Copyright © 2007 Indiana University Automated Customer Tracking and Behavior Recognition Raymond R. Burke and Alex Leykin Kelley School of Business Indiana.

Slides:



Advertisements
Similar presentations
Chapter 12 Customer Services and Retail Selling
Advertisements

Agile Route Shopper Tracker Shopperception: Using a KINECT to build real world Google Analytics.
Copyright © 2007 Indiana University Tools for Tracking Your Customers and Measuring Shopper Engagement Raymond R. Burke and Alex Leykin Kelley School of.
Nielsen Homescan® Data and Retail Insights American Egg Board 52 Weeks Ending December 26, 2009.
VISUAL HUMAN TRACKING AND GROUP ACTIVITY ANALYSIS: A VIDEO MINING SYSTEM FOR RETAIL MARKETING Alex Leykin Indiana University PhD Thesis by:
Human Identity Recognition in Aerial Images Omar Oreifej Ramin Mehran Mubarak Shah CVPR 2010, June Computer Vision Lab of UCF.
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
1 Approximated tracking of multiple non-rigid objects using adaptive quantization and resampling techniques. J. M. Sotoca 1, F.J. Ferri 1, J. Gutierrez.
1 Video Processing Lecture on the image part (8+9) Automatic Perception Volker Krüger Aalborg Media Lab Aalborg University Copenhagen
Learning to estimate human pose with data driven belief propagation Gang Hua, Ming-Hsuan Yang, Ying Wu CVPR 05.
Object Inter-Camera Tracking with non- overlapping views: A new dynamic approach Trevor Montcalm Bubaker Boufama.
Benny Neeman Leon Ribinik 27/01/2009. Our Goal – People Tracking We would like to be able to track and distinguish the different people in a movie.
Multiple People Detection and Tracking with Occlusion Presenter: Feifei Huo Supervisor: Dr. Emile A. Hendriks Dr. A. H. J. Stijn Oomes Information and.
1 A/R/T ForumJune 12, 2006 Copyright © 2006 Indiana University Customer Tracking Professor Ray Burke E.W. Kelley Professor of Business Administration Director,
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Authers : Yael Pritch Alex Rav-Acha Shmual Peleg. Presenting by Yossi Maimon.
Robust Multi-Pedestrian Tracking in Thermal-Visible Surveillance Videos Alex Leykin and Riad Hammoud.
Robust Multi-Pedestrian Tracking in Thermal-Visible Surveillance Videos Alex Leykin, Yang Ran, and Riad Hammoud.
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Tracking Objects with Dynamics Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 04/21/15 some slides from Amin Sadeghi, Lana Lazebnik,
Workshop on Earth Observation for Urban Planning and Management, 20 th November 2006, HK 1 Zhilin Li & Kourosh Khoshelham Dept of Land Surveying & Geo-Informatics.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
ECE 7340: Building Intelligent Robots QUALITATIVE NAVIGATION FOR MOBILE ROBOTS Tod S. Levitt Daryl T. Lawton Presented by: Aniket Samant.
Segmentation and Tracking of Multiple Humans in Crowded Environments Tao Zhao, Ram Nevatia, Bo Wu IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,
Ensemble Tracking Shai Avidan IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE February 2007.
Space Management Overview Exceeding customer expectations through merchandising excellence.
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.
CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.
Highlights Lecture on the image part (10) Automatic Perception 16
Multi-camera Video Surveillance: Detection, Occlusion Handling, Tracking and Event Recognition Oytun Akman.
1 Real Time, Online Detection of Abandoned Objects in Public Areas Proceedings of the 2006 IEEE International Conference on Robotics and Automation Authors.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Artificial Intelligence in Game Design Camera Control.
CSSE463: Image Recognition Day 30 This week This week Today: motion vectors and tracking Today: motion vectors and tracking Friday: Project workday. First.
Perception Introduction Pattern Recognition Image Formation
Chapter 14: SEGMENTATION BY CLUSTERING 1. 2 Outline Introduction Human Vision & Gestalt Properties Applications – Background Subtraction – Shot Boundary.
I A I Infrared Security System and Method US Patent 7,738,008 June How Does It Work? June 2010 I A I = Infrared Applications Inc.
Chapter 12: Web Usage Mining - An introduction Chapter written by Bamshad Mobasher Many slides are from a tutorial given by B. Berendt, B. Mobasher, M.
Measuring the Effect of Queues on Customer Purchases Andrés Musalem Duke University Joint work with Marcelo Olivares, Yina Lu (Decisions Risk and Operations,
CLASS 10 SCENE GRAPHS BASIC ANIMATION CS770/870. A scene Graph A data structure to hold components of a scene Usually a Tree of a Directed Acyclic Graph.
Vehicle Segmentation and Tracking From a Low-Angle Off-Axis Camera Neeraj K. Kanhere Committee members Dr. Stanley Birchfield Dr. Robert Schalkoff Dr.
Stable Multi-Target Tracking in Real-Time Surveillance Video
Robust Object Tracking by Hierarchical Association of Detection Responses Present by fakewen.
Expectation-Maximization (EM) Case Studies
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
Human Activity Recognition at Mid and Near Range Ram Nevatia University of Southern California Based on work of several collaborators: F. Lv, P. Natarajan,
By Naveen kumar Badam. Contents INTRODUCTION ARCHITECTURE OF THE PROPOSED MODEL MODULES INVOLVED IN THE MODEL FUTURE WORKS CONCLUSION.
Retail Location Power centers - This center is dominated by several large anchors or Category killers. Neighborhood Centers : They are designed to provide.
Using Adaptive Tracking To Classify And Monitor Activities In A Site W.E.L. Grimson, C. Stauffer, R. Romano, L. Lee.
Presented by: Idan Aharoni
Artificial Intelligence in Game Design Influence Maps and Decision Making.
CSSE463: Image Recognition Day 29 This week This week Today: Surveillance and finding motion vectors Today: Surveillance and finding motion vectors Tomorrow:
Suspicious Behavior in Outdoor Video Analysis - Challenges & Complexities Air Force Institute of Technology/ROME Air Force Research Lab Unclassified IED.
Unit 6.00 Understand the promotion of a fashion image.
Store Layout.
Chapter 18 Store Layout, Design, and Visual Merchandising Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights reserved.McGraw-Hill/Irwin.
Date of download: 5/29/2016 Copyright © 2016 SPIE. All rights reserved. From left to right are camera views 1,2,3,5 of surveillance videos in TRECVid benchmarking.
REAL-TIME DETECTOR FOR UNUSUAL BEHAVIOR
Tracking Objects with Dynamics
Nielsen Homescan® Data and Retail Insights
Vehicle Segmentation and Tracking in the Presence of Occlusions
Retailing Final stop on the distribution path
CSSE463: Image Recognition Day 29
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 29
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 29
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 29
Presentation transcript:

