Visual Object Recognition using Template Matching Luke Cole 1 , 2 , - - PowerPoint PPT Presentation

Introduction Approach Results Conclusions Future Work Acknowledgements

Visual Object Recognition using Template Matching

Luke Cole1,2, David Austin1,2, Lance Cole2 December 8, 2004

1Robotic Systems Lab, RSISE 2National ICT Australia,

Australian National University, Locked Bag 8001, ACT 0200, Australia Canberra, ACT 2601

Introduction Approach Results Conclusions Future Work Acknowledgements

Quick Overview of Template Matching

This is an old well established technique. A simple task of performing a correlation between a template image (object in training set) and a new image to classify.

Sum of All Differences (SAD) Sum of Square Differences (SSD) Normalised Cross Correlation (NCC)

Below: Raw Template (left), Edge Based Template (right). For each image set: test image (left), template (right).

Introduction Approach Results Conclusions Future Work Acknowledgements

The Research

Template Matching is a rich object detector. Captures entire essence of an object (not the case for many “higher-order” techniques). Some object have no or poor internal features so they are not well suited to “higher order” techniques. E.g. aspect graphs use edge features. It’s not always possible/easy to detect edges. So what is the problem with Template Matching? It’s expensive! This research addresses this scaling problem with results based

• n 91 classes and 140 000 extracted blobs each of size

680x480. Biologically inspired for real time long-term visual robotic systems.

Introduction Approach Results Conclusions Future Work Acknowledgements

Not always easy to detect edges

Introduction Approach Results Conclusions Future Work Acknowledgements

Approach Introduction

Training database acquisition and extraction. Training database reduction to create template images. Random classification via NCC’s as it is the best form of correlation and the most expensive.

Introduction Approach Results Conclusions Future Work Acknowledgements

The Object Database

Lego Bricks 140 000 image with 91 bricks, approximately 1000 different views for each class. Why is it a good database?

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Acquisition

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Acquisition

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Acquisition

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Extraction

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Reduction

Classifying a new test image across all the extracted blobs would be computationally infeasible. So we reduce the set (since we expect similar and incorrect images). If two images are similar, we do not simply keep one image and remove the rest. Instead, a clustering approach was taken. Each class is represented by a two-tier hierarchical structure.

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Reduction

Introduction Approach Results Conclusions Future Work Acknowledgements

Training Database Reduction

Obviously determining the correct NCC threshold would be a task in itself. So our results are based on four reduced sets with the NCC threshold equal to 0.75, 0.8, 0.85, 0.9.

Introduction Approach Results Conclusions Future Work Acknowledgements

Recognition Procedure

Introduction Approach Results Conclusions Future Work Acknowledgements

Results

C/C++ Implementation. Images obtained from a standard webcam (640x480). Results obtained on a AMD Athon(tm) XP 2700+ with 1GB

• f memory, running Debian Linux.

Different reduced sets (M) and closest classes (navg).

Introduction Approach Results Conclusions Future Work Acknowledgements

Accuracy and Execution Time

20 40 60 80 100 20 15 10 5 3 Accuracy (using colour hack) (%) Closest classes n_{avg} M = 0.75 M = 0.8 M = 0.85 M = 0.9 5 10 15 20 25 20 15 10 5 3 Execution time (sec) Closest classes n_{avg} M = 0.75 M = 0.8 M = 0.85 M = 0.9

Lastest result: 90% in 6.75 seconds for navg = 15, M = 0.9

Introduction Approach Results Conclusions Future Work Acknowledgements

Reduced and Examined Images

5000 10000 15000 20000 25000 0.9 0.85 0.8 0.75 Number of Images M 500 1000 1500 2000 2500 3000 3500 4000 20 15 10 5 3 Number of Images examined per classification Closest classes n_{avg} M = 0.75 M = 0.8 M = 0.85 M = 0.9

Introduction Approach Results Conclusions Future Work Acknowledgements

Conclusions

Uses all of the information about each object Not exactly real-time, however still favorably over more complex methods that take many minutes (NCC

• ptimizations).

Clustering and averaging seems an interesting way to catalogue and classify an object. Large computation required for unsegmented recognition

Introduction Approach Results Conclusions Future Work Acknowledgements

Future Work

More rigorous method to extracting and clustering. The green factor! Hardware implemention to template matching (FPGA). More camera views. Physical interaction.

Introduction Approach Results Conclusions Future Work Acknowledgements

Acknowledgements

This work was supported by funding from National ICT Australia. National ICT Australia is funded by the Australian Government’s Department of Communications, Information Technology and the Arts and the Australian Research Council through Backing Australia’s Ability and the ICT Centre of Excellence program.