歩行者検出における混合正規分布を用いた状態空間の自律構成法

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2018/09/01

タイトル(英語): Autonomous State Space Construction Method Based on Mixed Normal Distributions for Pedestrian Detection

著者名: 道下　裕也（九州工業大学），東　嵩士（九州工業大学），柴田　雅聡（（株）エクォス・リサーチ），村松　竜弥（（株）エクォス・リサーチ），山田　英夫（（株）エクォス・リサーチ），榎田　修一（九州工業大学）

著者名(英語): Yuya Michishita (Kyushu Institute of Technology), Shuto Higashi (Kyushu Institute of Technology), Masatoshi Shibata (EQUOS RESEARCH Co., Ltd.), Ryuya Muramatsu (EQUOS RESEARCH Co., Ltd.), Hideo Yamada (EQUOS RESEARCH Co., Ltd.), Shuichi Enokida (Kyushu In

キーワード: 人物検出，JS情報量，混合正規分布　　people detection，Jensen-Shannon divergence，mixed gaussian model

要約(英語): Recently, Co-occurrence histograms of oriented gradients (CoHOG) describes image features to calculate the co-occurrence of pixels allocated at the local level and has attracted attention as an effective object detection method. However, this method has some problems. For feature descriptions that focus on individual pixels, calculation cost and the number of dimensions tend to increase exponentially with respect to the number of pixels. Multiresolution CoHOG (MRCoHOG) can suppress such exponential increases to linear increase without reducing the classification accuracy. This paper proposes a procedure in which a feature plane is divided using a Gaussian mixture model and a histogram is automatically divided to establish a less costly method for performing MRCoHOG. Experimental results demonstrate that the proposed procedure is more effective than conventional procedures.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.138 No.9 （2018） 特集Ⅰ：知能メカトロニクス分野と連携する知覚情報技術 特集Ⅱ：国際会議ICESS 2017

本誌掲載ページ: 1100-1107 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/138/9/138_1100/_article/-char/ja/