1 0 0 0 OA 回転型ステレオカメラを用いた屋外シーンの密な三次元再構成
- 著者
- 吉田 武史 深尾 隆則
- 出版者
- The Society of Instrument and Control Engineers
- 雑誌
- 計測自動制御学会論文集 (ISSN:04534654)
- 巻号頁・発行日
- vol.49, no.1, pp.149-157, 2013 (Released:2013-02-08)
- 参考文献数
- 13
- 被引用文献数
- 1
This paper proposes a method to construct a three-dimensional (3D) model of an outdoor scene containing a large amount of information by combining local stereo images which are acquired from multiway. It is difficult to reconstruct outdoor scenes accurately using a single view of a stereo camera because the distance to a target is very far compared with the stereo camera's baseline length. Therefore the proposed method makes the 3D model accurately by reducing the uncertainties of a 3D point from various angles to the region which includes the correct point. Multi-view stereo images are captured using a rotational stereo camera that swings back and forth and can capture not only the upper surface of an object but also the side surface of the object. As an experiment, a blimp robot with a rotational stereo camera is used to capture aerial stereo images of the ground. The proposed method achieves the dense and accurate reconstruction of the outdoor 3D model.
1 0 0 0 OA のれんの回収可能性とその会計処理に関する考察
- 著者
- 吉田 武史
- 出版者
- 横浜商科大学
- 雑誌
- 横浜商大論集 (ISSN:02876825)
- 巻号頁・発行日
- vol.47, no.1, pp.103-138, 2013-09-30
1 0 0 0 下咽頭癌に対する内視鏡的粘膜下層剥離術
1 0 0 0 食道癌 (特集 消化器癌の予防はどこまで可能か)
- 著者
- 吉田 武史 清水 勇一 廣田 ジョージョ
- 出版者
- メディカルレビュー社
- 雑誌
- The GI forefront (ISSN:13499629)
- 巻号頁・発行日
- vol.3, no.2, pp.118-122, 2007-12
1 0 0 0 ステレオ視とHOGを用いた歩行者認識手法
- 著者
- 外谷文人 吉田 武史 胡振程 内村 圭一
- 出版者
- 一般社団法人情報処理学会
- 雑誌
- 情報処理学会研究報告高度交通システム(ITS) (ISSN:09196072)
- 巻号頁・発行日
- vol.2008, no.25, pp.21-27, 2008-03-07
歩行中の交通事故死亡者数を低減するため,車載カメラを利用した歩行者認識システムの要求が高まっている.本論文では,車両に設置した左右2台のカメラから得られる視差情報とHOGフィルタを用いた歩行者認識手法について提案する.まず,左右の画像から視差画像を算出し,視差情報をもとに領域分割を行い,背景領域を除去するその後,SobeIフィルタによりエッジ情報を抽出し,HOGフィルタを適用後,NaiveBayesCIassifierを用いて歩行者の認識を行う.これらの手法を道路撮影画像に適用し,有効性の確認と検証を行う. In late years, traffic fatalities in the pedestrian percentage is growing. Therefore, pedestrian aimed at the prevention of traffic accidents is to build the system demands. In this paper, as a part of the prevention of traffic accident system for the pedestrian, I propose pedestrian recognition using stereo vision and histogram of oriented gradient(HOG). First, we abstract pedestrian area from disparity image which is obtained from stereo vision. Next, we created edge image from the original image with Soble Filter. And abstract only edge included in pedestrian area. We perform HOG process for the edge image, and get the HOG feature. We perform pedestrian recognition with Naive Bayes Classifier using HOG feature. As inspection of this technique, I performed inspection by the ROC curve and inspection with a database for inspection. We showed that this approach was effective as pedestrian recognition method.