The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kertas kerja ini mencadangkan kaedah pemetaan haba orang yang terlibat dalam aktiviti kumpulan. Perkumpulan orang sebegini berguna untuk memahami aktiviti kumpulan. Dalam kerja terdahulu, pengelompokan orang dilakukan berdasarkan peraturan dan skema mudah yang tidak fleksibel (cth, berdasarkan kedekatan antara orang dan dengan model yang mewakili hanya bilangan orang yang tetap). Selain itu, beberapa kaedah pengelompokan sebelumnya memerlukan hasil pengecaman tindakan untuk individu individu, yang mungkin termasuk hasil yang salah. Sebaliknya, kaedah pemetaan haba kami yang dicadangkan boleh mengumpulkan sebarang bilangan orang yang mengubah penggunaan mereka secara dinamik. Kaedah kami boleh berfungsi secara bebas daripada pengecaman tindakan individu. Rangkaian dalam untuk kaedah yang dicadangkan kami terdiri daripada dua aliran input (iaitu, imej RGB dan kotak sempadan manusia). Rangkaian ini mengeluarkan peta haba yang mewakili nilai keyakinan mengikut piksel bagi kumpulan orang. Penerokaan meluas parameter yang sesuai telah dijalankan untuk mengoptimumkan imej kotak sempadan input. Hasilnya, kami menunjukkan keberkesanan kaedah yang dicadangkan untuk pemetaan haba orang yang terlibat dalam aktiviti kumpulan.
Kohei SENDO
Toyota Technological Institute
Norimichi UKITA
Toyota Technological Institute
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Kohei SENDO, Norimichi UKITA, "Heatmapping of Group People Involved in the Group Activity" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1209-1216, June 2020, doi: 10.1587/transinf.2019MVP0008.
Abstract: This paper proposes a method for heatmapping people who are involved in a group activity. Such people grouping is useful for understanding group activities. In prior work, people grouping is performed based on simple inflexible rules and schemes (e.g., based on proximity among people and with models representing only a constant number of people). In addition, several previous grouping methods require the results of action recognition for individual people, which may include erroneous results. On the other hand, our proposed heatmapping method can group any number of people who dynamically change their deployment. Our method can work independently of individual action recognition. A deep network for our proposed method consists of two input streams (i.e., RGB and human bounding-box images). This network outputs a heatmap representing pixelwise confidence values of the people grouping. Extensive exploration of appropriate parameters was conducted in order to optimize the input bounding-box images. As a result, we demonstrate the effectiveness of the proposed method for heatmapping people involved in group activities.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MVP0008/_p
Salinan
@ARTICLE{e103-d_6_1209,
author={Kohei SENDO, Norimichi UKITA, },
journal={IEICE TRANSACTIONS on Information},
title={Heatmapping of Group People Involved in the Group Activity},
year={2020},
volume={E103-D},
number={6},
pages={1209-1216},
abstract={This paper proposes a method for heatmapping people who are involved in a group activity. Such people grouping is useful for understanding group activities. In prior work, people grouping is performed based on simple inflexible rules and schemes (e.g., based on proximity among people and with models representing only a constant number of people). In addition, several previous grouping methods require the results of action recognition for individual people, which may include erroneous results. On the other hand, our proposed heatmapping method can group any number of people who dynamically change their deployment. Our method can work independently of individual action recognition. A deep network for our proposed method consists of two input streams (i.e., RGB and human bounding-box images). This network outputs a heatmap representing pixelwise confidence values of the people grouping. Extensive exploration of appropriate parameters was conducted in order to optimize the input bounding-box images. As a result, we demonstrate the effectiveness of the proposed method for heatmapping people involved in group activities.},
keywords={},
doi={10.1587/transinf.2019MVP0008},
ISSN={1745-1361},
month={June},}
Salinan
TY - JOUR
TI - Heatmapping of Group People Involved in the Group Activity
T2 - IEICE TRANSACTIONS on Information
SP - 1209
EP - 1216
AU - Kohei SENDO
AU - Norimichi UKITA
PY - 2020
DO - 10.1587/transinf.2019MVP0008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - This paper proposes a method for heatmapping people who are involved in a group activity. Such people grouping is useful for understanding group activities. In prior work, people grouping is performed based on simple inflexible rules and schemes (e.g., based on proximity among people and with models representing only a constant number of people). In addition, several previous grouping methods require the results of action recognition for individual people, which may include erroneous results. On the other hand, our proposed heatmapping method can group any number of people who dynamically change their deployment. Our method can work independently of individual action recognition. A deep network for our proposed method consists of two input streams (i.e., RGB and human bounding-box images). This network outputs a heatmap representing pixelwise confidence values of the people grouping. Extensive exploration of appropriate parameters was conducted in order to optimize the input bounding-box images. As a result, we demonstrate the effectiveness of the proposed method for heatmapping people involved in group activities.
ER -