SlideShare a Scribd company logo
Advisor : Yin-Fu Huang


        Automatic Road Environment
              Classification
  Intelligent Transportation Systems, IEEE Transactions on



                                          Student : Chen-Ju Lai
  1
Outline
       Introduction
       Road image subregions
       Feature extraction and representation
       Feature classification
       Experimental result
       Conclusion




    2
Introduction
   Input video frame :640X480 resolution
    Standard digital video camera(30-fps video)
   Feature extraction :color ,texture
    Classification method :k-NN and ANN
    Four class problem , accuracy : ~80%
        {off−road, urban, major/trunk road,multilane motorway/carriageway}
        Two class problem , accuracy : ~90%
        {off−road, on−road}
       A near real time classification rate of 1Hz. (i.e.,one frame
        classification per second)



    3
Introduction
       Colour based off-road environment and terrain type
        classification[3]
       Texture and neural network for road segmentation[7]
       Detection and classification of highway lanes using
        vehicle motion trajectories[31]




    4
Road image subregions




5
Feature extraction and representation
       Color Features
           Choice color space




    6
Feature extraction and representation
       Color Features
           Each such channel of each subregion as the normalized histogram
            distribution.
           Mean , standard deviation , and entropy.




               A given color value (indexed k = 1, . . . , L) occurs with
               probability pk
           Each color channel is summarized as a color feature vector of
            combining the histogram (quantized to 10 “bins”)
           13-value , 7 channel , 91-D color descriptor for each image frame.



    7
Feature extraction and representation
       Texture Features
           grey-level co-occurrence matrix (GLCM) statistics
           localized orientation is defined with as {N,S, E,W,NW,NE,SW,SE}




                   Original image                Co-occurrence Matrix

    8
Feature extraction and representation
       Texture Features
           grey-level co-occurrence matrix (GLCM) statistics




              Co-occurrence Matrix               Stochastic Matrix



    9
Feature extraction and representation
    Texture Features
        grey-level co-occurrence matrix (GLCM) statistics




    10
Feature extraction and representation
    Texture Features
        grey-level co-occurrence matrix (GLCM) statistics




     M(i, j) is the (i, j)th entry in GLCM M with dimension(colsx
     rows)
    11
Feature extraction and representation
    Texture Features
        grey-level co-occurrence matrix (GLCM) statistics




     horizontal standard deviation and mean (σI, μI ),
     vertical standard deviation and mean (σJ, μJ ).

    12
Feature extraction and representation
    Texture Features
        Gabor filters allow the study of the localized spatial distribution of
         the texture.
        The magnitude of the Gabor filter response identifies varying local
         texture frequencies and orientations in the image.
        Use for the extraction of more gradual (low-frequency) textures
         and more generally create discriminative texture descriptors.




    13
Feature extraction and representation
    Texture Features
        The use of only the (N,E) GLCM directions is within this visual
         discriminatory context.
        The Gabor filter in use is itself summarized as a quantized
         histogram
         (10 “bins”)
        Mean, standard deviation, and entropy
        23-value ,3 subregions , 69-D texture feature descriptor for each
         image frame.




    14
Feature extraction and representation
    Edge-Derived Features
        Three additional edge-derived features specific to the road-
         edge subregion.
        Use Canny edge detector
        The set of edges, connected contours , and straight line detected
         is then summarized by the entropy.




    15
Feature Classification
    A 163-D combined feature vector per image frame.
    K-NN and ANN
    Training set : 800 image frames (200 per class ,for four
     classes)
    Four-class
        classes = {off−road, urban, major/trunk road,
                  multilane motorway/carriageway}
    Two-class
        classes = {off−road, on−road}
        {on−road} = {{urban} ∪ {major/trunk road} ∪
                      {multilane motorway/carriageway}}



    16
Experimental result
    Two test video sequences
         Video sequence     Duration    Consist of
         Video sequence 1 40-s          10-s segments of
                                        {off-road, urban, major/trunk
                                        road, multilane
                                        motorway/carriageway}
         Video sequence 2 50-s         10-s segments of
                                       {urban, major/trunk road,
                                       multilane
                                       motorway/carriageway}
         Test image frame              20-s segments of {off-road}
                             Road environment
             600(20-s)       urban
             600(20-s)       major/trunk road
                                                                 30-fps video
             600(20-s)       multilane
                             motorway/carriageway
             900(30-s)       off-road
    17
Experimental result
    K-NN classification




