SlideShare uma empresa Scribd logo
1 de 28
Baixar para ler offline
Online Stochastic Tensor Decomposition for
Background Subtraction in Multispectral
Video Sequences
Andrews Sobral1, Sajid Javed2, Soon Ki Jung2, Thierry Bouwmans1, and
El-hadi Zahzah1
1Laboratoire MIA (Mathematiques Image de Applications)
Universite de La Rochelle, France
2Virtual Reality Laboratory, School of Computer Science and Engineering
Kyungpook National University, Republic of Korea
18 December, 2015
• Introduction
• Tensor Decomposition
–Methods
–Challenges
• Proposed Methodology
• Experimental Evaluations
• Conclusion
2
Main Contents
• What is Tensor?
– multi-dimensional numerical array
• generalization of conventional arrays
– Matrix
o second-order tensor: rank (2) tensor
– Vector
o first-order tensor: rank(1) tensor
• Higher order tensors (order≥3): stores data in a
multi-dimensional array
– Main operation
• unfolding or matricization
– reformating tensors into matrices
o frontal, vertical, and horizontal
3
Introduction
• Video or sequence of images as a tensor
4
Introduction-cont..
• Is it possible to decompose tensor for Background subtraction application?
– 2 components
• Multi-dimensional low-rank tensor (corresponds to
background model)
• Multi-dimensional sparse tensor (belongs to moving objects)
• Matrix-based decomposition
– matrix considers only single dimensional (i.e., grayscale)
– spatial correlation loss
• erroneous foreground regions
• Tensor-based decomposition
– multi-dimensional data is considered (3d or 4rth order tensor)
– multi-aspects generalization of matrices
5
Tensor Decomposition
• Example: background subtraction via tensor decomposition under convex
optimization framework
6
Tensor Decomposition
MaskInput Low-rank Sparse
Frontal slices
• Methods
– Tucker/HOSVD
– CANDECOMP-PARAFAC(CP)
– NTF (Non-negative Tensor Factorization)
– NTD (Non-negative Tucker Decomposition)
– NCP (Non-negative CP Decomposition)
• Major Challenges
– Batch optimization
– Higher Order SVD computation
– Computational complexities
– Designed for only monochromatic (i.e., grayscale) or trichromatic (i.e.,
RGB) cameras.
– Real-time processing is not desirable
7
Tensor Decomposition
• Is it possible to make “Online Tensor Decomposition method for RGB as
well as Multispectral bands for background subtraction”?
– Main contributions
• Online Stochastic framework for Tensor Decomposition (OSTD)
– computationally good
– less memory cost
• OSTD for Multi-Spectral Video Sequences (MSVS)
– RGB is not sufficient for color saturation/ shadows/ reflections
– Multi-spectral bands can improve foreground segmentation
8
Proposed Methodology
9
Proposed Framework
Input
Multi-spectral
Bands
𝑁 𝑡ℎ Order
Tensor
OSTD: Online
Stochastic Tensor
Decomposition
Low-rank
Sparse
• Let say 𝑁 𝑡ℎ order observation tensor
– corrupted by outliers,
• Main assumption
– can be reconstructed by the combination of
• low-rank component,
• sparse component,
– convex optimization framework
• represents the nuclear norm of 𝑖 𝑡ℎ mode
• represents the 𝑙1 norm
• Stochastic/Online optimization proposed by [Feng et.al 2013]
10
OSTD: The Model
• Main notion
– process only one frame at a time instance t
• MSVS: process each k band
• Nuclear norm is re-formulated
– Decompose nuclear norm into
• explicit product of basis and coefficients
• re-formulated norm is used proposed by [Feng et.al 2013]
– p ambient dimension, and r is rank
• Stochastic optimization
11
OSTD: Online Optimization
= 𝑖𝑛𝑓
𝐿∈ℝ 𝑝×𝑟,𝑅∈ℝ 𝑛×𝑟
1
2
( | 𝐿𝑖 | 𝐹
2
+ | 𝑅𝑖 | 𝐹
2
) 𝑠. 𝑡. , = 𝐿𝑖 𝑅𝑖
𝑇
• Advantages
– no batch processing
– iteratively update the basis
– used for each 𝑖 𝑡ℎ mode
