D2D: Divide to Detect, A Scale-Aware Framework for On-Road Object Detection Using IR Camera

Van Tin Luu, Vu Hoang Tran, Egor Poliakov, Ching Chun Huang

研究成果: Conference contribution同行評審

摘要

In this paper, to solve the problem of inconsistencies between the predictions in today's SOTA object detection networks, which incorporate the pyramid architecture with multi-level prediction, we proposed a scale-aware framework for IR image-based on-road object detection. The proposed framework uses scale-based attention mechanism to assign responsibilities to each feature levels. With this design, each feature level will focus on detecting a certain range of object scales, thereby minimizing the conflict among the predictions in the final result. Compared to Scaled-YOLOv4 baseline, our proposed method can achieve better performance without increasing FPS on FLIR dataset. The experimental results on RGB image-based object detection datasets also show that our proposed method gives good improvements when applied to RGB images.

原文English
主出版物標題2023 IEEE International Conference on Consumer Electronics, ICCE 2023
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665491303
DOIs
出版狀態Published - 2023
事件2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States
持續時間: 6 1月 20238 1月 2023

出版系列

名字Digest of Technical Papers - IEEE International Conference on Consumer Electronics
2023-January
ISSN(列印)0747-668X

Conference

Conference2023 IEEE International Conference on Consumer Electronics, ICCE 2023
國家/地區United States
城市Las Vegas
期間6/01/238/01/23

指紋

深入研究「D2D: Divide to Detect, A Scale-Aware Framework for On-Road Object Detection Using IR Camera」主題。共同形成了獨特的指紋。

引用此