Distributed Object Detection With Linear SVMs
- 26 February 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 44 (11), 2122-2133
- https://doi.org/10.1109/tcyb.2014.2301453
Abstract
In vision and learning, low computational complexity and high generalization are two important goals for video object detection. Low computational complexity here means not only fast speed but also less energy consumption. The sliding window object detection method with linear support vector machines (SVMs) is a general object detection framework. The computational cost is herein mainly paid in complex feature extraction and innerproduct-based classification. This paper first develops a distributed object detection framework (DOD) by making the best use of spatial-temporal correlation, where the process of feature extraction and classification is distributed in the current frame and several previous frames. In each framework, only subfeature vectors are extracted and the response of partial linear classifier (i.e., subdecision value) is computed. To reduce the dimension of traditional block-based histograms of oriented gradients (BHOG) feature vector, this paper proposes a cell-based HOG (CHOG) algorithm, where the features in one cell are not shared with overlapping blocks. Using CHOG as feature descriptor, we develop CHOG-DOD as an instance of DOD framework. Experimental results on detection of hand, face, and pedestrian in video show the superiority of the proposed method.Keywords
Funding Information
- National Basic Research Program of China 973 Program (2014CB340403)
- State Key Program of National Natural Science of China (61232010)
- National Natural Science Foundation of China (61172121, 61372145, 61172143, 61222109, 61271412)
- Program for New Century Excellent Talents in University (NCET-10-0620)
- Open Funding Project of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (BUAA-VR-13KF)
This publication has 55 references indexed in Scilit:
- Energy-saving object detection by efficiently rejecting a set of neighboring sub-imagesSignal Processing, 2013
- Fully affine invariant SURF for image matchingNeurocomputing, 2012
- Feature Extraction With Deep Neural Networks by a Generalized Discriminant AnalysisIEEE Transactions on Neural Networks and Learning Systems, 2012
- Learning optimal spatial filters by discriminant analysis for brain–computer-interfaceNeurocomputing, 2012
- Robust CoHOG Feature Extraction in Human-Centered Image/Video Management SystemIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Tactic analysis based on real-world ball trajectory in soccer videoPattern Recognition, 2011
- ORB: An efficient alternative to SIFT or SURFPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Efficient HOG human detectionSignal Processing, 2011
- Fast Haar Transform Based Feature Extraction for Face Representation and RecognitionIEEE Transactions on Information Forensics and Security, 2009
- Object Detection and Localization Using Local and Global FeaturesLecture Notes in Computer Science, 2006