• Major Processing: 3 Steps
– Low-rank approximation
• Initialize the basis, L
– Bilateral Random Projections (BRP) method
o L, Y, A are all random matrices
o speed-up low-rank recovery: fast convergence
• SVD decay slowly
12
OSTD cont…
𝐿 = 𝑌1(𝐴1
𝑇
𝑌1)−1
𝑌2
𝑇
• Find coefficients R as
• Fix R, and updated basis
– use block-coordinate decent method
– incremental updated
• Sparse outlier estimation
– M = −L𝑟 𝑡 of k element
• Background Model:
• Sparse Component:
13
OSTD cont…
𝑒 𝑡
=
𝑀 𝑡 𝑘 − λ2, 𝑖𝑓 𝑀 𝑡 𝑘 > λ2
𝑀 𝑡 𝑘 + λ2, 𝑖𝑓𝑀 𝑡 𝑘 < λ2
𝑟 𝑡 = (𝐿 𝑇 𝐿 + λ1 𝐼)−1 𝐿 𝑇 −𝑒 𝑡−1
• Synthetic Evaluation
– True low-rank tensor of size 30 × 30 × 30 is generated
by rank-3 factor matrices
• 𝑍 𝑛
∈ ℝ30×3
, where 𝑛 = 1,2,3
• random entries are corrupted
– Relative Root Square Error (RRSE) measure is computed
• Two different cases are considered
– smaller magnitude of true data
– with a higher magnitude
14
Experimental Evaluations
RRSE=
• Comparison Methods: Batch processing algorithms
– Bayesian Robust Tensor Factorization (BRTF) [Q. Zhao et.al 2014]
– Higher Order RPCA (HORPCA) [D. GoldFarb et.al 2013]
– Tensor Factorization method CP-ALS [T. Kolda 2009]
– Higher Order SVD (HOSVD) [L. De Lathauwer et.al 2013]
15
Experimental Evaluations
• Multispectral Video Sequences (MSVS)
– Acquisition
• commercial camera (FD-1665-MS)
– 7 spectral narrow bands = 6 visible + 1 NIR spectral band
– 5 video sequences
• 1 indoor video sequence
• 4 outdoor scenes
• frame Size: [658 × 491 × 3] with 250 to 2300 no. of frames
• frame rate: depends on overall scene illuminations
– 5 fps for dark scene and 15 fps for brighter one
– Main Challenges
• gradual illumination changes, shadows, and intermittent
object motion
• camouflage (color similarity between background and objects)
16
Experimental Evaluations
• MSVS dataset
– “integration of MS bands improve the foreground segmentation”
17
Experimental Evaluations
Video1 Video2 Video 3 Video 4 Video 5
• Visual Results of Video 1
18
Experimental Evaluations
RGB VS-1 VS-2 VS-3 VS-4 VS-5 VS-6 NIR
Input
Low-
rank
Sparse
Mask
• Visual Results of Video 2
19
Experimental Evaluations
RGB VS-1 VS-2 VS-3 VS-4 VS-5 VS-6 NIR
Input
Low-
rank
Sparse
Mask
20
Experimental Evaluations
Video 1
Video 2
Video 3
Video 4
Video 5
Input Low-rank Ground
Truth
RGB
Mask
6 VSB
Mask
1 NIR
Mask
• Qualitative Comparison
– White: True positive (TP) pixels
– Black: True negatives (TN) pixels
– Red: False positives (FP) pixels
– Green: False negatives (FN) pixels
21
Experimental Evaluations
Video 2
Video 3
Video 5
Input Ground
Truth
Proposed BRTF HORPCA CP-ALS
• Quantitative Analysis
– F measure score is computed for RGB and MS bands for comparison
22
Experimental Evaluations
• Time Complexity
– Independent number of samples
• grows linearly to the image resolution
23
Experimental Evaluations
• Video demo 1
– color saturation issue
24
Experimental Evaluations
Input Ground
Truth
RGB
Mask
MS
Mask
• Video demo 2
– color saturation issue
25
Experimental Evaluations
Input Ground
Truth
RGB
Mask
MS
Mask
• Video demo 3
– shadows, dynamic backgrounds, intermittent object motion
26
Experimental Evaluations
Input Ground
Truth
RGB
Mask
MS
Mask
• Online stochastic optimization framework is proposed
– tensor decomposition into low-rank and sparse tensor
• computationally attractive
• real-time processing achieved
– provides great potential for multi-spectral bands
• Limitation
– proposed method is not stable for RGB image features
• achieve promising accuracy with the integration of MS
spectral bands
• Future work
– disparity features will be integrated
– can be extended for visual tracker as Low-rank sparse tracking
27
Conclusion
28

