2026-05-14T20:39:15Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00188762 2025-01-20T01:55:39Z 6504:9465:9481

オフィス環境における逐次学習を用いた人物検出 羽入, 達也 趙, 強福 人工知能と認知科学 To design a good human detector, we may collect a huge number of data, and train the detector off-line. However, even if the training data set is very large, it may not contain enough information for some specific environment, and the obtained model may not generalize well. In this paper, we study incremental learning of a support vector machine-based human detector in an office environment. Experimental results show that it is possible to obtain a good human detector customized to a certain environment with less data if we use incremental learning. conference paper 情報処理学会 2018-03-13 application/pdf 第80回全国大会講演論文集 1 2018 505 506 AN00349328 https://ipsj.ixsq.nii.ac.jp/record/188762/files/IPSJ-Z80-2S-03.pdf eng