Fig. 2. Video sequence 1. Classification results using k-NN varying
parameter k.
    18
Experimental result
    K-NN classification




Fig. 3. Video sequence 2. Classification results using k-NN varying
parameter k.
    19
Experimental result
    ANN classification
        We employ a classical two-layer network topology with H hidden
         nodes.
        163 input node , 2 or 4 output node (two class or four class).
        The ANN is trained using I iterations.
        The general range of parameter H ={10, . . . , 60} and I = {150, . . . ,
         700}.




    20
Experimental result
    ANN classification




    21
Experimental result
    ANN classification




    22      Fig. 4. Examples of successful ANN classification for four road
            environments
Experimental result
    ANN classification




    23      Fig. 5. Examples of successful ANN classification for two road
            environments (ANN configuration: H = 15 Nodes; I = 200).
Experimental result
    Extended Sequence Results
        full video sequences (representing the complete set of viable data
         gathered over several hours in varying environments)




    24
Experimental result
    Misclassification




    25
Conclusion
    An ANN classifier gives ∼90%–97% successful
     classification for two class ; ∼80%–85% for four-class.
    A k-NN classifier implies the inherent feature overlap
     within the current feature space ,so it’s difficult to classify.
    Future work
        Subregion optimization
        Alternative computationally efficient texture measures
        The efficient of varying weather and lighting condition on
         performance




    26

More Related Content

What's hot

Densebox
DenseboxDensebox
Densebox
冠宇 陳
 
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
Sergio Orts-Escolano
 
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
The Statistical and Applied Mathematical Sciences Institute
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environments
NAVER Engineering
 
Shai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble trackingShai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble tracking
wolf
 
object detection paper review
object detection paper reviewobject detection paper review
object detection paper review
Yoonho Na
 
QGIS training class 2
QGIS training class 2QGIS training class 2
QGIS training class 2
Hiroaki Sengoku
 
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
Dongmin Choi
 
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Dongmin Choi
 
Can graph convolution network learn spatial relations ?
Can graph convolution network learn spatial relations ? Can graph convolution network learn spatial relations ?
Can graph convolution network learn spatial relations ?
azellecourtial
 
GEOPROCESSING IN QGIS
GEOPROCESSING IN QGISGEOPROCESSING IN QGIS
GEOPROCESSING IN QGIS
Swetha A
 
Remotesensingandgisapplications
RemotesensingandgisapplicationsRemotesensingandgisapplications
Remotesensingandgisapplications
imaduddin91
 
A Novel Approach for Ship Recognition using Shape and Texture
A Novel Approach for Ship Recognition using Shape and Texture A Novel Approach for Ship Recognition using Shape and Texture
A Novel Approach for Ship Recognition using Shape and Texture
ijait
 
Compound Structure Detection
Compound Structure DetectionCompound Structure Detection
Compound Structure Detection
Huseyin Gokhan Akcay
 
IRJET - Dehazing of Single Nighttime Haze Image using Superpixel Method
IRJET -  	  Dehazing of Single Nighttime Haze Image using Superpixel MethodIRJET -  	  Dehazing of Single Nighttime Haze Image using Superpixel Method
IRJET - Dehazing of Single Nighttime Haze Image using Superpixel Method
IRJET Journal
 
Computer vision,,summer training programme
Computer vision,,summer training programmeComputer vision,,summer training programme
Computer vision,,summer training programme
Praveen Pandey
 
Image processing with open cv,regular training programme in waayoo.com
Image processing with open cv,regular training programme in waayoo.comImage processing with open cv,regular training programme in waayoo.com
Image processing with open cv,regular training programme in waayoo.com
Praveen Pandey
 
Complex Background Subtraction Using Kalman Filter
Complex Background Subtraction Using Kalman FilterComplex Background Subtraction Using Kalman Filter
Complex Background Subtraction Using Kalman Filter
IJERA Editor
 
