1 Real Time, Online Detection of Abandoned Objects in Public Areas Proceedings of the 2006 IEEE International Conference on Robotics and Automation Authors.

Slides:



Advertisements
Similar presentations
People Counting and Human Detection in a Challenging Situation Ya-Li Hou and Grantham K. H. Pang IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART.
Advertisements

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.
Foreground Background detection from video Foreground Background detection from video מאת : אבישג אנגרמן.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes Professor :王聖智 教授 Student :周節.
Object Inter-Camera Tracking with non- overlapping views: A new dynamic approach Trevor Montcalm Bubaker Boufama.
Video Inpainting Under Constrained Camera Motion Kedar A. Patwardhan, Student Member, IEEE, Guillermo Sapiro, Senior Member, IEEE, and Marcelo Bertalm.
Multiple People Detection and Tracking with Occlusion Presenter: Feifei Huo Supervisor: Dr. Emile A. Hendriks Dr. A. H. J. Stijn Oomes Information and.
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
Different Tracking Techniques  1.Gaussian Mixture Model:  1.Construct the model of the Background.  2.Given sequence of background images find the.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Vision-Based Analysis of Small Groups in Pedestrian Crowds Weina Ge, Robert T. Collins, R. Barry Ruback IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE.
Høgskolen i Gjøvik Saleh Alaliyat Video - based Fall Detection in Elderly's Houses.
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
IEEE TCSVT 2011 Wonjun Kim Chanho Jung Changick Kim
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
Video Segmentation Based on Image Change Detection for Surveillance Systems Tung-Chien Chen EE 264: Image Processing and Reconstruction.
Robust Object Segmentation Using Adaptive Thresholding Xiaxi Huang and Nikolaos V. Boulgouris International Conference on Image Processing 2007.
Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
Object Detection and Tracking Mike Knowles 11 th January 2005
Video summarization by graph optimization Lu Shi Oct. 7, 2003.
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
CSE 291 Final Project: Adaptive Multi-Spectral Differencing Andrew Cosand UCSD CVRR.
Effective Gaussian mixture learning for video background subtraction Dar-Shyang Lee, Member, IEEE.
MULTIPLE MOVING OBJECTS TRACKING FOR VIDEO SURVEILLANCE SYSTEMS.
Triangle-based approach to the detection of human face March 2001 PATTERN RECOGNITION Speaker Jing. AIP Lab.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Feature extraction Feature extraction involves finding features of the segmented image. Usually performed on a binary image produced from.
Image Subtraction for Real Time Moving Object Extraction Shahbe Mat Desa, Qussay A. Salih, CGIV’04.
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.
Facial Recognition CSE 391 Kris Lord.
EE392J Final Project, March 20, Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama.
1 REAL-TIME IMAGE PROCESSING APPROACH TO MEASURE TRAFFIC QUEUE PARAMETERS. M. Fathy and M.Y. Siyal Conference 1995: Image Processing And Its Applications.
Shape Recognition and Pose Estimation for Mobile Augmented Reality Author : N. Hagbi, J. El-Sana, O. Bergig, and M. Billinghurst Date : Speaker.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Olga Zoidi, Anastasios Tefas, Member, IEEE Ioannis Pitas, Fellow, IEEE
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Characterizing activity in video shots based on salient points Nicolas Moënne-Loccoz Viper group Computer vision & multimedia laboratory University of.
Chapter 14: SEGMENTATION BY CLUSTERING 1. 2 Outline Introduction Human Vision & Gestalt Properties Applications – Background Subtraction – Shot Boundary.
Automated Face Detection Peter Brende David Black-Schaffer Veni Bourakov.
Data Extraction using Image Similarity CIS 601 Image Processing Ajay Kumar Yadav.
Bo QIN, Zongshun MA, Zhenghua FANG, Shengke WANG Computer-Aided Design and Computer Graphics, th IEEE International Conference on, p Presenter.
Hierarchical Method for Foreground DetectionUsing Codebook Model Jing-Ming Guo, Yun-Fu Liu, Chih-Hsien Hsia, Min-Hsiung Shih, and Chih-Sheng Hsu IEEE TRANSACTIONS.
Non-Photorealistic Rendering and Content- Based Image Retrieval Yuan-Hao Lai Pacific Graphics (2003)
Crowd Analysis at Mass Transit Sites Prahlad Kilambi, Osama Masound, and Nikolaos Papanikolopoulos University of Minnesota Proceedings of IEEE ITSC 2006.
Expectation-Maximization (EM) Case Studies
Figure ground segregation in video via averaging and color distribution Introduction to Computational and Biological Vision 2013 Dror Zenati.
Fall Detection in Homes of Older Adults Using the Microsoft Kinect ERIK E. STONE AND MARJORIE SKUBIC IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,
Implementation, Comparison and Literature Review of Spatio-temporal and Compressed domains Object detection. By Gokul Krishna Srinivasan Submitted to Dr.
By Naveen kumar Badam. Contents INTRODUCTION ARCHITECTURE OF THE PROPOSED MODEL MODULES INVOLVED IN THE MODEL FUTURE WORKS CONCLUSION.
Presented by: Idan Aharoni
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
CS 376b Introduction to Computer Vision 03 / 31 / 2008 Instructor: Michael Eckmann.
Tracking Groups of People for Video Surveillance Xinzhen(Elaine) Wang Advisor: Dr.Longin Latecki.
1/39 Motion Adaptive Search for Fast Motion Estimation 授課老師:王立洋老師 製作學生: M 蔡鐘葳.
Real-Time Hierarchical Scene Segmentation and Classification Andre Uckermann, Christof Elbrechter, Robert Haschke and Helge Ritter John Grossmann.
Learning and Removing Cast Shadows through a Multidistribution Approach Nicolas Martel-Brisson, Andre Zaccarin IEEE TRANSACTIONS ON PATTERN ANALYSIS AND.
Motion tracking TEAM D, Project 11: Laura Gui - Timisoara Calin Garboni - Timisoara Peter Horvath - Szeged Peter Kovacs - Debrecen.
Motion Estimation of Moving Foreground Objects Pierre Ponce ee392j Winter March 10, 2004.
Over the recent years, computer vision has started to play a significant role in the Human Computer Interaction (HCI). With efficient object tracking.
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.
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
Presenter: Ibrahim A. Zedan
Motion Detection And Analysis
Vehicle Segmentation and Tracking in the Presence of Occlusions
Image Segmentation Techniques
David Harwin Adviser: Petros Faloutsos
Related Work in Camera Network Tracking
Presentation transcript:

