Real-Time Counting People in Crowded Areas by Using Local Empirical Templates and Density Ratios

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, a fast and automated method of counting pedestrians in crowded areas is proposed along with three contributions. We firstly propose Local Empirical Templates (LET), which are able to outline the foregrounds, typically made by single pedestrians in a scene. LET are extracted by clustering foregrounds of single pedestrians with similar features in silhouettes. This process is done automatically for unknown scenes. Secondly, comparing the size of group foreground made by a group of pedestrians to that of appropriate LET captured in the same image patch with the group foreground produces the density ratio. Because of the local scale normalization between sizes, the density ratio appears to have a bound closely related to the number of pedestrians who induce the group foreground. Finally, to extract the bounds of density ratios for groups of different number of pedestrians, we propose a 3D human models based simulation in which camera viewpoints and pedestrians' proximity are easily manipulated. We collect hundreds of typical occluded-people patterns with distinct degrees of human proximity and under a variety of camera viewpoints. Distributions of density ratios with respect to the number of pedestrians are built based on the computed density ratios of these patterns for extracting density ratio bounds. The simulation is performed in the offline learning phase to extract the bounds from the distributions, which are used to count pedestrians in online settings. We reveal that the bounds seem to be invariant to camera viewpoints and humans' proximity. The performance of our proposed method is evaluated with our collected videos and PETS 2009's datasets. For our collected videos with the resolution of 320x240, our method runs in real-time with good accuracy and frame rate of around 30 fps, and consumes a small amount of computing resources. For PETS 2009's datasets, our proposed method achieves competitive results with other methods tested on the same datasets [1], [2].

• 2012-07-01

著者

• Saito Hideo

  Graduate School Of Science And Technology Keio University

• CHUNG Sheng-Luen

  Department of Electrical Engineering, National Taiwan University of Science and Technology

• HSU Gee-Sern

  Department of Mechanical Engineering, National Taiwan University of Science and Technology

• Saito Hideo

  Graduate School of Science and Technology, Keio University

• HUNG Dao-Huu

  Graduate School of Science and Technology, Keio University

関連論文

• RELATION BETWEEN THE DISTRIBUTION OF DAMAGE CAUSED BY THE 1995 HYOGOKEN-NAMBU EARTHQUAKE AND GROUND VIBRATION CHARACTERISTICS INFERRED FROM MICROSEISMS
• D-12-47 3D shape reconstruction of human foot using deformable models and multi viewpoint cameras system
• Plane-sweep algorithm: various tools for computer vision (コンピュータビジョンとイメージメディア)
• Calibration Free Virtual Display System Using Video Projector onto Real Object Surface(Artificial Reality and Telexistence)
• Plane-sweep algorithm: various tools for computer vision (パターン認識・メディア理解)
• Plane-sweep algorithm: various tools for computer vision (画像工学)
• Blind Deconvolution for a Curved Motion Based on Cepstral Analysis
• Real-Time Counting People in Crowded Areas by Using Local Empirical Templates and Density Ratios

スポンサーリンク