for assessing the roadway surface being driven on by a vehicle | |
CN109086687A (en) | The traffic sign recognition method of HOG-MBLBP fusion feature based on PCA dimensionality reduction | |
CN107679508A (en) | Road traffic sign detection recognition methods, apparatus and system | |
CN109145798B (en) | Driving scene target identification and travelable region segmentation integration method | |
KR101845769B1 (en) | Car rear detection system using convolution neural network, and method thereof | |
CN108765443A (en) | A kind of mark enhancing processing method of adaptive color Threshold segmentation | |
CN109101924A (en) | A kind of pavement marking recognition methods based on machine learning | |
CN104966066A (en) | Traffic block port monitoring oriented in-car human face detection method and system | |
CN103996041A (en) | Vehicle color identification method and system based on matching | |
CN102314599A (en) | Identification and deviation-detection method for lane | |
CN104537360A (en) | Method and system for detecting vehicle violation of not giving way | |
CN107273866A (en) | A kind of human body abnormal behaviour recognition methods based on monitoring system | |
CN105095869A (en) | Pedestrian detection method and apparatus | |
CN102938057A (en) | Vehicle shadow eliminating method and device | |
CN113200052B (en) | Intelligent road condition identification method for unmanned driving | |
CN108108703A (en) | Deceleration strip missing detection method, device and electronic equipment | |
CN110060221A (en) | A kind of bridge vehicle checking method based on unmanned plane image | |
CN111507391A (en) | Intelligent identification method for nonferrous metal broken materials based on machine vision | |
CN109190455A (en) | Black smoke vehicle recognition methods based on Gaussian Mixture and autoregressive moving-average model | |
CN112204566A (en) | Image processing method and device based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
RJ01 | Rejection of invention patent application after publication |