SlideShare una empresa de Scribd logo
1 de 39
Depth Images Prediction from a Single RGB Image
Using Deep learning
Deep Learning
May 2017
Soubhi Hadri
Depth Images Prediction from a Single RGB Image
Table of Contents :
Introduction.1
Existing Solutions.2
Dataset and Model.3
Project Code and Results.1
Introduction
Depth Images Prediction from a Single RGB Image
Introduction
-In 3D computer graphics a depth map is an image or image channel
that contains information relating to the distance of the surfaces of
scene objects from a viewpoint.
-RGB-D image : a RGB image and its corresponding depth image
-A depth image is an image channel in which each pixel relates to a
distance between the image plane and the corresponding object in the
RGB image.
Depth Images Prediction from a Single RGB Image
Introduction
To approximate the depth of objects :
• Stereo camera : camera with two/more lenses to simulate human vision.
• Realsense or Kinect to get RGB-D images
• Deep Learning..!!
Existing Solutions
Depth Images Prediction from a Single RGB Image
Deep Learning for depth estimation :
Recently, there are many works to estimate the depth map for RGB image.
Depth Images Prediction from a Single RGB Image
Deep Learning for depth estimation :
Learning Fine-Scaled Depth
Maps from Single RGB Images.
7 Feb 2017
Recently, there are many works to estimate the depth map for RGB image.
Dataset & Model
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
The NYU-Depth V2 data set is comprised of video sequences from a variety of
indoor scenes as recorded by both the RGB and Depth cameras from the
Microsoft Kinect.
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
The NYU-Depth V2 data set is comprised of video sequences from a variety of
indoor scenes as recorded by both the RGB and Depth cameras from the
Microsoft Kinect.
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
The dataset consists of :
• 1449 labeled pairs of aligned RGB and depth images (2.8 GB).
• 407,024 new unlabeled frames - raw rgb, depth (428 GB).
• Toolbox: Useful functions for manipulating the data and labels.
Different parts of the dataset can be downloaded individually.
Authors : Nathan Silberman, Derek Hoiem, Pushmeet Kohli and Rob Fergus
2012
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
The dataset consists of :
• 1449 labeled pairs of aligned RGB and depth images (2.8 GB).
• 407,024 new unlabeled frames - raw rgb, depth (428 GB).
• Toolbox: Useful functions for manipulating the data and labels.
Different parts of the dataset can be downloaded individually.
Authors : Nathan Silberman, Derek Hoiem, Pushmeet Kohli and Rob Fergus
2012
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
For this project:
• Office 1-2 dataset (part of the whole dataset).
• 15 GB after processing RAW data.
• 3522 RGB-D images.
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
For this project:
• Office 1-2 dataset (part of the whole dataset).
• 15 GB after processing RAW data.
• 3522 RGB-D images.
Split the data:
3522
20%
80% 2817
705
2414
403
Training
Validation
Test
Depth Images Prediction from a Single RGB Image
Dataset : NYU Depth V2
Samples of the data:
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Model proposed by JaN IVANECK in his master degree thesis -2016.
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Model proposed by JaN IVANECK in his master degree thesis -2016.
He derived his model from Eigen et al.
Predicting Depth, Surface
Normals and Semantic Labels
with a Common Multi-Scale
Convolutional Architecture.
17 Dec 2015
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Global context network
estimates the rough
depth map of the whole
scene from the input
RGB image.
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Gradient network
estimates horizontal and
vertical gradients of the
depth map globally, for
the whole RGB image.
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Refining network
improves the rough
estimate from the global
context network, utilizing
gradients estimated by the
gradient network and an
input RGB image.
Depth Images Prediction from a Single RGB Image
The Model for Depth Estimation:
Global context network
Architecture of the global context
network
The model is derived from AlexNet.
Depth Images Prediction from a Single RGB Image
Loss Function:
Root mean squared error log(rms-log)
Depth Images Prediction from a Single RGB Image
Training The Network:
1- Scale the output images to [0 1].
2-Subtraction 127 from input images to center the data (kind of normalization).
3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer
Learning).
4-Training the network using batches (batch size = 32) for 35 Epochs.
5- Save the session and model in the end of each Epoch.
Depth Images Prediction from a Single RGB Image
Training The Network:
1- Scale the label images to [0 1].
2-Subtraction 127 from input images to center the data (kind of normalization).
3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer
Learning).
4-Training the network using batches (batch size = 32) for 35 Epochs.
5- Save the session and model in the end of each Epoch.
Depth Images Prediction from a Single RGB Image
Training The Network:
1- Scale the label images to [0 1].
2-Subtraction 127 from input images to center the data (kind of normalization).
3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer
Learning).
4-Training the network using batches (batch size = 32) for 35 Epochs.
5- Save the session and model in the end of each Epoch.
Depth Images Prediction from a Single RGB Image
Training The Network:
1- Scale the label images to [0 1].
2-Subtraction 127 from input images to center the data (kind of normalization).
3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer
Learning).
4-Training the network using batches (batch size = 32) for 35 Epochs.
5- Save the session and model in the end of each Epoch.
Depth Images Prediction from a Single RGB Image
Training The Network:
1- Scale the label images to [0 1].
2-Subtraction 127 from input images to center the data (kind of normalization).
3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer
Learning).
4-Training the network using batches (batch size = 32) for 35 Epochs.
5- Save the session and model in the end of each Epoch.
Depth Images Prediction from a Single RGB Image
Project Functions :
1- split_data : to split and save the data into training/testing/val.npy files.
2- load_data : load data from .npy files.
3- plot_imgs: to plot pair of images.
4- get_next_batch: to get the next batch from training data.
5- loss : calculate the loss function.
6- model: to create model (network structure).
Depth Images Prediction from a Single RGB Image
Project Functions :
7- train: to start training .
8- evaluate: to evaluate new data after restoring the model..
Depth Images Prediction from a Single RGB Image
Project Tools and Libraries:
1- Tensorflow.
2- Slim : lightweight library for defining, training and evaluating complex
models in TensorFlow.
3- Tensorboard.
4- numpy.
5-matplotlib.
Depth Images Prediction from a Single RGB Image
Project Results: 
Training Loss error:
Depth Images Prediction from a Single RGB Image
Project Results: 
Samples of new data:
Depth Images Prediction from a Single RGB Image
Project Results: 
Explanation :
• Training data is not sufficient.
Depth Images Prediction from a Single RGB Image
Project Results: 
Explanation :
• Training data is not sufficient.
In Jan’s experiment:
• Full NYU dataset and 3 dataset generated from the original one.
• Network was trained for 100,000 iterations.
Depth Images Prediction from a Single RGB Image
Project Results: 
Explanation :
• Training data is not sufficient.
In Jan’s experiment:
• Full NYU dataset and 3 dataset generated from the original one.
• Network was trained for 100,000 iterations.
This experiment:
• It took ~26 hours for 30 Epochs.
Depth Images Prediction from a Single RGB Image
Project :
The project code and data will be available on GitHub:
https://github.com/SubhiH/Depth-Estimation-Deep-Learning
Depth Images Prediction from a Single RGB Image
Resources :
-https://arxiv.org/pdf/1607.00730.pdf
-http://janivanecky.com/
-http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html
Thank You

