Open AccessResearch on pedestrian detection system based on intelligent terminal with limited computing ability
Author(s) -
Ning Chen,
Li Menglu,
Zhijian Liu
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1419/1/012022
Subject(s) - pedestrian detection , computer science , pedestrian , terminal (telecommunication) , intelligent transportation system , support vector machine , real time computing , artificial intelligence , embedded system , engineering , computer network , transport engineering , civil engineering
Pedestrian detection technology is the use of computer vision technology to determine whether there are pedestrians in static images or video images, and accurately mark pedestrians. Intelligent vehicles, intelligent monitoring, human behaviour analysis and other aspects are related to pedestrian detection technology, so pedestrian detection technology has been widely concerned by all walks of life. However, in some application environments, the network setting is flexible and the location of the device can be changed at any time, so it is difficult to establish a pedestrian detection system by wired way, and the pedestrian detection system can only be established through WSN. It is necessary to consider how to complete pedestrian detection through intelligent terminal under the condition of limited computing power. Many researchers have put forward a lot of algorithms, which are constantly optimized, but there are still many problems to be solved in practical application. In this paper, aiming at the intelligent terminal in WSN environment with limited computing power, a pedestrian detection system based on HOG+SVM is designed, which can detect moving pedestrians in video in real time. The detection system is mainly composed of detection algorithm and video acquisition module. After the test of INRIA and CVC data set, the accuracy of the detection algorithm in this paper is 89.06%. This method is tested under the intelligent terminal with limited computing power, with a good detection effect.