Mais conteúdo relacionado

Mais procurados

Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsRyan B Harvey, CSDP, CSM
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)Universitat Politècnica de Catalunya
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]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
 
Incremental and Multi-feature Tensor Subspace Learning applied for Background...
Incremental and Multi-feature Tensor Subspace Learning applied for Background...Incremental and Multi-feature Tensor Subspace Learning applied for Background...
Incremental and Multi-feature Tensor Subspace Learning applied for Background...ActiveEon
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)Shunta Saito
 
[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
 
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
 
VIBE: Video Inference for Human Body Pose and Shape Estimation
VIBE: Video Inference for Human Body Pose and Shape EstimationVIBE: Video Inference for Human Body Pose and Shape Estimation
VIBE: Video Inference for Human Body Pose and Shape EstimationArithmer Inc.
 
Deep Beleif Networks
Deep Beleif NetworksDeep Beleif Networks
Deep Beleif NetworksDeepak Singh
 
Recent Progress in RNN and NLP
Recent Progress in RNN and NLPRecent Progress in RNN and NLP
Recent Progress in RNN and NLPhytae
 
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...Universitat Politècnica de Catalunya
 
Review: You Only Look One-level Feature
Review: You Only Look One-level FeatureReview: You Only Look One-level Feature
Review: You Only Look One-level FeatureDongmin Choi
 
Recent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionRecent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionKai-Wen Zhao
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Universitat Politècnica de Catalunya
 
Summarizing videos with Attention
Summarizing videos with AttentionSummarizing videos with Attention
Summarizing videos with AttentionArithmer Inc.
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationDat Nguyen
 
Webinar on Graph Neural Networks
Webinar on Graph Neural NetworksWebinar on Graph Neural Networks
Webinar on Graph Neural NetworksLucaCrociani1
 

Mais procurados (20)

Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
 
crfasrnn_presentation
crfasrnn_presentationcrfasrnn_presentation
crfasrnn_presentation
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]
 
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...
 
Incremental and Multi-feature Tensor Subspace Learning applied for Background...
Incremental and Multi-feature Tensor Subspace Learning applied for Background...Incremental and Multi-feature Tensor Subspace Learning applied for Background...
Incremental and Multi-feature Tensor Subspace Learning applied for Background...
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
 
[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...
 
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)
 
VIBE: Video Inference for Human Body Pose and Shape Estimation
VIBE: Video Inference for Human Body Pose and Shape EstimationVIBE: Video Inference for Human Body Pose and Shape Estimation
VIBE: Video Inference for Human Body Pose and Shape Estimation
 
Deep Beleif Networks
Deep Beleif NetworksDeep Beleif Networks
Deep Beleif Networks
 
Recent Progress in RNN and NLP
Recent Progress in RNN and NLPRecent Progress in RNN and NLP
Recent Progress in RNN and NLP
 
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
 
Review: You Only Look One-level Feature
Review: You Only Look One-level FeatureReview: You Only Look One-level Feature
Review: You Only Look One-level Feature
 
Recent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionRecent Object Detection Research & Person Detection
Recent Object Detection Research & Person Detection
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
 