Compound Structure Detection
Compound Structure DetectionCompound Structure Detection
Compound Structure Detection
Huseyin Gokhan Akcay
 
07 a70401 remotesensingandgisapplications
07 a70401 remotesensingandgisapplications07 a70401 remotesensingandgisapplications
07 a70401 remotesensingandgisapplications
imaduddin91
 

What's hot (20)

Densebox
DenseboxDensebox
Densebox
 
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
 
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
CLIM: Transition Workshop - Statistical Emulation with Dimension Reduction fo...
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environments
 
Shai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble trackingShai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble tracking
 
object detection paper review
object detection paper reviewobject detection paper review
object detection paper review
 
QGIS training class 2
QGIS training class 2QGIS training class 2
QGIS training class 2
 
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
[Review] BoxInst: High-Performance Instance Segmentation with Box Annotations...
 
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
 
Can graph convolution network learn spatial relations ?
Can graph convolution network learn spatial relations ? Can graph convolution network learn spatial relations ?
Can graph convolution network learn spatial relations ?
 
GEOPROCESSING IN QGIS
GEOPROCESSING IN QGISGEOPROCESSING IN QGIS
GEOPROCESSING IN QGIS
 
Remotesensingandgisapplications
RemotesensingandgisapplicationsRemotesensingandgisapplications
Remotesensingandgisapplications
 
A Novel Approach for Ship Recognition using Shape and Texture
A Novel Approach for Ship Recognition using Shape and Texture A Novel Approach for Ship Recognition using Shape and Texture
A Novel Approach for Ship Recognition using Shape and Texture
 
Compound Structure Detection
Compound Structure DetectionCompound Structure Detection
Compound Structure Detection
 
IRJET - Dehazing of Single Nighttime Haze Image using Superpixel Method
IRJET -  	  Dehazing of Single Nighttime Haze Image using Superpixel MethodIRJET -  	  Dehazing of Single Nighttime Haze Image using Superpixel Method
IRJET - Dehazing of Single Nighttime Haze Image using Superpixel Method
 
Computer vision,,summer training programme
Computer vision,,summer training programmeComputer vision,,summer training programme
Computer vision,,summer training programme
 
Image processing with open cv,regular training programme in waayoo.com
Image processing with open cv,regular training programme in waayoo.comImage processing with open cv,regular training programme in waayoo.com
Image processing with open cv,regular training programme in waayoo.com
 
Complex Background Subtraction Using Kalman Filter
Complex Background Subtraction Using Kalman FilterComplex Background Subtraction Using Kalman Filter
Complex Background Subtraction Using Kalman Filter
 
Compound Structure Detection
Compound Structure DetectionCompound Structure Detection
Compound Structure Detection
 
07 a70401 remotesensingandgisapplications
07 a70401 remotesensingandgisapplications07 a70401 remotesensingandgisapplications
07 a70401 remotesensingandgisapplications
 

Similar to Automatic road environment classification 20121002

Automatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level ImageryAutomatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level Imagery
Sunando Sengupta
 
Learning visual explanations for DCNN-based image classifiers using an attent...
Learning visual explanations for DCNN-based image classifiers using an attent...Learning visual explanations for DCNN-based image classifiers using an attent...
Learning visual explanations for DCNN-based image classifiers using an attent...
VasileiosMezaris
 
Depth estimation do we need to throw old things away
Depth estimation do we need to throw old things awayDepth estimation do we need to throw old things away
Depth estimation do we need to throw old things away
NAVER Engineering
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial Images
Koshy Geoji
 
Performance evaluation of multicast video distribution using lte a in vehicul...
Performance evaluation of multicast video distribution using lte a in vehicul...Performance evaluation of multicast video distribution using lte a in vehicul...
Performance evaluation of multicast video distribution using lte a in vehicul...
Communication Systems & Networks
 
Presentation for korea multimedia(in english)
Presentation for korea multimedia(in english)Presentation for korea multimedia(in english)
Presentation for korea multimedia(in english)
abyssecho
 
JASLA_presentation.pdf
JASLA_presentation.pdfJASLA_presentation.pdf
JASLA_presentation.pdf
Vignesh V Menon
 
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
IAESIJEECS
 
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATIONA DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
cscpconf
 
