Detection of pedestrians from still images

Tetik, Yusuf Engin; Bolat, Bulent

doi:10.1109/siu.2011.5929739

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The motivation of this approach is to detect whether the area contains legs [16]. The legs are vertical or near-vertical parts of the body so if a detected area has vertical edges at the bottom half of the area, it is labeled as a pedestrian candidate, and otherwise it is discarded (Fig.…”

Section: Methodsmentioning

confidence: 99%

“…First of all, computation time increases with the increasing number of features. Secondly, there could be irrelevant features and by using the irrelevant features, performance of the classifier might reduce [16]. To avoid from these two pitfalls, an Adaboost algorithm [14] is applied to the data.…”

Section: F(1) = (A + B) / (C + D + 1) F(2) = (A + C) / (B + D + 1) F(mentioning

confidence: 99%

See 1 more Smart Citation

Pedestrian detection from still images

Tetik

Bolat

2011

2011 International Symposium on Innovations in Intelligent Systems and Applications

Self Cite

View full text Add to dashboard Cite

In this work, a pedestrian detection method based on adaptive boosting is proposed. The proposed method works on still images. The features utilized in the work are derived from Haar-like templates. An Adaboost classifier is utilized for both feature selection and classification. To show the effectiveness of the proposed algorithm, the system is trained by using Nicta Pedestrian Dataset and tested by using Penn Fudan Pedestrian Dataset. The experimental result shows the proposed method's effectiveness.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: F(1) = (A + B) / (C + D + 1) F(2) = (A + C) / (B + D + 1) F(mentioning

confidence: 99%