Más contenido relacionado

La actualidad más candente

Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
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 awayNAVER Engineering
 
Recent Progress on Object Detection_20170331
Recent Progress on Object Detection_20170331Recent Progress on Object Detection_20170331
Recent Progress on Object Detection_20170331Jihong Kang
 
Understanding neural radiance fields
Understanding neural radiance fieldsUnderstanding neural radiance fields
Understanding neural radiance fieldsVarun Bhaseen
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
Digital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial DomainDigital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial DomainMostafa G. M. Mostafa
 
Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Universitat Politècnica de Catalunya
 
Depth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIDepth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIYu Huang
 
Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageWei Yang
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksUsman Qayyum
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learningYu Huang
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Universitat Politècnica de Catalunya
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNavneetPaul2
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkNader Karimi
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learningAntonio Rueda-Toicen
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learningpratik pratyay
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization11mr11mahesh
 
IMAGE PROCESSING - MATHANKUMAR.S - VMKVEC
IMAGE PROCESSING - MATHANKUMAR.S - VMKVECIMAGE PROCESSING - MATHANKUMAR.S - VMKVEC
IMAGE PROCESSING - MATHANKUMAR.S - VMKVECMathankumar S
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detectionchettykulkarni
 

La actualidad más candente (20)

Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
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
 
Recent Progress on Object Detection_20170331
Recent Progress on Object Detection_20170331Recent Progress on Object Detection_20170331
Recent Progress on Object Detection_20170331
 
Understanding neural radiance fields
Understanding neural radiance fieldsUnderstanding neural radiance fields
Understanding neural radiance fields
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
 
Digital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial DomainDigital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial Domain
 
Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)
 
Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...
 