Summarizing videos with Attention
Summarizing videos with AttentionSummarizing videos with Attention
Summarizing videos with Attention
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance Segmentation
 
Webinar on Graph Neural Networks
Webinar on Graph Neural NetworksWebinar on Graph Neural Networks
Webinar on Graph Neural Networks
 

Semelhante a Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences

An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learningmilad abbasi
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningMehrnaz Faraz
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNNJunho Cho
 
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
 
SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15Hao Zhuang
 
Virus, Vaccines, Genes and Quantum - 2020-06-18
Virus, Vaccines, Genes and Quantum - 2020-06-18Virus, Vaccines, Genes and Quantum - 2020-06-18
Virus, Vaccines, Genes and Quantum - 2020-06-18Aritra Sarkar
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...MLconf
 
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화NAVER Engineering
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
DC04 Image Compression Standards.pdf
DC04 Image Compression Standards.pdfDC04 Image Compression Standards.pdf
DC04 Image Compression Standards.pdfssuser1bd081
 
Tomoya Sato Master Thesis
Tomoya Sato Master ThesisTomoya Sato Master Thesis
Tomoya Sato Master Thesispflab
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterYousef Fadila
 
Nonlinear dimension reduction
Nonlinear dimension reductionNonlinear dimension reduction
Nonlinear dimension reductionYan Xu
 
Online video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkOnline video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkNAVER Engineering
 
Tensorizing Neural Network
Tensorizing Neural NetworkTensorizing Neural Network
Tensorizing Neural NetworkRuochun Tzeng
 
Week 12 Dimensionality Reduction Bagian 1
Week 12 Dimensionality Reduction Bagian 1Week 12 Dimensionality Reduction Bagian 1
Week 12 Dimensionality Reduction Bagian 1khairulhuda242
 

Semelhante a Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences (20)

An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNN
 
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15
 
Virus, Vaccines, Genes and Quantum - 2020-06-18
Virus, Vaccines, Genes and Quantum - 2020-06-18Virus, Vaccines, Genes and Quantum - 2020-06-18
Virus, Vaccines, Genes and Quantum - 2020-06-18
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
 
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화
대용량 데이터 분석을 위한 병렬 Clustering 알고리즘 최적화
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
DC04 Image Compression Standards.pdf
DC04 Image Compression Standards.pdfDC04 Image Compression Standards.pdf
DC04 Image Compression Standards.pdf
 
Tomoya Sato Master Thesis
Tomoya Sato Master ThesisTomoya Sato Master Thesis
Tomoya Sato Master Thesis
 
Temporal Segment Network
Temporal Segment NetworkTemporal Segment Network
Temporal Segment Network
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity Calorimeter
 
Nonlinear dimension reduction
Nonlinear dimension reductionNonlinear dimension reduction
Nonlinear dimension reduction
 
Understandig PCA and LDA
Understandig PCA and LDAUnderstandig PCA and LDA
Understandig PCA and LDA
 
Online video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkOnline video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident network
 
convolutional_rbm.ppt
convolutional_rbm.pptconvolutional_rbm.ppt
convolutional_rbm.ppt
 
Tensorizing Neural Network
Tensorizing Neural NetworkTensorizing Neural Network
Tensorizing Neural Network
 
Week 12 Dimensionality Reduction Bagian 1
Week 12 Dimensionality Reduction Bagian 1Week 12 Dimensionality Reduction Bagian 1
Week 12 Dimensionality Reduction Bagian 1
 

Último

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 

Último (20)

