Abstract:
We present a new algorithm to detect pedestrian in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, wel...Show MoreMetadata
Abstract:
We present a new algorithm to detect pedestrian in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, well known machine learning techniques are not well suited to learn the classifiers. The space of d-dimensional nonsingular covariance matrices can be represented as a connected Riemannian manifold. The main contribution of the paper is a novel approach for classifying points lying on a connected Riemannian manifold using the geometry of the space. The algorithm is tested on INRIA and DaimlerChrysler pedestrian datasets where superior detection rates are observed over the previous approaches.
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 30, Issue: 10, October 2008)
Feature extraction of hyperspectral image using principal component analysis and folded-principal component analysis
P. Deepa,K. Thilagavathi
Optimization of Principal Component Analysis in Feature Extraction
Gao Haibo,Hong Wenxue,Cui Jianxin,Xu Yonghong
Mode Shape Estimation using Complex Principal Component Analysis and k-Means Clustering
Hallvar Haugdal,Kjetil Uhlen
A Novel Face Feature Extraction Method Based on Two-dimensional Principal Component Analysis and Kernel Discriminant Analysis
Xiaoguo Wang,Jun Liu,Ming Tian,Yong Huang,Tieyong Cao,Xiongwei Zhang
A statistical shape model using 2D-principal component analysis from few medical samples and its evaluation
Tomoko Tateyama,Taishi Tanaka,Shinya Kohara,Amir Hossein Foruzan,Akira Furukawa,Yen-Wei Chen
Why principal component analysis is not an appropriate feature extraction method for hyperspectral data
A. Cheriyadat,L.M. Bruce
A ship detector applying principal component analysis to the Polarimetric Notch Filter
Tao Zhang,Armando Marino,Huilin Xiong
A global covariance matrix based principal component analysis for speaker identification
Chagnwoo Seo,Jun Youn,Youngeun Kim,Keunho Sim,Jaekwan Ko,Meihua Zhao,Jongkeun Kim,Heeae Ko,Eunyoung Kim,Younghwan Lim
Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis
Yuemei Ren,Liang Liao,Stephen John Maybank,Yanning Zhang,Xin Liu