Paper Info
Title
Benchmark data and method for real-time people counting in cluttered scenes using depth sensors.
Abstract
Real-time automatic counting of people has widespread applications in security, safety and logistics.However, there is currently no large-scale public dataset for benchmarking approaches on this problem. To fill this gap, we introduce the first real-world RGB-D People Counting DataSet (PCDS) containing over 4,500 videos recorded at the entrance doors of buses in normal and cluttered conditions. We also propose an efficient method for counting people in real-world cluttered scenes using depth videos alone. The proposed method computes a point cloud from the depth video frame and re-projects it onto the ground plane to normalize the depth information. The resulting depth image is analyzed for identifying potential human heads. The human head proposals are meticulously refined using a 3D human model. The proposals in each frame of the continuous video stream are tracked to trace their trajectories. The trajectories are again refined to ascertain reliable counting. People are eventually counted by accumulating the head trajectories leaving the scene. To enable effective head and trajectory identification, we also propose two different compound features. Thorough evaluation on the PCDS demonstrates that our overall technique is able to count people in cluttered scenes with high accuracy at 45 fps on a 1.7 GHz processor.
Year
DOI
Venue
2018
10.1109/tits.2019.2911128
IEEE Transactions on Intelligent Transportation Systems
Field
DocType
Volume
Normalization (statistics),Pattern recognition,Computer science,Ground plane,Artificial intelligence,RGB color model,Point cloud,Trajectory,Benchmarking,Human head,Doors
Journal
abs/1804.04339
Citations 
PageRank 
References 
1
0.35
5
Authors
6
Name
Order
Citations
PageRank
Huansheng Song141.40
ShiJie Sun210.35
Naveed Akhtar3233.98
ChaoYang Zhang410.35
Jianxin Li544348.67
A. Mian6167984.89