People Detection in Complex Scenes By Using An Improved and Robust HOG Descriptor
Journal Title: Advances in Image and Video Processing - Year 2017, Vol 5, Issue 3
Abstract
The detection of moving people in a complex scene filmed with a single camera is among the most difficult fields of research in vision by computer. In this work, we suggest improving the quality of detection methods based on the histogram of oriented gradients (HOG) descriptor. For that, we purpose to use a combination of type detector/descriptor to minimize the rate of the false detection produced by the descriptor HOG. The implementation of this combination as well as its evaluation on public bases show clearly that the technique which we propose produces many good results at the level of the detection of the people in movement compared with the descriptor HOG
Authors and Affiliations
Hdioud Boutaina, Oulad Haj Thami Rachid, El Haj Tirari Mohammed
Approach to Detecting Forest Fire by Image Processing Captured from IP Cameras
In this paper, the results show an algorithm to detect the presence of smoke and flame using image sequences captured by Internet Protocol (IP) cameras is represented. The important characteristics of smoke such as color...
Automatic Non-native Dialect and Accent Voice Detection of South Indian English
Speech recognition has achieved enormous improvements presently. However, robustness is still one of the big tribulations, e.g. performance of recognition fluctuates penetratingly depending on the speaker, particularly a...
A Mass Mediated Interpretation of The Chinese “Belt & Road Initiative” As Strategic Intelligence Perspective
This paper contrasts the current Chinese “Belt and Road Initiative” (BRI) against the opening of the U.S. west in the 19th century using principles of western rhetoric as basis for interpretation. Most specifically, Ke...
Enrichment of a Kinect-based Physiotherapy and Assessment Platform for Parkinson’s Disease Patients
Our Kinect-based physiotherapy platform tailored to Parkinson’s disease (PD) patients employs a Kinect sensor to extract 3D skeletal data in real-time from an exercising patient. The initial collection of five exercises...
Three Dimensional Image Processing in Hexagonal Prism Lattice of Z3 Grid
A 2D hexagonal image is an array of what are called pixels which are the coordinates of the hexagonal lattice points decided by the linear horizontal rows and the nonlinear vertical zig-zags. A 2D hexagonal image could a...