Semantic fusion of laser and vision in pedestrian detection

被引:34
作者
Oliveira, Luciano [1 ]
Nunes, Urbano [1 ]
Peixoto, Paulo [1 ]
Silva, Marco [1 ]
Moita, Fernando [1 ]
机构
[1] Univ Coimbra, Inst Syst & Robot, Coimbra, Portugal
关键词
Semantic sensor fusion; Pedestrian detection; Markov logic network;
D O I
10.1016/j.patcog.2010.05.014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Fusion of laser and vision in object detection has been accomplished by two main approaches: (1) independent integration of sensor-driven features or sensor-driven classifiers, or (2) a region of interest (ROI) is found by laser segmentation and an image classifier is used to name the projected ROI. Here, we propose a novel fusion approach based on semantic information, and embodied on many levels. Sensor fusion is based on spatial relationship of parts-based classifiers, being performed via a Markov logic network. The proposed system deals with partial segments, it is able to recover depth information even if the laser fails, and the integration is modeled through contextual information characteristics not found on previous approaches. Experiments in pedestrian detection demonstrate the effectiveness of our method over data sets gathered in urban scenarios. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:3648 / 3659
页数:12
相关论文
共 50 条
  • [31] Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications
    Budzan, Sebastian
    Wyzgolik, Roman
    Ilewicz, Witold
    APPLIED SCIENCES-BASEL, 2018, 8 (10):
  • [32] Semantic-driven multi-camera pedestrian detection
    Lopez-Cifuentes, Alejandro
    Escudero-Vinolo, Marcos
    Bescos, Jesus
    Carballeira, Pablo
    KNOWLEDGE AND INFORMATION SYSTEMS, 2022, 64 (05) : 1211 - 1237
  • [33] Pedestrian detection method based on feature fusion Centernet
    Fu, Xiaobiao
    Wang, Zhiwen
    Huang, Lincai
    Wang, Yuhang
    Zhang, Canlong
    2022 IEEE 6TH ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC), 2022, : 1834 - 1838
  • [34] Pedestrian Detection Fusion Method Based On Mean Shift
    Yu, Liping
    Yao, Wentao
    2009 SECOND INTERNATIONAL CONFERENCE ON MACHINE VISION, PROCEEDINGS, ( ICMV 2009), 2009, : 204 - +
  • [35] A New Descriptor for Pedestrian Detection Based on Feature Fusion
    Wang, Denggui
    Yang, Rong
    2018 8TH IEEE INTERNATIONAL CONFERENCE ON CONTROL SYSTEM, COMPUTING AND ENGINEERING (ICCSCE 2018), 2018, : 37 - 42
  • [36] Stabilizing Multispectral Pedestrian Detection With Evidential Hybrid Fusion
    Li, Qing
    Zhang, Changqing
    Hu, Qinghua
    Zhu, Pengfei
    Fu, Huazhu
    Chen, Lei
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (04) : 3017 - 3029
  • [37] Semantic-driven multi-camera pedestrian detection
    Alejandro López-Cifuentes
    Marcos Escudero-Viñolo
    Jesús Bescós
    Pablo Carballeira
    Knowledge and Information Systems, 2022, 64 : 1211 - 1237
  • [38] Semantic enhanced guide feature reconstruction for occluded pedestrian detection
    Sun X.
    Wu Q.
    Zhao C.
    Zhang M.
    Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering, 2022, 51 (09):
  • [39] Deep Feature Fusion by Competitive Attention for Pedestrian Detection
    Chen, Zhichang
    Zhang, Li
    Khattak, Abdul Mateen
    Gao, Wanlin
    Wang, Minjuan
    IEEE ACCESS, 2019, 7 : 21981 - 21989
  • [40] Fusion of radar and thermopile sensor data for pedestrian detection
    Linzmeier, Dirk
    Baer, Tobias
    Mekhaiel, Moheb
    TM-TECHNISCHES MESSEN, 2007, 74 (03) : 121 - 129