Realtime Single-Shot Refinement Neural Network for 3D Obejct Detection from LiDAR Point Cloud

Yutian Wu, Harutoshi Ogai

研究成果: Conference contribution

抄録

3D object detection from point cloud is an important aspect of environmental perception in intelligent systems such as autonomous driving systems and robot systems. However, efficient 3D feature extraction and accurate object localization is challenging for current algorithms. In this paper, we introduce a new single-shot refinement neural network for fast and accurate 3D object detection. Firstly, we simplify the 3D feature extraction network and use single-shot object detector to increase processing speed. Secondly, we exploit self-attention mechanism in main object detection branch to improve object feature representation. Thirdly, an object refinement branch is introduced to produce a finer regression of objects upon the primary estimation from the main detection branch. Both modifications lead to further improvements in performance without additional computational cost. Our approach is tested on KITTI 3D Car detection benchmark and achieves good results in the validation set. The running speed is around 40 frame per second.

本文言語English
ホスト出版物のタイトル2020 59th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ332-337
ページ数6
ISBN(電子版)9781728110899
出版ステータスPublished - 2020 9 23
イベント59th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2020 - Chiang Mai, Thailand
継続期間: 2020 9 232020 9 26

出版物シリーズ

名前2020 59th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2020

Conference

Conference59th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2020
国/地域Thailand
CityChiang Mai
Period20/9/2320/9/26

ASJC Scopus subject areas

  • 制御と最適化
  • 器械工学
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理
  • 決定科学(その他)
  • 産業および生産工学

フィンガープリント

「Realtime Single-Shot Refinement Neural Network for 3D Obejct Detection from LiDAR Point Cloud」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル