Single Stage Vehicle Logo Detector Based on Multi-Scale Prediction

Junxing ZHANG; Shuo YANG; Chunjuan BO; Huimin LU

doi:10.1587/transinf.2020EDP7088

Single Stage Vehicle Logo Detector Based on Multi-Scale Prediction

Junxing ZHANG, Shuo YANG, Chunjuan BO, Huimin LU

Full Text Views

0

Cite this

Summary :

Vehicle logo detection technology is one of the research directions in the application of intelligent transportation systems. It is an important extension of detection technology based on license plates and motorcycle types. A vehicle logo is characterized by uniqueness, conspicuousness, and diversity. Therefore, thorough research is important in theory and application. Although there are some related works for object detection, most of them cannot achieve real-time detection for different scenes. Meanwhile, some real-time detection methods of single-stage have performed poorly in the object detection of small sizes. In order to solve the problem that the training samples are scarce, our work in this paper is improved by constructing the data of a vehicle logo (VLD-45-S), multi-stage pre-training, multi-scale prediction, feature fusion between deeper with shallow layer, dimension clustering of the bounding box, and multi-scale detection training. On the basis of keeping speed, this article improves the detection precision of the vehicle logo. The generalization of the detection model and anti-interference capability in real scenes are optimized by data enrichment. Experimental results show that the accuracy and speed of the detection algorithm are improved for the object of small sizes.

Publication: IEICE TRANSACTIONS on Information Vol.E103-D No.10 pp.2188-2198

Publication Date: 2020/10/01

Publicized: 2020/07/14

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020EDP7088

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Junxing ZHANG
  Dalian Minzu University
Shuo YANG
  Kyushu Institute of Technology
Chunjuan BO
  Dalian Minzu University
Huimin LU
  Kyushu Institute of Technology

Keyword

vehicle logo detection, VLD-45-S, single-stage detector, multi-scale prediction, feature fusion

Cite this

Copy

Junxing ZHANG, Shuo YANG, Chunjuan BO, Huimin LU, "Single Stage Vehicle Logo Detector Based on Multi-Scale Prediction" in IEICE TRANSACTIONS on Information, vol. E103-D, no. 10, pp. 2188-2198, October 2020, doi: 10.1587/transinf.2020EDP7088.
Abstract: Vehicle logo detection technology is one of the research directions in the application of intelligent transportation systems. It is an important extension of detection technology based on license plates and motorcycle types. A vehicle logo is characterized by uniqueness, conspicuousness, and diversity. Therefore, thorough research is important in theory and application. Although there are some related works for object detection, most of them cannot achieve real-time detection for different scenes. Meanwhile, some real-time detection methods of single-stage have performed poorly in the object detection of small sizes. In order to solve the problem that the training samples are scarce, our work in this paper is improved by constructing the data of a vehicle logo (VLD-45-S), multi-stage pre-training, multi-scale prediction, feature fusion between deeper with shallow layer, dimension clustering of the bounding box, and multi-scale detection training. On the basis of keeping speed, this article improves the detection precision of the vehicle logo. The generalization of the detection model and anti-interference capability in real scenes are optimized by data enrichment. Experimental results show that the accuracy and speed of the detection algorithm are improved for the object of small sizes.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7088/_p

Copy

@ARTICLE{e103-d_10_2188,
author={Junxing ZHANG, Shuo YANG, Chunjuan BO, Huimin LU, },
journal={IEICE TRANSACTIONS on Information},
title={Single Stage Vehicle Logo Detector Based on Multi-Scale Prediction},
year={2020},
volume={E103-D},
number={10},
pages={2188-2198},
abstract={Vehicle logo detection technology is one of the research directions in the application of intelligent transportation systems. It is an important extension of detection technology based on license plates and motorcycle types. A vehicle logo is characterized by uniqueness, conspicuousness, and diversity. Therefore, thorough research is important in theory and application. Although there are some related works for object detection, most of them cannot achieve real-time detection for different scenes. Meanwhile, some real-time detection methods of single-stage have performed poorly in the object detection of small sizes. In order to solve the problem that the training samples are scarce, our work in this paper is improved by constructing the data of a vehicle logo (VLD-45-S), multi-stage pre-training, multi-scale prediction, feature fusion between deeper with shallow layer, dimension clustering of the bounding box, and multi-scale detection training. On the basis of keeping speed, this article improves the detection precision of the vehicle logo. The generalization of the detection model and anti-interference capability in real scenes are optimized by data enrichment. Experimental results show that the accuracy and speed of the detection algorithm are improved for the object of small sizes.},
keywords={},
doi={10.1587/transinf.2020EDP7088},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Single Stage Vehicle Logo Detector Based on Multi-Scale Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 2188
EP - 2198
AU - Junxing ZHANG
AU - Shuo YANG
AU - Chunjuan BO
AU - Huimin LU
PY - 2020
DO - 10.1587/transinf.2020EDP7088
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2020
AB - Vehicle logo detection technology is one of the research directions in the application of intelligent transportation systems. It is an important extension of detection technology based on license plates and motorcycle types. A vehicle logo is characterized by uniqueness, conspicuousness, and diversity. Therefore, thorough research is important in theory and application. Although there are some related works for object detection, most of them cannot achieve real-time detection for different scenes. Meanwhile, some real-time detection methods of single-stage have performed poorly in the object detection of small sizes. In order to solve the problem that the training samples are scarce, our work in this paper is improved by constructing the data of a vehicle logo (VLD-45-S), multi-stage pre-training, multi-scale prediction, feature fusion between deeper with shallow layer, dimension clustering of the bounding box, and multi-scale detection training. On the basis of keeping speed, this article improves the detection precision of the vehicle logo. The generalization of the detection model and anti-interference capability in real scenes are optimized by data enrichment. Experimental results show that the accuracy and speed of the detection algorithm are improved for the object of small sizes.
ER -