Copyright © 2007 Indiana University Automated Customer Tracking and Behavior Recognition Raymond R. Burke and Alex Leykin Kelley School of Business Indiana University November 2, 2007 Copyright © 2007 Indiana University

What is Retail Shoppability? Definition: The ability of the retail environment to translate consumer demand into purchase

Copyright © 2007 Indiana University What is Retail Shoppability? Definition: The ability of the retail environment to translate consumer demand into purchase Components: Consumer Engagement: Making consumers’ needs salient in specific retail settings

Copyright © 2007 Indiana University What is Retail Shoppability? Definition: The ability of the retail environment to translate consumer demand into purchase Components: Consumer Engagement: Making consumers’ needs salient in specific retail settings Purchase conversion: Turning shoppers into buyers

Copyright © 2007 Indiana University What Determines Shoppability? Factors: Store, department, and category navigation Physical and visual clutter Product visibility and presentation Product organization Product information and value communication Presentation of new products Shopping convenience Shopping enjoyment

Copyright © 2007 Indiana University How Do We Measure and Manage Shoppability? Survey Research Measure consumer perceptions of the shopping experience and diagnose problems with store, department, and category shoppability

Copyright © 2007 Indiana University How Do We Measure and Manage Shoppability? Survey Research Measure consumer perceptions of the shopping experience and diagnose problems with store, department, and category shoppability Observational Research Track shopper behavior, identify points of engagement and purchase obstacles, and then manipulate and measure response

Copyright © 2007 Indiana University Observational Measures Engagement: –Examination of signs, displays, circulars –Category dwell time –Salesperson contact –Product/package/display interaction Conversion: –Aisle and category penetration –Purchase conversion rate –Product price/margin (absence of incentive) –Shopping basket size –Returns

Copyright © 2007 Indiana University Key Customer Touchpoints Store Entrance and Window Displays Lead Fixtures and Merchandising End-of-Aisle Displays High Volume / Margin Departments Customer Service Desk Checkout

Copyright © 2007 Indiana University Benefits of Computer Tracking Breadth of Coverage: –Census of customers/items (e.g., for security, inventory) –24/7 tracking (time of day/crowding analysis) –Potential to track entire store (path analysis) –Scalable to multiple stores (benchmarking, experiments) Speed: –Real time data (e.g., for staffing, replenishment) Data Integration: –Link path, penetration, conversion data to consumer demographics, shopping basket, purchase history

Copyright © 2007 Indiana University Computer Tracking Solutions: Tracking Carts with Infrared/RFID Sensors Limitations –Only applicable in retail stores using carts and/or baskets (e.g., grocery, mass retail) –Only tracks customers who choose to use carts/baskets, losing “fill-in” shoppers –Unable to track customers who leave carts. May overestimate perimeter traffic, dwell times –No measure of gaze direction or package interaction –No information on group size or behavior

