Browsing by Author "Chen, Ping-Hung"

Now showing 1 - 2 of 2

Fast Deformable Model for Pedestrian Detection with Haar-like Features
(2017-01-01)
Chou, Kuang-Pen
;
Prasad, Mukesh
;
Puthal, Deepak
;
Chen, Ping-Hung
;
Vishwakarma, Dinesh Kumar
This paper proposes a novel Fast Deformable Model for Pedestrian Detection (FDMPD) to detect the pedestrians efficiently and accurately in the crowded environment. Despite of multiple detection methods available, detection becomes difficult due to variety of human postures and perspectives. The proposed study is divided into two parts. First part trains six Adaboost classifiers with Haar-like feature for different body parts (e.g., head, shoulders, and knees) to build the response feature maps. Second part uses these six response feature maps with full-body model to produce spatial deep features. The combined deep features are used as an input to SVM to judge the existence of pedestrian. As per the experiments conducted on the INRIA person dataset, the proposed FDMPD approach shows greater than 44.75 % improvement compared to other state-of-the-art methods in terms of efficiency and robustness.
New TDR waveguides and data reduction method for monitoring of stream and drainage stage
(2013-11-15)
Chung, Chih-Chung
;
Lin, Chih-Ping
;
Wu, I. -Ling
;
Chen, Ping-Hung
;
Tsay, Ting-Kuei
Less known in the field of hydrological measurements in civil engineering, time domain reflectometry (TDR) has been developed as a new solution to some of the more difficult level measurement problems. This study applied TDR methodology to provide two new designs for a water level sensing waveguide that can be applied in difficult field conditions such as in an underpass, tunnel, culvert, or sewer, etc. Two types of water level sensing waveguides are presented, including a rigid assembled coaxial pipe and a flexible adhered parallel wire. The corresponding data reduction procedure is also proposed to account for uncertainty of travel time analysis and calibrate the velocity of pulse propagation along the waveguides. The satisfactory performance of both the proposed TDR waveguides and data reduction method was experimentally validated. A field case study further demonstrated the feasibility of the TDR technique for water level measurements under typical urban drainage conditions. (C) 2013 Elsevier B.V. All rights reserved.