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 

Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences

  • 1. Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences Andrews Sobral1, Sajid Javed2, Soon Ki Jung2, Thierry Bouwmans1, and El-hadi Zahzah1 1Laboratoire MIA (Mathematiques Image de Applications) Universite de La Rochelle, France 2Virtual Reality Laboratory, School of Computer Science and Engineering Kyungpook National University, Republic of Korea 18 December, 2015
  • 2. • Introduction • Tensor Decomposition –Methods –Challenges • Proposed Methodology • Experimental Evaluations • Conclusion 2 Main Contents
  • 3. • What is Tensor? – multi-dimensional numerical array • generalization of conventional arrays – Matrix o second-order tensor: rank (2) tensor – Vector o first-order tensor: rank(1) tensor • Higher order tensors (order≥3): stores data in a multi-dimensional array – Main operation • unfolding or matricization – reformating tensors into matrices o frontal, vertical, and horizontal 3 Introduction
  • 4. • Video or sequence of images as a tensor 4 Introduction-cont..
  • 5. • Is it possible to decompose tensor for Background subtraction application? – 2 components • Multi-dimensional low-rank tensor (corresponds to background model) • Multi-dimensional sparse tensor (belongs to moving objects) • Matrix-based decomposition – matrix considers only single dimensional (i.e., grayscale) – spatial correlation loss • erroneous foreground regions • Tensor-based decomposition – multi-dimensional data is considered (3d or 4rth order tensor) – multi-aspects generalization of matrices 5 Tensor Decomposition
  • 6. • Example: background subtraction via tensor decomposition under convex optimization framework 6 Tensor Decomposition MaskInput Low-rank Sparse Frontal slices
  • 7. • Methods – Tucker/HOSVD – CANDECOMP-PARAFAC(CP) – NTF (Non-negative Tensor Factorization) – NTD (Non-negative Tucker Decomposition) – NCP (Non-negative CP Decomposition) • Major Challenges – Batch optimization – Higher Order SVD computation – Computational complexities – Designed for only monochromatic (i.e., grayscale) or trichromatic (i.e., RGB) cameras. – Real-time processing is not desirable 7 Tensor Decomposition
  • 8. • Is it possible to make “Online Tensor Decomposition method for RGB as well as Multispectral bands for background subtraction”? – Main contributions • Online Stochastic framework for Tensor Decomposition (OSTD) – computationally good – less memory cost • OSTD for Multi-Spectral Video Sequences (MSVS) – RGB is not sufficient for color saturation/ shadows/ reflections – Multi-spectral bands can improve foreground segmentation 8 Proposed Methodology
  • 9. 9 Proposed Framework Input Multi-spectral Bands 𝑁 𝑡ℎ Order Tensor OSTD: Online Stochastic Tensor Decomposition Low-rank Sparse
  • 10. • Let say 𝑁 𝑡ℎ order observation tensor – corrupted by outliers, • Main assumption – can be reconstructed by the combination of • low-rank component, • sparse component, – convex optimization framework • represents the nuclear norm of 𝑖 𝑡ℎ mode • represents the 𝑙1 norm • Stochastic/Online optimization proposed by [Feng et.al 2013] 10 OSTD: The Model
  • 11. • Main notion – process only one frame at a time instance t • MSVS: process each k band • Nuclear norm is re-formulated – Decompose nuclear norm into • explicit product of basis and coefficients • re-formulated norm is used proposed by [Feng et.al 2013] – p ambient dimension, and r is rank • Stochastic optimization 11 OSTD: Online Optimization = 𝑖𝑛𝑓 𝐿∈ℝ 𝑝×𝑟,𝑅∈ℝ 𝑛×𝑟 1 2 ( | 𝐿𝑖 | 𝐹 2 + | 𝑅𝑖 | 𝐹 2 ) 𝑠. 𝑡. , = 𝐿𝑖 𝑅𝑖 𝑇