1 Real Time, Online Detection of Abandoned Objects in Public Areas Proceedings of the 2006 IEEE International Conference on Robotics and Automation Authors : Nathaniel Bird, Stefan Atev, Nicolas Caramelli, Robert Martin, Osama Masoud, Nikolaos Papanikolopoulos

2 Outline  Introduction  Method Description A. Low-Level Processing B. Short-Term Logic C. Long-Term Logic D. Image Similarity  Results  Conclusions and Future Work

3 I. Introduction  This paper addresses this issue by presenting an algorithm for automated detection of abandoned objects.  Abandoned object : a stationary object has not been touching a person for some time threshold.  The method must Online in real time Stay active around the clock Not detect still people as abandoned objects Detect abandoned objects even if they are occluded by moving crowds of people for periods of time

4 II. Method Description A. Low-Level Processing  Background segmentation is performed using [6].  Processing only every tenth frame is still a high enough rate considering the temporal scale at which the events of interest occur.  [6] C. Stauffer and W. E. L. Grimson, “ Adaptive background mixture models for real-time tracking, ” Proceedings of the IEEE Computer Vision and Pattern Recognition, vol. 2, pp , June 1999

5 II. Method Description A. Low-Level Processing  The background segmentation method is restricted to user-specified regions of interest in the image. block out areas of the image where any background changes detected can be considered as noise (walls) Remove areas that are too far from the camera for accurate abandoned object identification

6 II. Method Description A. Low-Level Processing  Binary foreground mask  Blob extraction is then performed on the binary foreground mask.  Correlating the blobs detected in the last frame with the blobs detected in the current frame.

