Presentation is loading. Please wait.

Presentation is loading. Please wait.

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

Similar presentations


Presentation on theme: "Using Statistic-based Boosting Cascade Weilong Yang, Wei Song, Zhigang Qiao, Michael Fang 1."— Presentation transcript:

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

2  Haar-like feature generation ◦ Integral image  AdaBoost (feature selection) ◦ Limitations  Statistic-based boosting (StatBoost)  Cascade structure  Performance evaluation 2

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). 3

4 Weak classifier 3 Final classifier: linear combination of the weak classifiers Weights Increased Weak Classifier 2 Weak Classifier 1 4

5 5

6 It takes WEEKS to train! 6

7 Training of the weak classifier 7 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 Non-car Car Optimal threshold Feature value 8 Figure courtesy to Minh-Tri Phan, 2007

9 Constant Time 9 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 10

11  Overall form: degenerate decision tree  Reflects the fact: within any single image an overwhelming majority of sub-windows are negative [1] 11 All Sub-windows 123 Rejected Sub-windows Further Processing T TT F FF

12  False positive rate  Detection rate 12

13  Three-layer cascade  Each layer has 4, 11, and 73 weak classifiers, respectively 13

14 Number of car images: 500 14 (Courtesy to UIUC Image Database for Car Detection)

15 Number of non-car images: 500 15 (Courtesy to UIUC Image Database for Car Detection)

16 1 st Feature2 nd Feature3 rd Feature 16

17 17

18 18

19 19

20 20

21 Test results on 170 Images: 21

22 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 22


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

Similar presentations


Ads by Google