Experiments Test different parking lot images captured in different luminance conditions The test samples include 1300 available parking spaces and 1500.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Bayesian Belief Propagation
O BJ C UT M. Pawan Kumar Philip Torr Andrew Zisserman UNIVERSITY OF OXFORD.
An Adaptive Learning Method for Target Tracking across Multiple Cameras Kuan-Wen Chen, Chih-Chuan Lai, Yi-Ping Hung, Chu-Song Chen National Taiwan University.
Cornell Accelerating Belief Propagation in Hardware Skand Hurkat and José Martínez Computer Systems Laboratory Cornell University
Change Detection C. Stauffer and W.E.L. Grimson, “Learning patterns of activity using real time tracking,” IEEE Trans. On PAMI, 22(8): , Aug 2000.
Robust statistical method for background extraction in image segmentation Doug Keen March 29, 2001.
Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.
3D Human Body Pose Estimation from Monocular Video Moin Nabi Computer Vision Group Institute for Research in Fundamental Sciences (IPM)
Real-Time Human Pose Recognition in Parts from Single Depth Images Presented by: Mohammad A. Gowayyed.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
Robust Foreground Detection in Video Using Pixel Layers Kedar A. Patwardhan, Guillermoo Sapire, and Vassilios Morellas IEEE TRANSACTION ON PATTERN ANAYLSIS.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Student: Yao-Sheng Wang Advisor: Prof. Sheng-Jyh Wang ARTICULATED HUMAN DETECTION 1 Department of Electronics Engineering National Chiao Tung University.
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11
Processing Digital Images. Filtering Analysis –Recognition Transmission.
Student: Hsu-Yung Cheng Advisor: Jenq-Neng Hwang, Professor
Classification and application in Remote Sensing.
Stereo Computation using Iterative Graph-Cuts
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Arizona State University DMML Kernel Methods – Gaussian Processes Presented by Shankar Bhargav.
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
California Car License Plate Recognition System ZhengHui Hu Advisor: Dr. Kang.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Real-Time Decentralized Articulated Motion Analysis and Object Tracking From Videos Wei Qu, Member, IEEE, and Dan Schonfeld, Senior Member, IEEE.
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
Real-Time Face Detection and Tracking Using Multiple Cameras RIT Computer Engineering Senior Design Project John RuppertJustin HnatowJared Holsopple This.
Real Time Abnormal Motion Detection in Surveillance Video Nahum Kiryati Tammy Riklin Raviv Yan Ivanchenko Shay Rochel Vision and Image Analysis Laboratory.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Mean-shift and its application for object tracking
TP15 - Tracking Computer Vision, FCUP, 2013 Miguel Coimbra Slides by Prof. Kristen Grauman.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Mean Shift Theory and Applications Reporter: Zhongping Ji.
7.1. Mean Shift Segmentation Idea of mean shift:
S EGMENTATION FOR H ANDWRITTEN D OCUMENTS Omar Alaql Fab. 20, 2014.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
5. SUMMARY & CONCLUSIONS We have presented a coarse to fine minimization framework using a coupled dual ellipse model to form a subspace constraint that.
Learning Theory Reza Shadmehr Linear and quadratic decision boundaries Kernel estimates of density Missing data.
Jun-Won Suh Intelligent Electronic Systems Human and Systems Engineering Department of Electrical and Computer Engineering Speaker Verification System.
Markov Random Fields Probabilistic Models for Images
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
Kevin Cherry Robert Firth Manohar Karki. Accurate detection of moving objects within scenes with dynamic background, in scenarios where the camera is.
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
Image Modeling & Segmentation Aly Farag and Asem Ali Lecture #2.
Positional Relevance Model for Pseudo–Relevance Feedback Yuanhua Lv & ChengXiang Zhai Department of Computer Science, UIUC Presented by Bo Man 2014/11/18.
Expectation-Maximization (EM) Case Studies
Chapter 5 Multi-Cue 3D Model- Based Object Tracking Geoffrey Taylor Lindsay Kleeman Intelligent Robotics Research Centre (IRRC) Department of Electrical.
Sparse Bayesian Learning for Efficient Visual Tracking O. Williams, A. Blake & R. Cipolloa PAMI, Aug Presented by Yuting Qi Machine Learning Reading.
Image Classification for Automatic Annotation
Image Segmentation Shengnan Wang
A Reliable Skin Detection Using Dempster-Shafer Theory of Evidence
Journal of Visual Communication and Image Representation
Learning and Removing Cast Shadows through a Multidistribution Approach Nicolas Martel-Brisson, Andre Zaccarin IEEE TRANSACTIONS ON PATTERN ANALYSIS AND.
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11 CS479/679 Pattern Recognition Dr. George Bebis.
Student Gesture Recognition System in Classroom 2.0 Chiung-Yao Fang, Min-Han Kuo, Greg-C Lee, and Sei-Wang Chen Department of Computer Science and Information.
