Pulkit Agrawal Y7322 BVV Sri Raj Dutt Y7110 Sushobhan Nayak Y7460.

Slides:



Advertisements
Similar presentations
Gestures Recognition. Image acquisition Image acquisition at BBC R&D studios in London using eight different viewpoints. Sequence frame-by-frame segmentation.
Advertisements

Chapter 5: Space and Form Form & Pattern Perception: Humans are second to none in processing visual form and pattern information. Our ability to see patterns.
Face Recognition and Biometric Systems Eigenfaces (2)
CS Spring 2009 CS 414 – Multimedia Systems Design Lecture 4 – Digital Image Representation Klara Nahrstedt Spring 2009.
Face Recognition. Introduction Why we are interested in face recognition? Why we are interested in face recognition? Passport control at terminals in.
Extracting Minimalistic Corridor Geometry from Low-Resolution Images Yinxiao Li, Vidya, N. Murali, and Stanley T. Birchfield Department of Electrical and.
The Global Digital Elevation Model (GTOPO30) of Great Basin Location: latitude 38  15’ to 42  N, longitude 118  30’ to 115  30’ W Grid size: 925 m.
Global spatial layout: spatial pyramid matching Spatial weighting the features Beyond bags of features: Adding spatial information.
A presentation by Modupe Omueti For CMPT 820:Multimedia Systems
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Event prediction CS 590v. Applications Video search Surveillance – Detecting suspicious activities – Illegally parked cars – Abandoned bags Intelligent.
On the Relationship between Visual Attributes and Convolutional Networks Paper ID - 52.
Combining Human and Machine Capabilities for Improved Accuracy and Speed in Visual Recognition Tasks Research Experiment Design Sprint: IVS Flower Recognition.
Fast and Compact Retrieval Methods in Computer Vision Part II A. Torralba, R. Fergus and Y. Weiss. Small Codes and Large Image Databases for Recognition.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Three-dimensional co-occurrence matrices & Gabor filters: Current progress Gray-level co-occurrence matrices Carl Philips Gabor filters Daniel Li Supervisor:
Statistics of Natural Image Categories Antonio Torralba and Aude Oliva. Network: Computation in Neural Systems, 14(2003) Jonathan Huang
Feature Level Processing Lessons from low-level vision Applications in Highlighting Icon (symbol) design Glyph design.
Student Mini-Camp Project Report Pattern Recognition Participant StudentsAffiliations Patrick ChoiClaremont Graduate University Joseph McGrathUniv. of.
A Technique for Advanced Dynamic Integration of Multiple Classifiers Alexey Tsymbal*, Seppo Puuronen**, Vagan Terziyan* *Department of Artificial Intelligence.
Christian Siagian Laurent Itti Univ. Southern California, CA, USA
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Avalanche Ski-Resort Snow-Clad Mountain Moving Vistas: Exploiting Motion for Describing Scenes Nitesh Shroff, Pavan Turaga, Rama Chellappa University of.
Feature extraction Feature extraction involves finding features of the segmented image. Usually performed on a binary image produced from.
Brief overview of ideas In this introductory lecture I will show short explanations of basic image processing methods In next lectures we will go into.
Oral Defense by Sunny Tang 15 Aug 2003
Review: Intro to recognition Recognition tasks Machine learning approach: training, testing, generalization Example classifiers Nearest neighbor Linear.
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
Multiclass object recognition
Spatial-based Enhancements Lecture 3 prepared by R. Lathrop 10/99 updated 10/03 ERDAS Field Guide 6th Ed. Ch 5: ;
Computer vision.
Image Pattern Recognition The identification of animal species through the classification of hair patterns using image pattern recognition: A case study.
1 SEGMENTATION OF BREAST TUMOR IN THREE- DIMENSIONAL ULTRASOUND IMAGES USING THREE- DIMENSIONAL DISCRETE ACTIVE CONTOUR MODEL Ultrasound in Med. & Biol.,
General Tensor Discriminant Analysis and Gabor Features for Gait Recognition by D. Tao, X. Li, and J. Maybank, TPAMI 2007 Presented by Iulian Pruteanu.
Group Sparse Coding Samy Bengio, Fernando Pereira, Yoram Singer, Dennis Strelow Google Mountain View, CA (NIPS2009) Presented by Miao Liu July
Visual Distinctness What is easy to find How to represent quantitity Lessons from low-level vision Applications in Highlighting Icon (symbol) design -
The University of Texas at Austin Vision-Based Pedestrian Detection for Driving Assistance Marco Perez.
Automated Target Recognition Using Mathematical Morphology Prof. Robert Haralick Ilknur Icke José Hanchi Computer Science Dept. The Graduate Center of.
A Two-level Pose Estimation Framework Using Majority Voting of Gabor Wavelets and Bunch Graph Analysis J. Wu, J. M. Pedersen, D. Putthividhya, D. Norgaard,
Putting Context into Vision Derek Hoiem September 15, 2004.
Implementing GIST on the GPU. Refrence Original Work  Aude Oliva, Antonio Torralba  Modeling the shape of the scene: a holistic representation of the.
Modeling the Shape of a Scene: Seeing the trees as a forest Scene Understanding Seminar
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
1 Iris Recognition Ying Sun AICIP Group Meeting November 3, 2006.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
Context-based vision system for place and object recognition Antonio Torralba Kevin Murphy Bill Freeman Mark Rubin Presented by David Lee Some slides borrowed.
Remote Sensing Unsupervised Image Classification.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
1.Learn appearance based models for concepts 2.Compute posterior probabilities or Semantic Multinomial (SMN) under appearance models. -But, suffers from.
9.913 Pattern Recognition for Vision Class9 - Object Detection and Recognition Bernd Heisele.
Using the Forest to see the Trees: A computational model relating features, objects and scenes Antonio Torralba CSAIL-MIT Joint work with Aude Oliva, Kevin.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Digital Image Processing CSC331
Image Quality Measures Omar Javed, Sohaib Khan Dr. Mubarak Shah.
Pattern Recognition. What is Pattern Recognition? Pattern recognition is a sub-topic of machine learning. PR is the science that concerns the description.
CS262: Computer Vision Lect 09: SIFT Descriptors
Traffic Sign Recognition Using Discriminative Local Features Andrzej Ruta, Yongmin Li, Xiaohui Liu School of Information Systems, Computing and Mathematics.
Recognizing Deformable Shapes
Figure Legend: From: Some observations on contrast detection in noise
Outline Texture modeling - continued Filtering-based approaches.
Context-based vision system for place and object recognition
Object detection as supervised classification
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
CS 1674: Intro to Computer Vision Scene Recognition
Multiple Instance Learning: applications to computer vision
RGB-D Image for Scene Recognition by Jiaqi Guo
Brief Review of Recognition + Context
EE513 Audio Signals and Systems
Wavelet-based texture analysis and segmentation
Ying Dai Faculty of software and information science,
Presentation transcript:

