Earticle

초록

영어

The pedestrian detection is a hot research topic in computer recognition. It involves not only the pedestrian location information but also the intrusion detection function, which has wide prospects in the application of vehicle traffic, campus monitoring, and building guard. However, the identification accuracy and recognition speed play an important role in the pedestrian detection, which calls for a fast pedestrian detection approach. The general pedestrian detection implementation, based on the integral channel features method and soft cascade classifier, is the popular technique in the current business application since its better speed and accuracy. Thus, this method uses the feature approximation technique and multiple classifiers to achieve the feature computing, which speeds up the detection without resizing image. To this end, this paper is motived to propose a multi-scale handling method for the fast pedestrian detection, using the tactics detection from sparse to dense. Our pedestrian detection method consists of four parts functions, mainly pedestrian statistics and intrusion detection, pedestrian tracking and pedestrian flow statistics. All these modules are introduced with its details about design and implementation. In Addition, the proposed multi-scale handling method can be applied into most of object detectors to improve their recognition speed. In conclusion, our proposed approach has a good potential application prospect in the video surveillance system.

목차

Abstract
 1. Introduction
 2. Related Work
 3. The System Requirements of Pedestrian Detection
  3.1. Video Monitoring
  3.2. Pedestrian Statistics and Intrusion Detection
  3.3. Historical Data and Statistical Chart Display
 4. The Design of Pedestrian Detection
  4.1. The Overall Workflow of Pedestrian Detection
  4.2. The Multi-scales Detection from Sparse to Dense
  4.3. The Pedestrian Tracking based Statistics
  4.4. The Camera Control and Video Replay
  4.5. The Chart Display
 5. Summary and Future Works.
 Acknowledgment
 References

키워드

저자

• Shuoping Wang [ Zhejiang University City College, Hangzhou, P.R. China, 310015 ]
• Zhike Han [ Zhejiang University City College, Hangzhou, P.R. China, 310015 ]
• Li Zhu [ College of Computer Science and Engineering, Zhejiang University, Hangzhou, P.R. China, 310027 ]
• Qi Chen [ College of Computer Science and Engineering, Zhejiang University, Hangzhou, P.R. China, 310027 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Security and Its Applications

• 간기

  격월간

• pISSN

  1738-9976

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605