Nonparametric Semantic Segmentation
Fast Preprocessing for Robust Face Sketch Synthesis
Dynamical Statistical Shape Priors for Level Set Based Tracking
Context-Aware Modeling and Recognition of Activities in Video
Image Segmentation Techniques
Lecture 26: Faces and probabilities
Presented by: Yang Yu Spatiotemporal GMM for Background Subtraction with Superpixel Hierarchy Mingliang Chen, Xing Wei, Qingxiong.
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Paper Reading Dalong Du April.08, 2011.
Mathematical Foundations of BME
Presentation transcript:

Experiments Test different parking lot images captured in different luminance conditions The test samples include 1300 available parking spaces and 1500 occupied spaces The final false-acceptance rate (FAR) and false-rejection rate (FRR) are and 0.02 In comparison, Dan’s method, which is a single-space detection method based on a SVM classifier, has FDR = and FRR = seconds to perform the detection and segmentation of parking spaces for a 320x240 color image on a PC with a 1.6GHz Pentium-4 CPU The world projection information is well-learned and embedded in the semantic knowledge so that the inter-object occlusion problem can be properly handled BHDF: one-row space detection  As an optimal inference problem  The statistical properties embedded in the BHDF graphical model D, S are conditional independent given H p(s i ) is assumed to be a uniform distribution “Occupied” status and “available” status are equally possible Ignore the effect of ln(p(S L )) due to uniform assumption R s (h i ) is the set of semantic nodes connecting to h i in the graph; N i is the neighbors of the ith pixel  Optimal inference Belief propagation technique BHDF: graphical learning  3-layer BHDF is a well-defined graphical model  Graphical topology is learned in advance One-to-one connections between the D layer and the H layer Four-neighboring connections inside the H layer Topological connections between the S layer and the H layer are learned based on training samples and camera calibration Note that a car can occlude only its neighbors, each semantic node only connects to its relative nodes on the H layer  Inter-layer and intra-layer message propagations are defined by using three trainable models (A,B,C)  Analyze the statuse of each row As an optimal inference problem which is subject to three aspects Local regions should be correctly classified p(D L |H L ) Adjacent regions should follow neighboring constraints p(H L ) Parked cars in the same row would match the inter- occluded patterns p(H L |S L ) One row of parking space Row-by-Row fashion  Select one row of parking space Assume each parking space as an equal-sized cube on the ground of the 3D scene Projection one row of parking space from 3D to 2D based on camera calibration BHDF: three trainable models  Local classification model p(D L |H L ) Assume each image pixel has the identical local model; We aim to calculate p(d i |h i ={G,O,C}) Non-parametric density estimation for h i ={G,O} N G and N D : normalization terms;  (.) is a symmetric kernel function d Gj / d D j denotes one of the T n / T m “ground/ otherwise” pixel samples  Overcome the luminance variation problem Train different probability models for p(d|h=G) and p(d|h=O) under different luminance conditions Select a suitable classification model dynamically Parametric density estimation for h i ={C} Converted to a new color domain: x=[u p] = T( d=[R G B] )  Combat the luminance variation problem Only the chromatic information (u,p) is used The distribution can be approximated by a Gaussian function  Adjacency model p(H L ) Accumulated histogram to approximate the probability table p(h i,h j ) based on 5000 pseudo training samples Most of the neighboring pairs follow the smoothness constraints Boundary regions, such as between “car” pixels and “ground” pixels, have quite different statistical distributions Goals  Available space number  Available space locations  Parking guidance  Monitor the changes of space status Motivations  Parking has become a problem  Intelligent parking lots surveillance systems is becoming practical  Assist users in efficiently finding empty parking spaces A BAYESIAN HIERARCHICAL DETECTION FRAMEWORK FOR PARKING SPACE DETECTION Ching-Chun Huang 1,3, Sheng-Jyh Wang 1, Yao-Jen Chang 2,3, and Tsuhan Chen 3 1 Department of Electronics Engineering, National Chiao Tung University, Taiwan. 2 Advanced Technology Center, Industrial Technology Research Institute, Taiwan 3 Department of Electrical & Computer Engineering, Carnegie Mellon University, USA. Key ideas  Background Traditional methods: P(S|D) Given one space observation (D) Decide the status of the space (S) Consider occlusion Different spaces have different occlusion patterns Occlusion is a “ pixel-level ” problem Owing to the occluded regions, adjacent spaces become highly relative Decide the status “ space by space ” is not suitable  Proposed method: Bayesian hierarchical detection framework (BHDF) to combine (D,L,S) Introduce a hidden pixel labeling layer “L” Analyze from pixel level to space level Infer the statuses of multiple spaces all together Challenges  Luminance variations  Inter-occlusions among cars  Occlusions caused by obstacles System flow Labeling results under different lighting conditions (Left) A pseudo training sample of parking lot status for global semantic model. (Right) Pre-defined “ground” regions in the black color and “otherwise” regions in the light-gray color 3D->2D occlusion Obstacle occlusion  Global semantic model p(H L |S L ) Accumulated histogram to approximate the probability table p(h i |R s (h i )) based on pseudo training samples Pseudo training samples represent the inter-occluded patterns Pseudo samples can be automatically generated based on camera projection parameters and projecting 3D-cubes to 2D