Pedestrian detection method in vehicle video based on AMSSD

被引：0
作者：
Wang, Chunli [1 ]
Bai, Jinning [1 ]
机构：
[1] Dalian Maritime Univ, Sch Informat Sci & Technol, Dalian, Peoples R China
来源：
CONFERENCE PROCEEDINGS OF 2019 IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, COMMUNICATIONS AND COMPUTING (IEEE ICSPCC 2019) | 2019年
基金：
中国国家自然科学基金;
关键词：
pedestrian detection; SSD; MobileNet;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Pedestrian detection in vehicle video has high requirements for speed and accuracy of detection. To improve the detection speed, the underlying network of the SSD framework, the VGG-16 network, is replaced with MobileNet. In order to improve the detection accuracy of small targets, a deconvolution layer is added to this framework. With this layer, the feature map of low resolution and high semantic information with the feature map of high resolution and little semantic information is fused to increase the ability to extract the shallow feature. The VOC dataset and COCO dataset are used as the training set, and the Cityscapes dataset is used as the test set to verify the effect of the constructed framework AMSSD. The experimental results show that the proposed method can improve the detection speed and accuracy.
引用
收藏
页数：4
相关论文
共 28 条
[1]   3D Face Morphable Models "In-the-Wild" [J].
Booth, James ;
Antonakos, Epameinondas ;
Ploumpis, Stylianos ;
Trigeorgis, George ;
Panagakis, Yannis ;
Zafeiriou, Stefanos .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5464-5473
[2]   Cascade R-CNN: Delving into High Quality Object Detection [J].
Cai, Zhaowei ;
Vasconcelos, Nuno .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :6154-6162
[3]   A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection [J].
Cai, Zhaowei ;
Fan, Quanfu ;
Feris, Rogerio S. ;
Vasconcelos, Nuno .
COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 :354-370
[4]  
Chen LB, 2017, IEEE INT SYMP NANO, P1, DOI 10.1109/NANOARCH.2017.8053709
[5]   Semantic Channels for Fast Pedestrian Detection [J].
Costea, Arthur Daniel ;
Nedevschi, Sergiu .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2360-2368
[6]   MDSSD: multi-scale deconvolutional single shot detector for small objects [J].
Cui, Lisha ;
Ma, Rui ;
Lv, Pei ;
Jiang, Xiaoheng ;
Gao, Zhimin ;
Zhou, Bing ;
Xu, Mingliang .
SCIENCE CHINA-INFORMATION SCIENCES, 2020, 63 (02)
[7]  
Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036
[8]   Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection [J].
Du, Xianzhi ;
El-Khamy, Mostafa ;
Lee, Jungwon ;
Davis, Larry .
2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, :953-961
[9]  
Fu C., 2017, ARXIV, P1
[10]   Fast R-CNN [J].
Girshick, Ross .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1440-1448
123