  • 12. • Advantages – no batch processing – iteratively update the basis – used for each 𝑖 𝑡ℎ mode • Major Processing: 3 Steps – Low-rank approximation • Initialize the basis, L – Bilateral Random Projections (BRP) method o L, Y, A are all random matrices o speed-up low-rank recovery: fast convergence • SVD decay slowly 12 OSTD cont… 𝐿 = 𝑌1(𝐴1 𝑇 𝑌1)−1 𝑌2 𝑇
  • 13. • Find coefficients R as • Fix R, and updated basis – use block-coordinate decent method – incremental updated • Sparse outlier estimation – M = −L𝑟 𝑡 of k element • Background Model: • Sparse Component: 13 OSTD cont… 𝑒 𝑡 = 𝑀 𝑡 𝑘 − λ2, 𝑖𝑓 𝑀 𝑡 𝑘 > λ2 𝑀 𝑡 𝑘 + λ2, 𝑖𝑓𝑀 𝑡 𝑘 < λ2 𝑟 𝑡 = (𝐿 𝑇 𝐿 + λ1 𝐼)−1 𝐿 𝑇 −𝑒 𝑡−1
  • 14. • Synthetic Evaluation – True low-rank tensor of size 30 × 30 × 30 is generated by rank-3 factor matrices • 𝑍 𝑛 ∈ ℝ30×3 , where 𝑛 = 1,2,3 • random entries are corrupted – Relative Root Square Error (RRSE) measure is computed • Two different cases are considered – smaller magnitude of true data – with a higher magnitude 14 Experimental Evaluations RRSE=
  • 15. • Comparison Methods: Batch processing algorithms – Bayesian Robust Tensor Factorization (BRTF) [Q. Zhao et.al 2014] – Higher Order RPCA (HORPCA) [D. GoldFarb et.al 2013] – Tensor Factorization method CP-ALS [T. Kolda 2009] – Higher Order SVD (HOSVD) [L. De Lathauwer et.al 2013] 15 Experimental Evaluations
  • 16. • Multispectral Video Sequences (MSVS) – Acquisition • commercial camera (FD-1665-MS) – 7 spectral narrow bands = 6 visible + 1 NIR spectral band – 5 video sequences • 1 indoor video sequence • 4 outdoor scenes • frame Size: [658 × 491 × 3] with 250 to 2300 no. of frames • frame rate: depends on overall scene illuminations – 5 fps for dark scene and 15 fps for brighter one – Main Challenges • gradual illumination changes, shadows, and intermittent object motion • camouflage (color similarity between background and objects) 16 Experimental Evaluations
  • 17. • MSVS dataset – “integration of MS bands improve the foreground segmentation” 17 Experimental Evaluations Video1 Video2 Video 3 Video 4 Video 5
  • 18. • Visual Results of Video 1 18 Experimental Evaluations RGB VS-1 VS-2 VS-3 VS-4 VS-5 VS-6 NIR Input Low- rank Sparse Mask
  • 19. • Visual Results of Video 2 19 Experimental Evaluations RGB VS-1 VS-2 VS-3 VS-4 VS-5 VS-6 NIR Input Low- rank Sparse Mask
  • 20. 20 Experimental Evaluations Video 1 Video 2 Video 3 Video 4 Video 5 Input Low-rank Ground Truth RGB Mask 6 VSB Mask 1 NIR Mask
  • 21. • Qualitative Comparison – White: True positive (TP) pixels – Black: True negatives (TN) pixels – Red: False positives (FP) pixels – Green: False negatives (FN) pixels 21 Experimental Evaluations Video 2 Video 3 Video 5 Input Ground Truth Proposed BRTF HORPCA CP-ALS
  • 22. • Quantitative Analysis – F measure score is computed for RGB and MS bands for comparison 22 Experimental Evaluations
  • 23. • Time Complexity – Independent number of samples • grows linearly to the image resolution 23 Experimental Evaluations
  • 24. • Video demo 1 – color saturation issue 24 Experimental Evaluations Input Ground Truth RGB Mask MS Mask
  • 25. • Video demo 2 – color saturation issue 25 Experimental Evaluations Input Ground Truth RGB Mask MS Mask
  • 26. • Video demo 3 – shadows, dynamic backgrounds, intermittent object motion 26 Experimental Evaluations Input Ground Truth RGB Mask MS Mask
  • 27. • Online stochastic optimization framework is proposed – tensor decomposition into low-rank and sparse tensor • computationally attractive • real-time processing achieved – provides great potential for multi-spectral bands • Limitation – proposed method is not stable for RGB image features • achieve promising accuracy with the integration of MS spectral bands • Future work – disparity features will be integrated – can be extended for visual tracker as Low-rank sparse tracking 27 Conclusion
  • 28. 28