22
Automatic Car Detection Using Statistic-based Boosting Cascade Weilong Yang, Wei Song, Zhigang Qiao, Michael Fang 1

Using Statistic-based Boosting Cascade Weilong Yang, Wei Song, Zhigang Qiao, Michael Fang 1

Embed Size (px)

Citation preview

1

Automatic Car Detection

Using Statistic-based Boosting Cascade

Weilong Yang, Wei Song, Zhigang Qiao, Michael Fang

2

Haar-like feature generation◦ Integral image

AdaBoost (feature selection)◦ Limitations

Statistic-based boosting (StatBoost) Cascade structure Performance evaluation

System Overview

3

The objective is to learn a sequence of best weak classifiers and the best combining weights

Each weak classifier is constructed based on one feature (1D).

Key Concepts of AdaBoost

4

AdaBoost (illustrated)

Weak classifier 3

Final classifier: linear combination of the weak classifiers

WeightsIncreased

Weak Classifier 2

Weak Classifier 1

5

Formal Procedure of AdaBoost

6

It takes WEEKS to train!

Computational Issue

7

The Bottleneck

Factor

Description Common value

N number of examples

10,000

M number of weak classifiers in total

4,000 - 6,000

T number of Haar-like features

40,000

A view of a face detector training algorithm

for weak classifier m from 1 to M:…update weights – O(N)for feature t from 1 to T:

compute N feature values – O(N)sort N feature values – O(N log N)train feature classifier – O(N)

select best feature classifier – O(T)…

Training of the weak classifier

Figure courtesy to Minh-Tri Phan, 2007

8

Train the weak classifiers using statistics Assume the feature values of each class are

of normal distribution

Fast-StatBoost (1)

Non-car

Car

Optimalthreshold

Featurevalue

Figure courtesy to Minh-Tri Phan, 2007

9

Fast-StatBoost (2)

A view of our face detector training algorithm

for weak classifier m from 1 to M:…update weights – O(N)Extract statistics of integral image – O(Nd2)for feature t from 1 to T:

project statistics into 1D – O(1)train feature classifier – O(1)

select best feature classifier – O(T)…

Constant Time

Figure courtesy to Minh-Tri Phan, 2007

10

Motivation◦ Increase detection performance◦ Reduce computation time

Key insight◦ Use simpler classifiers to reject the majority of

sub-windows◦ Use more complex ones to achieve low false

positive rates on the rest of them

The Cascade

11

Overall form: degenerate decision tree Reflects the fact: within any single image an

overwhelming majority of sub-windows are negative [1]

The Cascade (illustrated)

All Sub-windows

1 2 3

Rejected Sub-windows

Further Processing

T T T

FF F

12

False positive rate

Detection rate

A Cascade of Classifiers

13

Three-layer cascade Each layer has 4, 11, and 73 weak

classifiers, respectively

Our Cascaded Car Detector

14

Training Set (1)

Number of car images: 500

(Courtesy to UIUC Image Database for Car Detection)

15

Training Set (2)

Number of non-car images: 500

(Courtesy to UIUC Image Database for Car Detection)

16

First Three Features

1st Feature 2nd Feature

3rd Feature

17

Distribution of the First Three Features

18

Car Detection (Uniform Scale)

19

Car Detection (Different Scales)

20

False Positives

21

The ROC curveTest results on 170 Images:

22

References

1. P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” In Proc. CVPR, 2001.

2. M. Pham, T. Cham, “Fast training and selection of Haar features using statistics in boosting-based face detection.” In Proc. ICCV 2007