Skip to main content

SRODNet: Object Detection Network Based on Super Resolution for Autonomous Vehicles

Author(s): Musunuri, Yogendra Rao; Kwon, Oh-Seol; Kung, Sun-Yuan

To refer to this page use:
Abstract: Object detection methods have been applied in several aerial and traffic surveillance applications. However, object detection accuracy decreases in low-resolution (LR) images owing to feature loss. To address this problem, we propose a single network, SRODNet, that incorporates both super-resolution (SR) and object detection (OD). First, a modified residual block (MRB) is proposed in the SR to recover the feature information of LR images, and this network was jointly optimized with YOLOv5 to benefit from hierarchical features for small object detection. Moreover, the proposed model focuses on minimizing the computational cost of network optimization. We evaluated the proposed model using standard datasets such as VEDAI-VISIBLE, VEDAI-IR, DOTA, and Korean highway traffic (KoHT), both quantitatively and qualitatively. The experimental results show that the proposed method improves the accuracy of vehicular detection better than other conventional methods.
Electronic Publication Date: 10-Dec-2022
Citation: Musunuri, Yogendra Rao, Kwon, Oh-Seol, Kung, Sun-Yuan. (SRODNet: Object Detection Network Based on Super Resolution for Autonomous Vehicles. Remote Sensing, 14 (24), 6270 - 6270. doi:10.3390/rs14246270
DOI: doi:10.3390/rs14246270
EISSN: 2072-4292
Language: en
Type of Material: Journal Article
Journal/Proceeding Title: Remote Sensing
Version: Final published version. This is an open access article.

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.