TY - GEN
T1 - Pixel structure based on Hausdorff distance for human detection in outdoor environments
AU - Chen, Yan
AU - Wu, Qiang
AU - He, Xiangjian
AU - Jia, Wenjing
AU - Hintz, Tom
PY - 2007
Y1 - 2007
N2 - This paper proposes a novel method for human detection from static images based on pixel structure of input images. In training stage, all sample images consisting of human images and non-human images are used to construct a Hausdorff distance map based on statistically analyzing the difference between the different blocks on each original image. A projection matrix will be created with Linear Discriminant Method (LDM) based on the Hausdorff distance map. This projection matrix will be used to transform multi-dimensional feature vectors (distance maps of testing images) into a feature in a one-dimensional domain. The decision will be made on the simple one-dimensional feature domain according to a precalculated threshold to distinguish human figures from non-human figures. In comparison with the common method based on Mahalanobis distance maps, the proposed method based on Hausdorff distance maps performs much better. Encouraging experimental results have been obtained using 800 human images and 800 non-human images.
AB - This paper proposes a novel method for human detection from static images based on pixel structure of input images. In training stage, all sample images consisting of human images and non-human images are used to construct a Hausdorff distance map based on statistically analyzing the difference between the different blocks on each original image. A projection matrix will be created with Linear Discriminant Method (LDM) based on the Hausdorff distance map. This projection matrix will be used to transform multi-dimensional feature vectors (distance maps of testing images) into a feature in a one-dimensional domain. The decision will be made on the simple one-dimensional feature domain according to a precalculated threshold to distinguish human figures from non-human figures. In comparison with the common method based on Mahalanobis distance maps, the proposed method based on Hausdorff distance maps performs much better. Encouraging experimental results have been obtained using 800 human images and 800 non-human images.
UR - http://www.scopus.com/inward/record.url?scp=44949166893&partnerID=8YFLogxK
U2 - 10.1109/DICTA.2007.4426777
DO - 10.1109/DICTA.2007.4426777
M3 - Conference contribution
AN - SCOPUS:44949166893
SN - 0769530672
SN - 9780769530673
T3 - Proceedings - Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society, DICTA 2007
SP - 67
EP - 72
BT - Proceedings - Digital Image Computing Techniques and Applications
T2 - Australian Pattern Recognition Society (APRS)
Y2 - 3 December 2007 through 5 December 2007
ER -