人検出のための生成型学習とNegative-Bag MILBoostによる学習の効率化

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: 2014/03/01

タイトル(英語): Efficient Learning Method for Human Detection based on Automatic Generation of Training Samples with the Negative-Bag MILBoost

著者名: 土屋　成光（中部大学　工学部　情報工学科），山内　悠嗣（中部大学　工学部　情報工学科），藤吉　弘亘（中部大学　工学部　情報工学科）

著者名(英語): Masamitsu Tsuchiya (Dept. of Computer Science, Chubu University), Yuji Yamauchi (Dept. of Computer Science, Chubu University), Hironobu Fujiyoshi (Dept. of Computer Science, Chubu University)

キーワード: 3次元人体モデル，Negative-Bag MILBoost，人検出，生成型学習　　3D Human model，Negative-Bag MILBoost，Human Detection，Generative Learning

要約(英語): Statistical learning methods for human detection require large quantities of training samples and thus suffer from high sample collection costs. Their detection performance is also liable to be lower when the training samples are collected in a different environment than the one in which the detection system must operate. In this paper we propose a generative learning method that uses the automatic generation of training samples from 3D models together with an advanced MILBoost learning algorithm. In this study, we use a three-dimensional human model to automatically generate positive samples for learning specialized to specific scenes. Negative training samples are collected by random automatic extraction from video stream, but some of these samples may be collected with incorrect labeling. When a classifier is trained by statistical learning using incorrectly labeled training samples, this can impair its recognition performance. Therefore, in this study an improved version of MILBoost is used to perform generative learning which is immune to the adverse effects of incorrectly labeled samples among the training samples. In evaluation tests, we found that a classifier trained using training samples generated from a 3D human model was capable of better detection performance than a classifier trained using training samples extracted by hand. The proposed method can also mitigate the degradation of detection performance when there are image of people mixed in with the negative samples used for learning.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.3 （2014） 特集：情報環境と人間の調和に向けた工学技術

本誌掲載ページ: 450-458 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/134/3/134_450/_article/-char/ja/