7 II. Method Description B. Short-Term Logic  Blob types: Abandoned Object (A) Person (P) Still Person (SP) Unknown (U)  Blob behaviors: Creation Splits Merges Blob centroid velocity

8 II. Method Description B. Short-Term Logic  Person Group (PG) A PG is created containing the new blobs that split from a P or an SP. All blobs contained within a PG are classified as U until one of them becomes a P, at which all other blobs within it can be classified normally. This is to stop a sitting person from being incorrectly classified as an abandoned object if they place a bag beside them that splits from their blob.  : threshold velocity above which an abandoned object, still person, or unknown becomes a person.

9 II. Method Description B. Short-Term Logic

10 II. Method Description B. Short-Term Logic

11 II. Method Description C. Long-Term Logic  The long term logic maintains a set of potential abandoned objects and a set of still people. Contour in the image plane Timestamp of when they were first detected.  When an A type blob is found, it first checked if it does not overlap with any item in the potential abandoned object or still person sets. Yes => copied into potential abandoned object set No => ignore  So did SP type blob.

12 II. Method Description C. Long-Term Logic  All items in the potential abandoned object set and the still person set are checked every time a frame is processed. If their corresponding area in the binary foreground mask is filled less than some percentage, p, then the item is dropped. P were empirically found to be between 75% and 80%

13 II. Method Description C. Long-Term Logic  time threshold t If during a check it is discovered that t time has elapsed since an item was added to the potential abandoned object set, an alarm is triggered for that object.  After the alarm is triggered, the long-term logic adjusts a mask used by the background segmentation module so that it will not improperly learn the abandoned object into the background.

14 II. Method Description D. Image Similarity  When the potential abandoned object is first detected, a copy of the image at its location is saved.  At every time step, the area surrounding the object ( a “ halo ” excluding the object) is checked for significant foreground activity.  If there is no noticeable foreground activity in the halo, the current image is compared pixel-by-pixel to the stored image for the potential abandoned object, and an average per-pixel difference is calculated.

15 II. Method Description D. Image Similarity  An exponential running average of this difference is then updated.  If the value of the exponential running average exceeds an empirically determined threshold, the potential abandoned object is deemed to be moving too much to be a stationary object. => reclassified to a still person.

16 III. Results A. Alarm Description  The following information is what is recorded for every alarm : 1. Identification Number 2. Start Time 3. Trigger Time 4. End Time 5. Image-Plane Location

17 III. Results B. Ground Truth  The ground truth for a given video sequence is determined manually for every sequence by a human operator.

18 III. Results C. PED/PAT Score Description  A candidate match is declared if there is sufficient spatial proximity and/or overlap between the two alarms as well as a temporal distance below a specific tolerance.  The candidate matches will usually result in a many-to-many relationship Bipartite graph  We therefore give each edge a weight equal to the timestamp difference between the two alarms and then find the minimum-weighted maximum- cardinality matching.

19 III. Results D. Overall Score Description  We define an overall score as follows:  x is relative importance we wish to give to the PED score over the PAT score. x=0 => PAT plot X=0.5 => weight PED and PAT equally X=1 => PED plot  We use a value of x=0.75 because we consider finding true alarms more important than some false positives.

20 III. Results E. Test Sequences

21 III. Results F. Results

22 III. Results F. Results

23 IV. Conclusions and Future Work  We have presented a method to detect abandoned objects that works online in real time, uses color data, can adapt to scene changes around the clock, does not detect still people as abandoned objects and detects abandoned objects even if they are occluded by moving crowds of people for periods of time.  The results for densely populated scenes are not as good, indicating that future research should look into defining a short- term logic that characterizes the behavior of blobs corresponding to crowds.