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Sunando Sengupta
 
TAME: Trainable Attention Mechanism for Explanations
TAME: Trainable Attention Mechanism for ExplanationsTAME: Trainable Attention Mechanism for Explanations
TAME: Trainable Attention Mechanism for Explanations
VasileiosMezaris
 
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATIONA DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
csandit
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imagery
Shunta Saito
 
Performance evaluation with a
Performance evaluation with aPerformance evaluation with a
Performance evaluation with a
ijmnct
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
Azharo7
 
PK_MTP_PPT
PK_MTP_PPTPK_MTP_PPT
PK_MTP_PPT
Pawan Kumar
 
A hybrid controller for vision based navigation of autonomous vehicles in urb...
A hybrid controller for vision based navigation of autonomous vehicles in urb...A hybrid controller for vision based navigation of autonomous vehicles in urb...
A hybrid controller for vision based navigation of autonomous vehicles in urb...
Sushil kumar
 
Meroli Grazing Angle Techinique Pixel2010
Meroli Grazing Angle Techinique Pixel2010Meroli Grazing Angle Techinique Pixel2010
Meroli Grazing Angle Techinique Pixel2010
stefanome
 
Vision Based Traffic Surveillance System
Vision Based Traffic Surveillance SystemVision Based Traffic Surveillance System
Vision Based Traffic Surveillance System
maheshwaraneee
 
An Adaptive Two-level Filtering Technique for Noise Lines in Video Images
An Adaptive Two-level Filtering Technique for Noise Lines in Video ImagesAn Adaptive Two-level Filtering Technique for Noise Lines in Video Images
An Adaptive Two-level Filtering Technique for Noise Lines in Video Images
CSCJournals
 

Similar to Automatic road environment classification 20121002 (20)

Automatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level ImageryAutomatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level Imagery
 
Learning visual explanations for DCNN-based image classifiers using an attent...
Learning visual explanations for DCNN-based image classifiers using an attent...Learning visual explanations for DCNN-based image classifiers using an attent...
Learning visual explanations for DCNN-based image classifiers using an attent...
 
Depth estimation do we need to throw old things away
Depth estimation do we need to throw old things awayDepth estimation do we need to throw old things away
Depth estimation do we need to throw old things away
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial Images
 
Performance evaluation of multicast video distribution using lte a in vehicul...
Performance evaluation of multicast video distribution using lte a in vehicul...Performance evaluation of multicast video distribution using lte a in vehicul...
Performance evaluation of multicast video distribution using lte a in vehicul...
 
Presentation for korea multimedia(in english)
Presentation for korea multimedia(in english)Presentation for korea multimedia(in english)
Presentation for korea multimedia(in english)
 
JASLA_presentation.pdf
JASLA_presentation.pdfJASLA_presentation.pdf
JASLA_presentation.pdf
 
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
09 23sept 8434 10235-1-ed performance (edit ari)update 17jan18tyas
 
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATIONA DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
 
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
 
TAME: Trainable Attention Mechanism for Explanations
TAME: Trainable Attention Mechanism for ExplanationsTAME: Trainable Attention Mechanism for Explanations
TAME: Trainable Attention Mechanism for Explanations
 
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATIONA DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
A DIGITAL COLOR IMAGE WATERMARKING SYSTEM USING BLIND SOURCE SEPARATION
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imagery
 
Performance evaluation with a
Performance evaluation with aPerformance evaluation with a
Performance evaluation with a
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
PK_MTP_PPT
PK_MTP_PPTPK_MTP_PPT
PK_MTP_PPT
 
A hybrid controller for vision based navigation of autonomous vehicles in urb...
A hybrid controller for vision based navigation of autonomous vehicles in urb...A hybrid controller for vision based navigation of autonomous vehicles in urb...
A hybrid controller for vision based navigation of autonomous vehicles in urb...
 
