TY - GEN
T1 - Human detection using Histogram of Oriented Gradients and human body ratio estimation
AU - Lee, Kelvin
AU - Choo, Che Yon
AU - See, Hui Qing
AU - Tan, Zhuan Jiang
AU - Lee, Yunli
PY - 2010
Y1 - 2010
N2 - Recent research has been devoted to detecting people in images and videos. In this paper, a human detection method based on Histogram of Oriented Gradients (HoG) features and human body ratio estimation is presented. We utilized the discriminative power of HoG features for human detection, and implemented motion detection and local regions sliding window classifier, to obtain a rich descriptor set. Our human detection system consists of two stages. The initial stage involves image preprocessing and image segmentation, whereas the second stage classifies the integral image as human or non-human using human body ratio estimation, local region sliding window method and HoG Human Descriptor. Subsequently, it increases the detection rate and reduces the false alarm by deducting the overlapping window. In our experiments, DaimlerChrysler pedestrian benchmark data set is used to train a standard descriptor and the results showed an overall detection rate of 80% above.
AB - Recent research has been devoted to detecting people in images and videos. In this paper, a human detection method based on Histogram of Oriented Gradients (HoG) features and human body ratio estimation is presented. We utilized the discriminative power of HoG features for human detection, and implemented motion detection and local regions sliding window classifier, to obtain a rich descriptor set. Our human detection system consists of two stages. The initial stage involves image preprocessing and image segmentation, whereas the second stage classifies the integral image as human or non-human using human body ratio estimation, local region sliding window method and HoG Human Descriptor. Subsequently, it increases the detection rate and reduces the false alarm by deducting the overlapping window. In our experiments, DaimlerChrysler pedestrian benchmark data set is used to train a standard descriptor and the results showed an overall detection rate of 80% above.
KW - Background subtraction
KW - Features extraction
KW - Histogram of Oriented Gradients (HOG)
KW - Human body ratio estimation
KW - Human detection
KW - Local region sliding window classifier
KW - Support Vector Machine (SVM)
UR - https://www.scopus.com/pages/publications/77958528979
U2 - 10.1109/ICCSIT.2010.5564984
DO - 10.1109/ICCSIT.2010.5564984
M3 - Conference contribution
AN - SCOPUS:77958528979
SN - 9781424455386
T3 - Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
SP - 18
EP - 22
BT - Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
T2 - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
Y2 - 9 July 2010 through 11 July 2010
ER -