Entity

Time filter

Source Type


Wei Y.,Beijing Urban Engineering Design and Research Institute | Tian Q.,North China University of Technology | Guo T.,North China University of Technology
Advances in Mechanical Engineering | Year: 2013

Considering the importance of pedestrian detection in a variety of applications such as advanced robots and intelligent surveillance systems, this paper presents an improved pedestrian detection method through integrating Haar-like features, AdaBoost algorithm, histogram of oriented gradients (HOG) descriptor, and support vector machine (SVM) classifiers, in which the head and shoulder information is utilized especially. Due to the fast training speed of Haar-like features and the high detection efficiency of HOG features, the proposed method can classify pedestrians precisely with higher speed. Experimental results validated the efficiency and effectiveness of the proposed algorithm. © 2013 Yun Wei et al. Source


Tian Q.,North China University of Technology | Zhou B.,North China University of Technology | Zhao W.-H.,North China University of Technology | Wei Y.,Nanjing Southeast University | And 2 more authors.
Journal of Software | Year: 2013

Conventional moving objects detection and tracking using visible light image was often affected by the change of moving objects, change of illumination conditions, interference of complex backgrounds, shaking of camera, shadow of moving objects and moving objects of self-occlusion or mutual-occlusion phenomenon. We propose a human detection method using HOG features of head and shoulder based on depth map and detecting moving objects in particular scene in this paper. In-depth study on Kinect to get depth map with foreground objects. Through the comprehensive analysis based on distance information of the moving objects segmentation extraction removal diagram of background information, by analyzing and comprehensively applying segmentation a method based on distance information to extract pedestrian's Histograms of Oriented Gradients (HOG) features of head and shoulder[1], then make a comparison to the SVM classifier. SVM classifier isolate regions of interest (features of head and shoulder) and judge to achieve real-time detection of objects (pedestrian). The human detection method by using features of head and shoulder based on depth map is a good solution to the problem of low efficiency and identification in traditional human detection system. The detection accuracy of our algorithm is approximate at 97.4% and the average time processing per frame is about 51.76 ms. © 2013 ACADEMY PUBLISHER. Source


Tian Q.,North China University of Technology | Zhao W.H.,North China University of Technology | Zhang L.,North China University of Technology | Wei Y.,Beijing Urban Engineering Design and Research Institute | Wei Y.,Nanjing Southeast University
Applied Mechanics and Materials | Year: 2013

Vehicle and pedestrian detection plays a critical role in the intelligent transportation system. The paper proposes an algorithm which can solve the problem effectively by Histograms of Oriented Gradients (HOG) features extraction and Support Vector Machine (SVM). This detection system is based on Histograms of Oriented Gradients features combined with Support Vector Machine for the recognition stage which is insensitive to lightings and noises. We use Kalman filter to track the objects. As shown in experiments, the method has high detection rate and can also satisfy the real-time intelligent transportation system. © (2013) Trans Tech Publications, Switzerland. Source


Tian Q.,North China University of Technology | Zhang L.,North China University of Technology | Wei Y.,Nanjing Southeast University | Wei Y.,Beijing Urban Engineering Design and Research Institute | And 2 more authors.
International Journal of Online Engineering | Year: 2013

This Many detection and tracking methods are able to detect and track vehicle motion reliably in the daytime. However, vehicle detection and tracking in video surveillance at night remain very important problems that the vehicle signatures have low contrast against the background. Traditional methods based on the analysis of the difference between successive frames and a background frame can not work. This paper presents a method for vehicle detection and tracking at night in video surveillance. The method uses Histograms of Oriented Gradients (HOG) features to extract features, and then uses Support Vector Machine (SVM) to recognize the object. In tracking phase, we use Kalman filter to track the object. As shown in experiments, the algorithm can exactly detect and track moving vehicles in video surveillance at night. Source


Tian Q.,North China University of Technology | Zhang L.,North China University of Technology | Wei Y.,Beijing Urban Engineering Design and Research Institute | Fei W.-W.,China Aerospace Science and Technology Corporation | Zhao W.-H.,Beijing Urban Engineering Design and Research Institute
Advances in Mechanical Engineering | Year: 2013

An efficient and rapid method for car detection in video is presented in this paper. In this method, rear side view of cars is used in the detection phase. And in combination with histograms of oriented gradients (HOG) which is one of the most discriminative features, a linear support vector machine (SVM) is used for object classification. Besides, in order to avoid car missing, Kalman filter is used to track the objects. It is known that the calculation of HOG is complex and costs the most run time. So the processing time in this method is decreased by using information of objects' areas from the previous frames. It is shown by the experimental results that the detection rate can reach 96.20% and is more accurate when choosing the fit interval number such as 5. It is also illustrated that this method can decrease the calculating time on a large degree when the accuracy is about 94.90% by comparing with traditional method of HOG combining with SVM. © 2013 Qing Tian et al. Source

Discover hidden collaborations