Depth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIDepth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors II
 
Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single image
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural Networks
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learning
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization
 
IMAGE PROCESSING - MATHANKUMAR.S - VMKVEC
IMAGE PROCESSING - MATHANKUMAR.S - VMKVECIMAGE PROCESSING - MATHANKUMAR.S - VMKVEC
IMAGE PROCESSING - MATHANKUMAR.S - VMKVEC
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detection
 

Similar a Depth estimation using deep learning

SeRanet introduction
SeRanet introductionSeRanet introduction
SeRanet introductionKosuke Nakago
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsPetteriTeikariPhD
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image ProcessingAnkur Nanda
 
Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Tech Podcast Night
 
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMeetupDataScienceRoma
 
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...KIMMINHA3
 
Techniques for effective and efficient fire detection from social media images
Techniques for effective and efficient fire detection from social media imagesTechniques for effective and efficient fire detection from social media images
Techniques for effective and efficient fire detection from social media imagesUniversidade de São Paulo
 
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...Universitat Politècnica de Catalunya
 
Optimized Feedforward Network of CNN with Xnor Final Presentation
Optimized Feedforward Network of CNN with Xnor Final PresentationOptimized Feedforward Network of CNN with Xnor Final Presentation
Optimized Feedforward Network of CNN with Xnor Final PresentationIndiana University Bloomington
 
cvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxcvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxPyariMohanJena
 
ppt 20BET1024.pptx
ppt 20BET1024.pptxppt 20BET1024.pptx
ppt 20BET1024.pptxManeetBali
 
Ijmsr 2016-10
Ijmsr 2016-10Ijmsr 2016-10
Ijmsr 2016-10ijmsr
 
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...Savvas Chatzichristofis
 
Coin recognition using matlab
Coin recognition using matlabCoin recognition using matlab
Coin recognition using matlabslmnsvn
 
Computer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureComputer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureSanghamitra Deb
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Surveys of Image Recoginition.ppt
Surveys of Image Recoginition.pptSurveys of Image Recoginition.ppt
Surveys of Image Recoginition.pptSarang Rakhecha
 

Similar a Depth estimation using deep learning (20)

SeRanet introduction
SeRanet introductionSeRanet introduction
SeRanet introduction
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problems
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界
 
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image Processing
 
[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp
 
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
 
Techniques for effective and efficient fire detection from social media images
Techniques for effective and efficient fire detection from social media imagesTechniques for effective and efficient fire detection from social media images
Techniques for effective and efficient fire detection from social media images
 
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...
Visualization of Deep Learning Models (D1L6 2017 UPC Deep Learning for Comput...
 
Optimized Feedforward Network of CNN with Xnor Final Presentation
Optimized Feedforward Network of CNN with Xnor Final PresentationOptimized Feedforward Network of CNN with Xnor Final Presentation
Optimized Feedforward Network of CNN with Xnor Final Presentation
 
MAJOR PROJECT
MAJOR PROJECT MAJOR PROJECT
MAJOR PROJECT
 
cvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxcvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptx
 
ppt 20BET1024.pptx
ppt 20BET1024.pptxppt 20BET1024.pptx
ppt 20BET1024.pptx
 
Ijmsr 2016-10
Ijmsr 2016-10Ijmsr 2016-10
Ijmsr 2016-10
 
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...
Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (S...
 