Copyright © 2007 Indiana University Computer Tracking Solutions: Tracking Shoppers with Video Cameras Limitations –Cameras have a limited field of view and work best in smaller stores (e.g., specialty retail stores, drug stores, convenience stores, banks) –Tracking entire customer path requires multiple cameras with overlapping views –Occlusions (e.g., shelving, signage, other customers) and shadows can interfere with tracking –Difficult to distinguish between employees and customers

Copyright © 2007 Indiana University Tracking - System Overview Low-level Processing Camera Model Obstacle Model Foreground Segmentation Head Detection Tracking Jump-diffuse transitions Priors and Likelihoods Accept/Reject Candidate Event Detection Actor Distances Deterministic Agglomerative Clustering Validity Index Activity Detection Event Distances Fuzzy Agglomerative Clustering Adaptively Remove Weak Clusters

Copyright © 2007 Indiana University Tracking – Background Subtraction Color μ RGB I low I hi codeword codebook ……

Copyright © 2007 Indiana University Tracking – Background Subtraction The result of background subtraction is a binary bitmap Foreground regions corresponding to moving people are represented as blobs

Copyright © 2007 Indiana University Tracking – Detecting Heads The head is usually the least occluded part of the human body. Therefore, to reliably detect multiple people within one blob, we look at their head locations: 1.Estimate the height of each vertical line of the blob 2.Find a number of local maxima in the resulting histogram

Copyright © 2007 Indiana University Tracking – Detecting Heads (cont.)

Copyright © 2007 Indiana University Temporal Tracking Goal: find a correspondence between the bodies, already detected in the current frame with the bodies which appear in the next frame. Apply Markov Chain Monte Carlo (MCMC) to estimate the next state ? ? ? x t-1 xtxt ztzt ? Add body Delete body Recover deleted Change Size Move

Copyright © 2007 Indiana University

Swarming Shopper groups detected based on “swarming” idea in reverse –Swarming is used in graphics to generate flocking behaviour in animations. –Rules define flocking behaviour: Avoid collisions with the neighbors. Maintain fixed distance with neighbors Coordinate velocity vector with neighbors.

Copyright © 2007 Indiana University Tracking Customer Groups We treat customers as swarming agents, acting according to simple rules (e.g. stay together with swarm members) Customer groups

Copyright © 2007 Indiana University Defining Swarming Rules Two actors come sufficiently close according to some distance measure: –Relative position p i =(x i, y i ) of actor i on the floor –Body orientations α i –Dwelling state δ i ={T,F}. Distance between two agents is a linear combination of co-location, co-ordination and co-dwelling

Copyright © 2007 Indiana University Swarming The actors that best fit this model signal a Swarming Event Multiple swarming events are further clustered with fuzzy weights to find out shoppers in the same group over long periods

Copyright © 2007 Indiana University Activity Detection The shopper group detection is accomplished by clustering the short term events over long time periods. –The events could be separated in time, but they will be part of the same shopper group if the actors are the same (the first term).

Copyright © 2007 Indiana University Activity detection Higher level activities (shopper groups) detected using these events as building blocks over longer time periods Some definitions: –B ei ={b  e i } the set of all bodies taking part in an event e i. –τ ei and τ ej are the average times of events e i and e j happening.

Copyright © 2007 Indiana University Results: Swarming activities detected in space-time Dot location: average event location Dot size: validity Dots of same color: belong to same activity

Copyright © 2007 Indiana University Group Detection

Copyright © 2007 Indiana University Tracking Sequence number FramesPeople People missed False hits Identity switches %

Copyright © 2007 Indiana University Group Detection SequenceGroupsP+P−P−Partial Total Percent Ground truth (manually determined) false positives false negatives (groups missed) Partially identified groups (≥2 people in the group Correctly identified)

Copyright © 2007 Indiana University Qualitative Assesments Longer paths provide better group detection ( p val << 1 ) Two-people groups are easiest to detect Simple one-step clustering of trajectories is not sufficient for long-term group detection Employee tracks pose a significant problem and have to be excluded Several groups were missed by the operator in the initial ground truth –System caught groups missed by the human expert after inspection of results.

Copyright © 2007 Indiana University Tracking Example: Store View

Copyright © 2007 Indiana University Summary of Tracking Insights 1.Track customer path 2.Measure category penetration, dwell time, and conversion 3.Measure line queues and crowding 4.Cluster shoppers based on path similarity Evaluate store layout and product adjacencies Manage in-store communication, product assortment, and pricing Manage service levels, staffing Behavioral segmentation

Copyright © 2007 Indiana University Resources Questions? Indiana University’s Kelley School of Business