Contextual information based network with high-frequency feature fusion for high frame rate and ultra-low delay small-scale object detection

Dongmei Huang*, Jihan Zhang, Tingting Hu, Ryuji Fuchikami, Takashi Ikenaga

*この研究の対応する著者

研究成果: Conference contribution

抄録

High frame rate and ultra-low delay small-scale object detection plays an important role in factory automation for its timely and accurate reaction. Although many CNN based detection methods have been proposed to improve the accuracy of small object detection for the low resolution and large gap between the object and the background, it is difficult to achieve a trade-off between accuracy and speed. For the pursuit of ultra-low delay processing by utilizing FPGA, this paper proposes: (A) IoU and distance based loss function, (B) Contextual information with high temporal correlation based parallel detection, (C) High frequency feature fusion for enhancing low-bit networks. The proposed methods achieve 45.3 % mAP for test sequences, which is only 0.7 % mAP lower compared with the general method. Meanwhile, the size of the model has been compressed to 1.94 % of the original size and reaches a speed of 278 fPs on FPGA and 15 fPs on GPU.

本文言語English
ホスト出版物のタイトルProceedings of MVA 2021 - 17th International Conference on Machine Vision Applications
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9784901122207
DOI
出版ステータスPublished - 2021 7 25
イベント17th International Conference on Machine Vision Applications, MVA 2021 - Aichi, Japan
継続期間: 2021 7 252021 7 27

出版物シリーズ

名前Proceedings of MVA 2021 - 17th International Conference on Machine Vision Applications

Conference

Conference17th International Conference on Machine Vision Applications, MVA 2021
国/地域Japan
CityAichi
Period21/7/2521/7/27

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理

フィンガープリント

「Contextual information based network with high-frequency feature fusion for high frame rate and ultra-low delay small-scale object detection」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