TY - JOUR
T1 - Occlusion Handling via Random Subspace Classifiers for Human Detection
AU - Marin, Javier
AU - Vazquez, David
AU - Lopez, Antonio M.
AU - Amores, Jaume
AU - Kuncheva, Ludmila I.
PY - 2014/3
Y1 - 2014/3
N2 - This paper describes a general method to address partial occlusions for human detection in still images. The random subspace method (RSM) is chosen for building a classifier ensemble robust against partial occlusions. The component classifiers are chosen on the basis of their individual and combined performance. The main contribution of this work lies in our approach's capability to improve the detection rate when partial occlusions are present without compromising the detection performance on non occluded data. In contrast to many recent approaches, we propose a method which does not require manual labeling of body parts, defining any semantic spatial components, or using additional data coming from motion or stereo. Moreover, the method can be easily extended to other object classes. The experiments are performed on three large datasets: the INRIA person dataset, the Daimler Multicue dataset, and a new challenging dataset, called PobleSec, in which a considerable number of targets are partially occluded. The different approaches are evaluated at the classification and detection levels for both partially occluded and non-occluded data. The experimental results show that our detector outperforms state-of-the-art approaches in the presence of partial occlusions, while offering performance and reliability similar to those of the holistic approach on non-occluded data. The datasets used in our experiments have been made publicly available for benchmarking purposes.
AB - This paper describes a general method to address partial occlusions for human detection in still images. The random subspace method (RSM) is chosen for building a classifier ensemble robust against partial occlusions. The component classifiers are chosen on the basis of their individual and combined performance. The main contribution of this work lies in our approach's capability to improve the detection rate when partial occlusions are present without compromising the detection performance on non occluded data. In contrast to many recent approaches, we propose a method which does not require manual labeling of body parts, defining any semantic spatial components, or using additional data coming from motion or stereo. Moreover, the method can be easily extended to other object classes. The experiments are performed on three large datasets: the INRIA person dataset, the Daimler Multicue dataset, and a new challenging dataset, called PobleSec, in which a considerable number of targets are partially occluded. The different approaches are evaluated at the classification and detection levels for both partially occluded and non-occluded data. The experimental results show that our detector outperforms state-of-the-art approaches in the presence of partial occlusions, while offering performance and reliability similar to those of the holistic approach on non-occluded data. The datasets used in our experiments have been made publicly available for benchmarking purposes.
KW - Ensemble
KW - Human detection
KW - Partial occlusions
KW - Random subspace classifiers
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=uab_pure&SrcAuth=WosAPI&KeyUT=WOS:000331906100004&DestLinkType=FullRecord&DestApp=WOS
U2 - 10.1109/TCYB.2013.2255271
DO - 10.1109/TCYB.2013.2255271
M3 - Article
C2 - 23757554
SN - 2168-2267
VL - 44
SP - 342
EP - 354
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 3
ER -