Meroli Grazing Angle Techinique Pixel2010
Meroli Grazing Angle Techinique Pixel2010Meroli Grazing Angle Techinique Pixel2010
Meroli Grazing Angle Techinique Pixel2010
 
Vision Based Traffic Surveillance System
Vision Based Traffic Surveillance SystemVision Based Traffic Surveillance System
Vision Based Traffic Surveillance System
 
An Adaptive Two-level Filtering Technique for Noise Lines in Video Images
An Adaptive Two-level Filtering Technique for Noise Lines in Video ImagesAn Adaptive Two-level Filtering Technique for Noise Lines in Video Images
An Adaptive Two-level Filtering Technique for Noise Lines in Video Images
 

More from es712

Extracting ocean
Extracting oceanExtracting ocean
Extracting ocean
es712
 
Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...
es712
 
Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)
es712
 
Cervical cancer classification using gabor filters 1026
Cervical cancer classification using gabor filters 1026Cervical cancer classification using gabor filters 1026
Cervical cancer classification using gabor filters 1026
es712
 
A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)
es712
 
Pca and kpca of ecg signal
Pca and kpca of ecg signalPca and kpca of ecg signal
Pca and kpca of ecg signal
es712
 
Classification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my spaceClassification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my space
es712
 
Tennis video shot classification based on support vector
Tennis video shot classification based on support vectorTennis video shot classification based on support vector
Tennis video shot classification based on support vector
es712
 
Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)
es712
 

More from es712 (9)

Extracting ocean
Extracting oceanExtracting ocean
Extracting ocean
 
Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...
 
Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)
 
Cervical cancer classification using gabor filters 1026
Cervical cancer classification using gabor filters 1026Cervical cancer classification using gabor filters 1026
Cervical cancer classification using gabor filters 1026
 
A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)
 
Pca and kpca of ecg signal
Pca and kpca of ecg signalPca and kpca of ecg signal
Pca and kpca of ecg signal
 
Classification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my spaceClassification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my space
 
Tennis video shot classification based on support vector
Tennis video shot classification based on support vectorTennis video shot classification based on support vector
Tennis video shot classification based on support vector
 
Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)
 

Recently uploaded

A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
Intelisync
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Wask
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
GDSC PJATK
 
Operating System Used by Users in day-to-day life.pptx
Operating System Used by Users in day-to-day life.pptxOperating System Used by Users in day-to-day life.pptx
Operating System Used by Users in day-to-day life.pptx
Pravash Chandra Das
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
Postman
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
Ivanti
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
Jason Packer
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
Hiike
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
saastr
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
shyamraj55
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
MichaelKnudsen27
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
innovationoecd
 
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
Tatiana Kojar
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
saastr
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
Brandon Minnick, MBA
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
kumardaparthi1024
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
Hiroshi SHIBATA
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
tolgahangng
 

Recently uploaded (20)

A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
 
Operating System Used by Users in day-to-day life.pptx
Operating System Used by Users in day-to-day life.pptxOperating System Used by Users in day-to-day life.pptx
Operating System Used by Users in day-to-day life.pptx
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
 
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
Skybuffer AI: Advanced Conversational and Generative AI Solution on SAP Busin...
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
 

