Ensemble of Two-Stage Regression Based Detectors for Accurate Vehicle Detection in Traffic Surveillance Data

被引:0
作者
Sommer, Lars [1 ,2 ]
Acatay, Oliver [1 ]
Schumann, Arne [1 ]
Beyerer, Juergen [1 ,2 ]
机构
[1] Fraunhofer IOSB, Fraunhoferstr 1, D-76131 Karlsruhe, Germany
[2] KIT, Vis & Fus Lab, Technol Fabr, Haid & Neu Str 7, D-76131 Karlsruhe, Germany
来源
2018 15TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS) | 2018年
关键词
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The growing amount of traffic surveillance data results in an increased need for automatic detection systems to analyze the data. For this purpose, deep learning based detection frameworks like Faster R-CNN and SSD have been employed in recent years. Though the detection accuracy is clearly improved compared to conventional detection methods, there exists large potential for further improvements especially in case of adverse weather conditions. In this paper, we employ the RefineDet detection framework as it combines advantages of several detection frameworks including Faster R-CNN and SSD. We use an ensemble of two detectors with different base networks to generate detections that are more robust. For this, SENets-the winner of the ImageNet2017 classification challenge-are used in addition to ResNet-50. To account for small vehicles in the background and strong variation in vehicle scale, we apply multi-scale testing. Our proposed detector achieves top-performing results on the UA-DETRAC dataset especially in case of rainy and nighttime scenarios.
引用
收藏
页码:417 / 422
页数:6
相关论文
共 23 条
[1]  
Amin S., 2017, ADV VIDEO SIGNAL BAS, P1
[2]  
[Anonymous], 2018, COMPUTER VISION PATT
[3]  
[Anonymous], 2016, CVPR
[4]  
[Anonymous], IEEE T PATTERN ANAL
[5]  
[Anonymous], 2016, ADV NEURAL INFORM PR
[6]  
[Anonymous], 2015, P IEEE INT C COMPUTE
[7]  
[Anonymous], 2015, ICCV
[8]  
[Anonymous], 2013, IEEE Comput. Soc.
[9]  
[Anonymous], CVPR
[10]  
[Anonymous], 2015, ABS151104136 ARXIV C