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: 2021/12/01タイトル(英語): 3D Object Detection by 3D Geometric Information and Deep Neural Network for Avoiding Unknown Low-height Obstacles著者名: 雨宮 立弥（名城大学理工学部），田崎 豪（名城大学理工学部）著者名(英語): Tatsuya Amemiya (Faculty of Science and Technology, Meijo University), Tsuyoshi Tasaki (Faculty of Science and Technology, Meijo University)キーワード: 障害物回避，Semantic Segmentation，Deep Neural Network，法線マップ obstacle avoidance，Semantic Segmentation，Deep Neural Network，normal map要約(英語): In this study, we developed a new method to detect unknown low-height obstacles using 3D point clouds from stereo cameras. Conventional semantic segmentation methods using a depth image by Deep Neural Network (DNN) can detect road surfaces with a high accuracy. However, it is difficult to detect unknown low-height obstacles not included in the training data. Methods that use geometric information such as normal and height face difficulty to find objects with a surface that parallels to the road surface and low objects, respectively. Therefore, we deal with the difficult problem of detecting unknown low-height obstacles. To solve the problem, we focused on the difference in difficult detection between DNN and geometric methods. Based on the confidence from the output of DNN, we help difficult obstacle detection for DNN by using geometric information, and vice versa. When tested on a robot equipped with a stereo camera, the IoU, which indicates the detection accuracy of unknown obstacles, was improved by 18.1 percentage points compared to DNN. Moreover, our method enabled the robot to safely avoid three types of unknown low-height obstacles.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.141 No.12 （2021） 特集Ⅰ：電気・電子・情報関係学会東海支部連合大会 特集Ⅱ：研究会優秀論文本誌掲載ページ: 1256-1264 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/141/12/141_1256/_article/-char/ja/
