Performance Analysis and Augmentation of K-means Clustering, based approach for Human Detection in Videos

  Mr. Pruthviraj Parmar,  Mrs. Gayatri Sunilkumar Pandi(Jain)

“Performance Analysis and Augmentation of K-means Clustering, based approach for Human Detection in Videos” takes us to video level processing techniques to identify human from video. Surveillance System have become increasingly popular in the globalization process. Intelligent Video Surveillance system based on image recognition is widely used to effectively help to provide security, safety and prevents many crimes. Due to the high Complexity in techniques such as real-time processing and image contents analysis/understanding. However detecting humans in images and videos still challenging task owing to their variable appearance caused by variety of clothes shadows, articulation and illumination situations, and unpredictable poses that they can adopt. In this thesis there is a brief survey of different object detection techniques, as well as human detection techniques like fuzzy logic, single Gaussian model, mixture of Gaussian model, Background Subtraction Technique, human body Pose Recognition ,appearance based ,motion-based and hybrid methods. Hear Adaptive Background subtraction method and K-means clustering used for detection of the human .It works efficient for the indoor environment. There is near about 67-70% human detection from the video frame for the indoor. For the outdoor there are so many parameters which effect the human detection, so it is not efficient

Keywords- Human Detection, Background Subtraction, Human Detection technique-means clustering, skin detection

Unique Identification Number - IJEDR1502177
Page Number(s) - 1029-1035
Pubished in - Volume 3 | Issue 2 | May 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Mr. Pruthviraj Parmar,  Mrs. Gayatri Sunilkumar Pandi(Jain),   "Performance Analysis and Augmentation of K-means Clustering, based approach for Human Detection in Videos", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.1029-1035, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502177.pdf