FSSSD: Fixed Scale SSD for Vehicle Detection

Jiwon Jun, Hyunjeong Pak, Moongu Jeon

Abstract

Since surveillance cameras are commonly installed in high places, the objects in the taken images are relatively small. Detecting small objects is a hard issue for the one-stage detector, and its performance in the surveillance system is not good. Two-stage detectors work better, but their speed is too slow to use in the real-time system. To remedy the drawbacks, we propose an efficient method, named as Fixed Scale SSD(FSSSD), which is an extension of SSD. The proposed method has three key points: high-resolution inputs to detect small objects, a lightweight Backbone to speed up, and prediction blocks to enrich features. FSSSD achieve 63.7% AP at 16.7 FPS in the UA-DETRAC test dataset. The performance is similar to two-stage detectors and faster than any other one-stage method.

Download


Paper Citation


in Harvard Style

Jun J., Pak H. and Jeon M. (2020). FSSSD: Fixed Scale SSD for Vehicle Detection.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, pages 336-342. DOI: 10.5220/0008950503360342


in Bibtex Style

@conference{visapp20,
author={Jiwon Jun and Hyunjeong Pak and Moongu Jeon},
title={FSSSD: Fixed Scale SSD for Vehicle Detection},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={336-342},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008950503360342},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - FSSSD: Fixed Scale SSD for Vehicle Detection
SN - 978-989-758-402-2
AU - Jun J.
AU - Pak H.
AU - Jeon M.
PY - 2020
SP - 336
EP - 342
DO - 10.5220/0008950503360342