1. Improved Rooftop Detection in Aerial Images with Machine Learning
11/18/2018
Improved Rooftop Detection in Aerial Images with Machine Learning
M. A. Maloof
Georgetown University
P. Langley
Institute for the study of learning and expertise
T. O. Binford
Stanford University
R. Nevatia
University of southern California
S. Sage
Presented By
Yong Li
11/18/2018

2. Outline Introduction The task domain Image analysis
Data set description
Four algorithms for supervised learning
Experiments and results
Comments

3. Introduction The flood of images Handcrafted knowledge
Recent applications in business and industry hold useful lessons
Machine learning approach improves the ability of image analysts to deal with the flood of images.

4. The Task Domain Aerial images of ground sites.
A common task: detect change at a site as reflected in differences between two images (building, road, and vehicles)
This paper focus on identifying buildings in satellite photographs.
HOW ??

5. Image Analysis
Building Detection and Description System (BUDDS) (Lin and Nevatia, 1998)
Rooftop Generation
Pixels
Edge elements
Edge detector
lines
Line feather detector
U-Constructs
Three-sided structure
Junctions and parallel line
parallelograms
U-constructs and junctions

6. Image Analysis rooftop generation Rooftop selection
Machine learning may improve this process (Hypothesis)

7. The Data Set Description
Following Lin and Nevatia (1998)
Nine continue feathers
Two classes—rooftop and non-rooftop
Manual labeling(interactive labeling system)

8. The Learning techniques
Nearest Neighbor
Naïve Bayes
C5.0
Perceptron
BUDDS Classifier (Control)

9. Cost-Sensitive Learning
Severely skewed data
Favoritism toward the majority class
Naïve
Predict the class i with the least expected risk
C 5.0
Uses a method similar to that in CART (Breiman et al., 1984)
Nearest neighbor
Incorporate a cost parameter τj (0, 1).
The altered distance
Perceptron and BUDDS
The adjusted threshold
sj is the maximum value the weighted sum can take for the jth class

10. ROC Analysis The accuracy measure is not sufficient
Separated accuracy on both classes in term of false positives and false negatives
ROC (Receiver Operating Characteristic) analysis
Vary some aspect of the situation (costs, the class distribution or threshold)
Plot the false positive rate against the true positive rate

11. ROC Curve

12. Experiments and Results (I)
Experiment I.
Randomly, 60% training and 40% testing
Accuracy as the measure of performance is not suitable to this problem

13. Experiments and Results (I)

14. Experiments and Results (II)
Within-Image Learning
Between-Image Learning
Generalizing over Aspect
Generalizing over Location
Leaving One Image Out

15. Experiments and Results (II)

16. Experiments and Results (II)

17. Experiments and Results (II)
Naive
Naive

18. Experiments and Results (II)

19. Experiments and Results (II)

20. Experiments and Results (II)

21. Experiments and Results (II)

22. Experiments and Results (II)

23. Conclusion
the results of the naïve Bayesian classifier are best one and support our main hypothesis.
But not always better than BUDDS

24. Comments Advantages Disadvantages
Comprehensively studied the use of machine learning to improve a rooftop detection process.
It is possible to use machine learning methods to identify rooftops and outperform the performance of BUDDS (not strong).
Disadvantages
Didn’t consider time and space complexity.