Pulkit Agrawal Y7322 BVV Sri Raj Dutt Y7110 Sushobhan Nayak Y7460

Outline What is a scene Scene recognition Method Results Future Work References

What is a Scene? Scene- as opposed to ‘object’ or ‘texture’ Object: when view subtends 1 to 2 meters around observer---hand distance

What is a Scene? observer and fixated point- >5 meters

Scene Recognition 2 approaches  Object recognition  Global info – details and object info ignored o Experimental evidence o ‘Gist’ of image

Scene Recognition Exclusive classification Structural attributes- Continuous organization of scenes along semantic axes

Semantic axes 2 levels:  Degree of naturalness: man-made to natural landscape Ambiguous (building in field) pictures around center

Semantic axes  Natural scenes- degree of openness  Artificial urban scenes- degree of verticalness and horizontalness Highways--  Highways +Tall Building---  Tall Buildings

Method Information at various Scales What do we Need ?? High Frequency ?Low Frequency ? Both ??

Feature Extraction Image Power Spectrum Gabor Filters (Scale, Orientation) Features (512 used)

Mathematical Details… Important data from Image power spectrum Structural discriminant feature DST=Discriminat Spectral Template- --an encoding of the discriminant structure between two image categories ‘u’ -  weighted integral of power spectrum

Classification Image = Feature Vector() Required Classes Linear Discriminant Analysis Discriminating Vector (D.V) Maximum Separation b/w classes

Mathematical Details….. Image represented as Feature Vector x. m 1, m 2 : mean vector of feature vector of 2 classes

Mathematical Details… g n = feature G n = Gabor filter d n = through learning

Learning… Projection of Training Set Image F.V. on D.V. Use LDA to determine Threshold Classifier Obtained

Learning

Work.. Artificial v/s Natural Open v/s Non Open

Results Artificial v/s Natural Artificial 80 Test Images 67 classified Correctly Natural 80 Test Images 75 classified Correctly 89% Correct results

Result

Future Work Arrangement in semantic axes Addition of features Depth Symmetry Contrast Ruggedness 8 category arrangement (skyscrapers, highway, street, flat building, beach, field, mountain, forest) Experiment with Haar and other filters

Reference Torralba A. & Olivia A., Semantic Organisation of Scenes using Discriminant Structural Templates (1999) Torralba A. & Olivia A., Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope(2001) Olivia A., Gist of the Scene ope/ ope/