Chandra Mani Sharma

Adaptive real-time motion segmentation technique based on statistical background model

Abstract Motion segmentation is a crucial step for video analysis and has many applications. This paper proposes a method for motion segmentation, which is based on construction of statistical background model. Variance and Covariance of pixels are computed to construct the model for scene background. We perform average frame differencing with this model to extract the objects of interest from the video frames. Morphological operations are used to smooth the object segmentation results. The proposed technique is adaptive to the dynamically changing background because of change in the lighting conditions and in scene background. The method has the capability to relearn the background to adapt these variations. The immediate advantage of the proposed method is its high processing speed of 30 frames per second on large sized (high resolution) videos. We compared the proposed method with other five popular methods of object segmentation in order to prove the effectiveness of the proposed technique. Experimental results demonstrate the novelty of the proposed method in terms of various performance parameters. The method can segment the video stream in real-time, when background changes, lighting conditions vary, and even in the presence of clutter and occlusion

Automatic multiple human detection and tracking for visual surveillance system

Object Tracking is an important task in video processing because of its variety of applications in visual surveillance, human activity monitoring and recognition, traffic flow management etc. Multiple object detection and tracking in outdoor environment is a challenging task because of the problems raised by poor lighting conditions, variation in poses of human object, shape, size, clothing, etc. This paper proposes a novel technique for detection and tracking of multiple human objects in a video. A classifier is trained for object detection using Haar-like features from training image set. Human objects are detected with help of this trained detector and are tracked using particle filter. The experimental results show that the proposed technique can detect and track multiple humans in a video adequately fast in the presence of poor lighting conditions, variation in poses of human objects, shape, size, clothing etc. and the technique can handle varying number of human objects in a video at various points of time.

Automatic human activity recognition in video using background modeling and spatio-temporal template matching based technique

Human activity recognition is a challenging area of research because of its various potential applications in visual surveillance. A spatio-temporal template matching based approach for activity recognition is proposed in this paper. We model the background in a scene using a simple statistical model and extract the foreground objects in a scene. Spatio-temporal templates are constructed using the motion history images (MHI) and object shape information for different human activities in a video like walking, standing, bending, sleeping and jumping. Experimental results show that the method can recognize these multiple activities for multiple objects with accuracy and speed.

Review of Search based Techniques in Software Testing

The most effort seeking job in software testing is the generation of test cases. The success of testing pursuit highly depends on the effectiveness of the test cases. Various approaches have been proposed to ease the task of test case generation and to perform software testing. It has witnessed a paradigm shift from manual test case generation to automated test case generation in the recent time. Search Based Software Testing (SBST) has evolved as a new domain in software testing. This paper reviews the various Search Based Software Testing approaches, foresees trends in the research being conducted in this area and explores the new possibilities which future of the software testing envisages. This paper presents an exhaustive survey on Search Based Software Testing and also touches upon the other disciplines of modern day computing which seamlessly overlap with SBST.

On human activity recognition in video sequences

In this paper, we describe a novel template matching based approach for recognition of different human activities in a video sequence. We model the background in the scene using a simple statistical model and extract the foreground objects present in a scene. The matching templates are constructed using the motion history images (MHI) and spatial silhouettes for recognizing activities like walking, standing, bending, sleeping and jogging in a video sequence. Experimental results demonstrate that the proposed method can recognize these activities accurately for standard KTH database as well as for our own database.

Machine Learning based approach for Human Trait Identification from Blog Data

form a major part of a persons personality. Emotional intelligence (EI) is the ability to identify, assess, and control the emotions of oneself, of others, and of groups. The written expressions reflect authors personality. Various personality traits can be determined by the analysis of the contents written by a person. This paper proposes a novel technique for human trait identification from the analysis of authors written expressions. The proposed technique is based on the concept of supervised machine learning and uses Support Vector Machine for classifying the personality of a writer. We classify the personality of a writer into five categories namely, highly extrovert, highly introvert, low introvert, low extrovert and ambivert. Experiments have been carried out on the real world blog data and results demonstrate that the proposed technique can determine the personality traits of a writer with accuracy and speed. We have also implemented a PHP based online system, which reads the contents of a blog and can automatically predict the personality of writer of the blog

A Context-aware Approach for Detecting Skin Colored Pixels in Images

Detecting the human skin and its analysis has number of important applications. This is a challenging task as. in images, the skin color is quite sensitive to the chrominance and intensity of the pixels. So the techniques with a single model for skin fail to cope up with the variation in skin colors because of ethnicity, age, lighting etc. This paper proposes a novel technique for skin detection in color images. The proposed technique has two steps; (i) first the faces of humans are detected in the color images (ii) then based on the statistics captured from the sampling of the face area, the rest of the skin is detected. For face detection purpose, we train a binary classifier using machine learning approach. After face detection, the sampled pixels are matched to find the other exposed skin areas using an approach based on Gaussian model for skin.