Coin recognition using matlab
Coin recognition using matlabCoin recognition using matlab
Coin recognition using matlab
 
Computer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureComputer Vision Landscape : Present and Future
Computer Vision Landscape : Present and Future
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Surveys of Image Recoginition.ppt
Surveys of Image Recoginition.pptSurveys of Image Recoginition.ppt
Surveys of Image Recoginition.ppt
 

Último

Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx959SahilShah
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)Dr SOUNDIRARAJ N
 
Class 1 | NFPA 72 | Overview Fire Alarm System
Class 1 | NFPA 72 | Overview Fire Alarm SystemClass 1 | NFPA 72 | Overview Fire Alarm System
Class 1 | NFPA 72 | Overview Fire Alarm Systemirfanmechengr
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfROCENODodongVILLACER
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEroselinkalist12
 
Concrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxConcrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxKartikeyaDwivedi3
 
Piping Basic stress analysis by engineering
Piping Basic stress analysis by engineeringPiping Basic stress analysis by engineering
Piping Basic stress analysis by engineeringJuanCarlosMorales19600
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
 
Solving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptSolving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptJasonTagapanGulla
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitterShivangiSharma879191
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girlsssuser7cb4ff
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxk795866
 

Último (20)

Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx
 
young call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Serviceyoung call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Service
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
 
Class 1 | NFPA 72 | Overview Fire Alarm System
Class 1 | NFPA 72 | Overview Fire Alarm SystemClass 1 | NFPA 72 | Overview Fire Alarm System
Class 1 | NFPA 72 | Overview Fire Alarm System
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdf
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
 
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
 
Concrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxConcrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptx
 
Piping Basic stress analysis by engineering
Piping Basic stress analysis by engineeringPiping Basic stress analysis by engineering
Piping Basic stress analysis by engineering
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
 
POWER SYSTEMS-1 Complete notes examples
POWER SYSTEMS-1 Complete notes  examplesPOWER SYSTEMS-1 Complete notes  examples
POWER SYSTEMS-1 Complete notes examples
 
Solving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptSolving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.ppt
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girls
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptx
 

