Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

被引:0
|
作者
Liu, Weizhe [1 ]
Lis, Krzysztof [1 ]
Salzmann, Mathieu [1 ]
Fua, Pascal [1 ]
机构
[1] Ecole Polytech Fed Lausanne EPFL, Comp Vis Lab, Sch Commun & Comp Sci, Lausanne, Switzerland
关键词
D O I
10.1109/iros40897.2019.8967852
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image-plane density has no immediate physical meaning because it is subject to perspective distortion. This is a concern in sequences acquired by drones because the viewpoint changes often. This distortion is usually handled implicitly by either learning scale-invariant features or estimating density in patches of different sizes, neither of which accounts for the fact that scale changes must be consistent over the whole scene. In this paper, we explicitly model the scale changes and reason in terms of people per square-meter. We show that feeding the perspective model to the network allows us to enforce global scale consistency and that this model can be obtained on the fly from the drone sensors. In addition, it also enables us to enforce physically-inspired temporal consistency constraints that do not have to be learned. This yields an algorithm that outperforms state-of-the-art methods in inferring crowd density from a moving drone camera especially when perspective effects are strong.
引用
收藏
页码:244 / 249
页数:6
相关论文
共 50 条
  • [41] Texture-Based Feature Mining for Crowd Density Estimation: A Study
    Saqib, Muhammad
    Khan, Sultan Daud
    Blumenstein, Michael
    PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ), 2016, : 18 - 23
  • [42] A survey of crowd counting and density estimation based on convolutional neural network
    Fan, Zizhu
    Zhang, Hong
    Zhang, Zheng
    Lu, Guangming
    Zhang, Yudong
    Wang, Yaowei
    NEUROCOMPUTING, 2022, 472 : 224 - 251
  • [43] A density-based spatial clustering for physical constraints
    Xin Wang
    Camilo Rostoker
    Howard J. Hamilton
    Journal of Intelligent Information Systems, 2012, 38 : 269 - 297
  • [44] A density-based spatial clustering for physical constraints
    Wang, Xin
    Rostoker, Camilo
    Hamilton, Howard J.
    JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2012, 38 (01) : 269 - 297
  • [45] An assessment of conventional and drone-based measurements for tree attributes in timber volume estimation: A case study on stone pine plantation
    Gulci, Sercan
    Akay, Abdullah E.
    Gulci, Nese
    Tas, Inanc
    ECOLOGICAL INFORMATICS, 2021, 63
  • [46] Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints
    Jau, You-Yi
    Zffu, Rui
    Su, Hao
    Chandraker, Manmohan
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 4950 - 4957
  • [47] Estimation of the Grasping Pose of Unknown Objects Based on Multiple Geometric Constraints
    Su J.
    Zhang Y.
    Fang L.
    Li Q.
    Wang S.
    Jiqiren/Robot, 2020, 42 (02): : 129 - 138
  • [48] Crowd density estimation based on statistical analysis of local intra-crowd motions for public area surveillance
    Zhang, Zhaoxiang
    Li, Min
    OPTICAL ENGINEERING, 2012, 51 (04)
  • [49] LTE-based Passive Device-Free Crowd Density Estimation
    Di Domenico, Simone
    De Sanctis, Mauro
    Cianca, Ernestina
    Colucci, Paolo
    Bianchi, Giuseppe
    2017 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2017,
  • [50] Estimation of crowd density in surveillance scenes based on deep convolutional neural network
    Pu, Shiliang
    Song, Tao
    Zhang, Yuan
    Xie, Di
    8TH INTERNATIONAL CONFERENCE ON ADVANCES IN INFORMATION TECHNOLOGY, 2017, 111 : 154 - 159