Automatic road environment classification 20121002

  • 1. Advisor : Yin-Fu Huang Automatic Road Environment Classification Intelligent Transportation Systems, IEEE Transactions on Student : Chen-Ju Lai 1
  • 2. Outline  Introduction  Road image subregions  Feature extraction and representation  Feature classification  Experimental result  Conclusion 2
  • 3. Introduction  Input video frame :640X480 resolution Standard digital video camera(30-fps video)  Feature extraction :color ,texture Classification method :k-NN and ANN  Four class problem , accuracy : ~80% {off−road, urban, major/trunk road,multilane motorway/carriageway} Two class problem , accuracy : ~90% {off−road, on−road}  A near real time classification rate of 1Hz. (i.e.,one frame classification per second) 3
  • 4. Introduction  Colour based off-road environment and terrain type classification[3]  Texture and neural network for road segmentation[7]  Detection and classification of highway lanes using vehicle motion trajectories[31] 4
  • 6. Feature extraction and representation  Color Features  Choice color space 6
  • 7. Feature extraction and representation  Color Features  Each such channel of each subregion as the normalized histogram distribution.  Mean , standard deviation , and entropy. A given color value (indexed k = 1, . . . , L) occurs with probability pk  Each color channel is summarized as a color feature vector of combining the histogram (quantized to 10 “bins”)  13-value , 7 channel , 91-D color descriptor for each image frame. 7
  • 8. Feature extraction and representation  Texture Features  grey-level co-occurrence matrix (GLCM) statistics  localized orientation is defined with as {N,S, E,W,NW,NE,SW,SE} Original image Co-occurrence Matrix 8
  • 9. Feature extraction and representation  Texture Features  grey-level co-occurrence matrix (GLCM) statistics Co-occurrence Matrix Stochastic Matrix 9
  • 10. Feature extraction and representation  Texture Features  grey-level co-occurrence matrix (GLCM) statistics 10
  • 11. Feature extraction and representation  Texture Features  grey-level co-occurrence matrix (GLCM) statistics M(i, j) is the (i, j)th entry in GLCM M with dimension(colsx rows) 11
  • 12. Feature extraction and representation  Texture Features  grey-level co-occurrence matrix (GLCM) statistics horizontal standard deviation and mean (σI, μI ), vertical standard deviation and mean (σJ, μJ ). 12
  • 13. Feature extraction and representation  Texture Features  Gabor filters allow the study of the localized spatial distribution of the texture.  The magnitude of the Gabor filter response identifies varying local texture frequencies and orientations in the image.  Use for the extraction of more gradual (low-frequency) textures and more generally create discriminative texture descriptors. 13
  • 14. Feature extraction and representation  Texture Features  The use of only the (N,E) GLCM directions is within this visual discriminatory context.  The Gabor filter in use is itself summarized as a quantized histogram (10 “bins”)  Mean, standard deviation, and entropy  23-value ,3 subregions , 69-D texture feature descriptor for each image frame. 14
  • 15. Feature extraction and representation  Edge-Derived Features  Three additional edge-derived features specific to the road- edge subregion.  Use Canny edge detector  The set of edges, connected contours , and straight line detected is then summarized by the entropy. 15
  • 16. Feature Classification  A 163-D combined feature vector per image frame.  K-NN and ANN  Training set : 800 image frames (200 per class ,for four classes)  Four-class  classes = {off−road, urban, major/trunk road, multilane motorway/carriageway}  Two-class  classes = {off−road, on−road}  {on−road} = {{urban} ∪ {major/trunk road} ∪ {multilane motorway/carriageway}} 16
  • 17. Experimental result  Two test video sequences Video sequence Duration Consist of Video sequence 1 40-s 10-s segments of {off-road, urban, major/trunk road, multilane motorway/carriageway} Video sequence 2 50-s 10-s segments of {urban, major/trunk road, multilane motorway/carriageway} Test image frame 20-s segments of {off-road} Road environment 600(20-s) urban 600(20-s) major/trunk road 30-fps video 600(20-s) multilane motorway/carriageway 900(30-s) off-road 17
  • 18. Experimental result  K-NN classification Fig. 2. Video sequence 1. Classification results using k-NN varying parameter k. 18
  • 19. Experimental result  K-NN classification Fig. 3. Video sequence 2. Classification results using k-NN varying parameter k. 19
  • 20. Experimental result  ANN classification  We employ a classical two-layer network topology with H hidden nodes.  163 input node , 2 or 4 output node (two class or four class).  The ANN is trained using I iterations.  The general range of parameter H ={10, . . . , 60} and I = {150, . . . , 700}. 20
  • 21. Experimental result  ANN classification 21
  • 22. Experimental result  ANN classification 22 Fig. 4. Examples of successful ANN classification for four road environments
  • 23. Experimental result  ANN classification 23 Fig. 5. Examples of successful ANN classification for two road environments (ANN configuration: H = 15 Nodes; I = 200).
  • 24. Experimental result  Extended Sequence Results  full video sequences (representing the complete set of viable data gathered over several hours in varying environments) 24
  • 25. Experimental result  Misclassification 25
  • 26. Conclusion  An ANN classifier gives ∼90%–97% successful classification for two class ; ∼80%–85% for four-class.  A k-NN classifier implies the inherent feature overlap within the current feature space ,so it’s difficult to classify.  Future work  Subregion optimization  Alternative computationally efficient texture measures  The efficient of varying weather and lighting condition on performance 26