Depth estimation using deep learning

  • 1. Depth Images Prediction from a Single RGB Image Using Deep learning Deep Learning May 2017 Soubhi Hadri
  • 2. Depth Images Prediction from a Single RGB Image Table of Contents : Introduction.1 Existing Solutions.2 Dataset and Model.3 Project Code and Results.1
  • 4. Depth Images Prediction from a Single RGB Image Introduction -In 3D computer graphics a depth map is an image or image channel that contains information relating to the distance of the surfaces of scene objects from a viewpoint. -RGB-D image : a RGB image and its corresponding depth image -A depth image is an image channel in which each pixel relates to a distance between the image plane and the corresponding object in the RGB image.
  • 5. Depth Images Prediction from a Single RGB Image Introduction To approximate the depth of objects : • Stereo camera : camera with two/more lenses to simulate human vision. • Realsense or Kinect to get RGB-D images • Deep Learning..!!
  • 7. Depth Images Prediction from a Single RGB Image Deep Learning for depth estimation : Recently, there are many works to estimate the depth map for RGB image.
  • 8. Depth Images Prediction from a Single RGB Image Deep Learning for depth estimation : Learning Fine-Scaled Depth Maps from Single RGB Images. 7 Feb 2017 Recently, there are many works to estimate the depth map for RGB image.
  • 10. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect.
  • 11. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect.
  • 12. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 The dataset consists of : • 1449 labeled pairs of aligned RGB and depth images (2.8 GB). • 407,024 new unlabeled frames - raw rgb, depth (428 GB). • Toolbox: Useful functions for manipulating the data and labels. Different parts of the dataset can be downloaded individually. Authors : Nathan Silberman, Derek Hoiem, Pushmeet Kohli and Rob Fergus 2012
  • 13. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 The dataset consists of : • 1449 labeled pairs of aligned RGB and depth images (2.8 GB). • 407,024 new unlabeled frames - raw rgb, depth (428 GB). • Toolbox: Useful functions for manipulating the data and labels. Different parts of the dataset can be downloaded individually. Authors : Nathan Silberman, Derek Hoiem, Pushmeet Kohli and Rob Fergus 2012
  • 14. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 For this project: • Office 1-2 dataset (part of the whole dataset). • 15 GB after processing RAW data. • 3522 RGB-D images.
  • 15. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 For this project: • Office 1-2 dataset (part of the whole dataset). • 15 GB after processing RAW data. • 3522 RGB-D images. Split the data: 3522 20% 80% 2817 705 2414 403 Training Validation Test
  • 16. Depth Images Prediction from a Single RGB Image Dataset : NYU Depth V2 Samples of the data:
  • 17. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Model proposed by JaN IVANECK in his master degree thesis -2016.
  • 18. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Model proposed by JaN IVANECK in his master degree thesis -2016. He derived his model from Eigen et al. Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture. 17 Dec 2015
  • 19. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Global context network estimates the rough depth map of the whole scene from the input RGB image.
  • 20. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Gradient network estimates horizontal and vertical gradients of the depth map globally, for the whole RGB image.
  • 21. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Refining network improves the rough estimate from the global context network, utilizing gradients estimated by the gradient network and an input RGB image.
  • 22. Depth Images Prediction from a Single RGB Image The Model for Depth Estimation: Global context network Architecture of the global context network The model is derived from AlexNet.
  • 23. Depth Images Prediction from a Single RGB Image Loss Function: Root mean squared error log(rms-log)
  • 24. Depth Images Prediction from a Single RGB Image Training The Network: 1- Scale the output images to [0 1]. 2-Subtraction 127 from input images to center the data (kind of normalization). 3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer Learning). 4-Training the network using batches (batch size = 32) for 35 Epochs. 5- Save the session and model in the end of each Epoch.
  • 25. Depth Images Prediction from a Single RGB Image Training The Network: 1- Scale the label images to [0 1]. 2-Subtraction 127 from input images to center the data (kind of normalization). 3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer Learning). 4-Training the network using batches (batch size = 32) for 35 Epochs. 5- Save the session and model in the end of each Epoch.
  • 26. Depth Images Prediction from a Single RGB Image Training The Network: 1- Scale the label images to [0 1]. 2-Subtraction 127 from input images to center the data (kind of normalization). 3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer Learning). 4-Training the network using batches (batch size = 32) for 35 Epochs. 5- Save the session and model in the end of each Epoch.
  • 27. Depth Images Prediction from a Single RGB Image Training The Network: 1- Scale the label images to [0 1]. 2-Subtraction 127 from input images to center the data (kind of normalization). 3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer Learning). 4-Training the network using batches (batch size = 32) for 35 Epochs. 5- Save the session and model in the end of each Epoch.
  • 28. Depth Images Prediction from a Single RGB Image Training The Network: 1- Scale the label images to [0 1]. 2-Subtraction 127 from input images to center the data (kind of normalization). 3-Initialize the convolution layers using AlexNet pre-trained CNN (Transfer Learning). 4-Training the network using batches (batch size = 32) for 35 Epochs. 5- Save the session and model in the end of each Epoch.
  • 29. Depth Images Prediction from a Single RGB Image Project Functions : 1- split_data : to split and save the data into training/testing/val.npy files. 2- load_data : load data from .npy files. 3- plot_imgs: to plot pair of images. 4- get_next_batch: to get the next batch from training data. 5- loss : calculate the loss function. 6- model: to create model (network structure).
  • 30. Depth Images Prediction from a Single RGB Image Project Functions : 7- train: to start training . 8- evaluate: to evaluate new data after restoring the model..
  • 31. Depth Images Prediction from a Single RGB Image Project Tools and Libraries: 1- Tensorflow. 2- Slim : lightweight library for defining, training and evaluating complex models in TensorFlow. 3- Tensorboard. 4- numpy. 5-matplotlib.
  • 32. Depth Images Prediction from a Single RGB Image Project Results:  Training Loss error:
  • 33. Depth Images Prediction from a Single RGB Image Project Results:  Samples of new data:
  • 34. Depth Images Prediction from a Single RGB Image Project Results:  Explanation : • Training data is not sufficient.
  • 35. Depth Images Prediction from a Single RGB Image Project Results:  Explanation : • Training data is not sufficient. In Jan’s experiment: • Full NYU dataset and 3 dataset generated from the original one. • Network was trained for 100,000 iterations.
  • 36. Depth Images Prediction from a Single RGB Image Project Results:  Explanation : • Training data is not sufficient. In Jan’s experiment: • Full NYU dataset and 3 dataset generated from the original one. • Network was trained for 100,000 iterations. This experiment: • It took ~26 hours for 30 Epochs.
  • 37. Depth Images Prediction from a Single RGB Image Project : The project code and data will be available on GitHub: https://github.com/SubhiH/Depth-Estimation-Deep-Learning
  • 38. Depth Images Prediction from a Single RGB Image Resources : -https://arxiv.org/pdf/1607.00730.pdf -http://janivanecky.com/ -http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html