DocumentCode :
6224
Title :
Distributed Object Detection With Linear SVMs
Author :
Yanwei Pang ; Kun Zhang ; Yuan Yuan ; Kongqiao Wang
Author_Institution :
Sch. of Electron. Inf. Eng., Tianjin Univ., Tianjin, China
Volume :
44
Issue :
11
fYear :
2014
fDate :
Nov. 2014
Firstpage :
2122
Lastpage :
2133
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 :
computational complexity; feature extraction; generalisation (artificial intelligence); image classification; object detection; spatiotemporal phenomena; support vector machines; video signal processing; BHOG feature vector; CHOG algorithm; CHOG-DOD; block-based histograms of oriented gradients feature vector; cell-based HOG algorithm; complex feature extraction; computational complexity; computational cost; distributed classification; distributed object detection framework; energy consumption; feature descriptor; generalization; innerproduct-based classification; linear SVM; linear support vector machines; partial linear classifier; sliding window object detection method; spatial-temporal correlation; subfeature vector extraction; video object detection; Computational efficiency; Feature extraction; Histograms; Object detection; Support vector machines; US Department of Defense; Vectors; Cell-based histograms of oriented gradients (CHOG); computer vision; feature extraction; linear classifier; machine learning; object detection;
fLanguage :
English
Journal_Title :
Cybernetics, IEEE Transactions on
Publisher :
ieee
ISSN :
2168-2267
Type :
jour
DOI :
10.1109/TCYB.2014.2301453
Filename :
6748917
Link To Document :
بازگشت