Recursive hybrid fusion pyramid network for real-time small object detection on embedded devices

Ping Yang Chen, Jun Wei Hsieh, Chien Yao Wang, Hong Yuan Mark Liao

研究成果: Conference contribution同行評審

摘要

This paper proposes a novel RHF-Net (Recursive Hybrid Fusion pyramid network) to solve the problem of small object detection on real-time embedded devices. Though the object detection accuracy rate is improved by a large margin with SoTA (State-of-The-Art) models, e.g., SSD, YOLO, RetinaNet, and RefineDet, they are still problematic for small object detection and inefficient on embedded systems. One novelty of the RHF-Net is a bidirectional fusion module) that allows to fuse feature maps with both the top-down and bottom-up directions to generate flexible FPs for small object detection. This module can be easily integrated to any feature pyramid based object detection model. Another novelty of this net is a recursive concatenation and reshaping module which can recursively concatenate not only high-level semantic features from deep layers but also reshape spatially richer features from shallower layers to prevent small objects from disappearing. RHF-Net net adopts computationally low-cost and feature preserving operations in the fusion, thus it is efficient and accurate even on embedded devices. The superiority of RHF-Net is investigated on the COCO benchmark and UAVDT dataset in terms of mAP and FPS.

原文English
主出版物標題Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
發行者IEEE Computer Society
頁面1612-1621
頁數10
ISBN(電子)9781728193601
DOIs
出版狀態Published - 六月 2020
事件2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States
持續時間: 14 六月 202019 六月 2020

出版系列

名字IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
2020-June
ISSN(列印)2160-7508
ISSN(電子)2160-7516

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
國家United States
城市Virtual, Online
期間14/06/2019/06/20

指紋 深入研究「Recursive hybrid fusion pyramid network for real-time small object detection on embedded devices」主題。共同形成了獨特的指紋。

引用此