Cooperative Multi-Scale Convolutional Neural Networks for Person Detection

被引:0
|
作者
Eisenbach, Markus [1 ]
Seichter, Daniel [1 ]
Wengefeld, Tim [1 ]
Gross, Horst-Michael [1 ]
机构
[1] Ilmenau Univ Technol, Neuroinformat & Cognit Robot Lab, D-98684 Ilmenau, Germany
关键词
PEDESTRIAN DETECTION; MODEL;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Robust person detection is required by many computer vision applications. We present a deep learning approach, that combines three Convolutional Neural Networks to detect people at different scales, which is the first time that a mult-iresolution model is combined with deep learning techniques in the pedestrian detection domain. The networks learn features from raw pixel information, which is also rare for pedestrian detection. Due to the use of multiple Convolutional Neural Networks at different scales, the learned features are specific for far, medium, and near scales respectively, and thus, the overall performance is improved. Furthermore, we show, that neural approaches can also be applied successfully for the remaining processing steps of classification and non-maximum suppression. The evaluation on the most popular Caltech pedestrian detection benchmark shows that the proposed method can compete with state of the art methods without using Caltech training data and without fine tuning. Therefore, it is shown that our method generalizes well on domains it is not trained on.
引用
收藏
页码:267 / 276
页数:10
相关论文
共 50 条
  • [1] Atrial Fibrillation Detection by Multi-scale Convolutional Neural Networks
    Yao, Zhenjie
    Zhu, Zhiyong
    Chen, Yixin
    [J]. 2017 20TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2017, : 1159 - 1164
  • [2] MSCNN: Steganographer Detection Based on Multi-Scale Convolutional Neural Networks
    Yang, Jinglan
    Dong, Chao
    Zhang, Feng
    Lei, Min
    Bai, Xu
    [J]. WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, WASA 2021, PT I, 2021, 12937 : 215 - 226
  • [3] Multi-scale object detection in remote sensing imagery with convolutional neural networks
    Deng, Zhipeng
    Sun, Hao
    Zhou, Shilin
    Zhao, Juanping
    Lei, Lin
    Zou, Huanxin
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 145 : 3 - 22
  • [4] Multi-scale convolutional neural networks for cloud segmentation
    Aouaidjia, Kamel
    Boukerch, Issam
    [J]. REMOTE SENSING OF CLOUDS AND THE ATMOSPHERE XXV, 2020, 11531
  • [5] MULTI-SCALE CONVOLUTIONAL NEURAL NETWORKS FOR CROWD COUNTING
    Zeng, Lingke
    Xu, Xiangmin
    Cai, Bolun
    Qiu, Suo
    Zhang, Tong
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 465 - 469
  • [6] Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks
    Pan, Xipeng
    Yang, Dengxian
    Li, Lingqiao
    Liu, Zhenbing
    Yang, Huihua
    Cao, Zhiwei
    He, Yubei
    Ma, Zhen
    Chen, Yiyi
    [J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2018, 21 (06): : 1721 - 1743
  • [7] MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection
    Ma, Wenchi
    Wu, Yuanwei
    Wang, Zongbo
    Wang, Guanghui
    [J]. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 2510 - 2515
  • [8] Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks
    Xipeng Pan
    Dengxian Yang
    Lingqiao Li
    Zhenbing Liu
    Huihua Yang
    Zhiwei Cao
    Yubei He
    Zhen Ma
    Yiyi Chen
    [J]. World Wide Web, 2018, 21 : 1721 - 1743
  • [9] Coronary Artery Fibrous Plaque Detection Based on Multi-Scale Convolutional Neural Networks
    Xiuling Liu
    Jiaxing Du
    Jianli Yang
    Peng Xiong
    Jing Liu
    Feng Lin
    [J]. Journal of Signal Processing Systems, 2020, 92 : 325 - 333
  • [10] Coronary Artery Fibrous Plaque Detection Based on Multi-Scale Convolutional Neural Networks
    Liu, Xiuling
    Du, Jiaxing
    Yang, Jianli
    Xiong, Peng
    Liu, Jing
    Lin, Feng
    [J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2020, 92 (03): : 325 - 333