Publication Details
Real-time Algorithms of Object Detection using Classifiers
Hradiš Michal, Ing., Ph.D. (DCGM)
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)
WaldBoost, Object Detection, Classification Cost, EnMS, Neighborhood Suppression, Acceleration, GPU, SIMD, FPGA
Real-time objectdetection is currently expanding field of computer vision. One ofmost popular methods for the object detection is based onexploitation of statistical classifiers (namely those based onAdaBoost algorithm). This contribution presents methods foracceleration of object detection based on the AdaBoost. First itdescribes image pre-processing and the learning of classifiers.Finally, the contribution presents algorithmic accelerations of thedetection process and effective implementations of classification onvarious architectures - CPU/SSE, GPGPU and FPGA. Accelerateddetectors achieve high performance compared to state of the artsolutions and are suitable for real-time applications.
@inbook{BUT91467,
author="Roman {Juránek} and Michal {Hradiš} and Pavel {Zemčík}",
title="Real-time Algorithms of Object Detection using Classifiers",
booktitle="Real-Time System",
year="2012",
publisher="InTech - Open Access Publisher",
address="Rijeka",
pages="1--22",
isbn="9789535105107",
url="http://www.intechopen.com/books/real-time-systems-architecture-scheduling-and-application"
}