Presentation | 2014-06-12 Optimized HOG for Database System Mao HATTO, Takaaki MIYAJIMA, Hiroki MATSUTANI, Hideharu AMANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | As technology of High Performance Computing and Pattern Recognition has evolved rapidly, Human Detection system also has gathered attention recently. HOG (Histogram of Oriented Gradients) is an effective way for extract feature values. Also, Real Adaboost Algorithm has a good discrernment performance and easiness for implementation. Feature data collected by such kind of human detection system are stored in a database server, and they are expected to apply for security system or some otehr useful application. However, these are some difficulities in the human detection system, which consists HOG feature and Real Adaboost, due to large data of feature values. In this paper, we aim the reduction of feature data with same detection accuracy using fixed-point arithmetic and LUTs (Look Up Table), and high performance execution via FPGA (Field-Programmable Gate Array). |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Human Detection / HOG / Real Adaboost / FPGA |
Paper # | RECONF2014-3 |
Date of Issue |
Conference Information | |
Committee | RECONF |
---|---|
Conference Date | 2014/6/4(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Reconfigurable Systems (RECONF) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Optimized HOG for Database System |
Sub Title (in English) | |
Keyword(1) | Human Detection |
Keyword(2) | HOG |
Keyword(3) | Real Adaboost |
Keyword(4) | FPGA |
1st Author's Name | Mao HATTO |
1st Author's Affiliation | Graduate School of Science and Technology, Keio University() |
2nd Author's Name | Takaaki MIYAJIMA |
2nd Author's Affiliation | Graduate School of Science and Technology, Keio University |
3rd Author's Name | Hiroki MATSUTANI |
3rd Author's Affiliation | Graduate School of Science and Technology, Keio University |
4th Author's Name | Hideharu AMANO |
4th Author's Affiliation | Graduate School of Science and Technology, Keio University |
Date | 2014-06-12 |
Paper # | RECONF2014-3 |
Volume (vol) | vol.114 |
Number (no) | 75 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |