Robust Statistical Approach for Extraction of Moving Human Silhouettes from Videos

Human pose estimation is one of the key problems in computer vision that has been studied in the recent years. The significance of human pose estimation is in the higher level tasks of understanding human actions applications such as recognition of anomalous actions present in videos and many other related applications. The human poses can be estimated by extracting silhouettes of humans as silhouettes are robust to variations and it gives the shape information of the human body. Some common challenges include illumination changes, variation in environments, and variation in human appearances. Thus there is a need for a robust method for human pose estimation. This paper presents a study and analysis of approaches existing for silhouette extraction and proposes a robust technique for extracting human silhouettes in video sequences. Gaussian Mixture Model (GMM) A statistical approach is combined with HSV (Hue, Saturation and Value) color space model for a robust background model that is used for background subtraction to produce foreground blobs, called human silhouettes. Morphological operations are then performed on foreground blobs from background subtraction. The silhouettes obtained from this work can be used in further tasks associated with human action interpretation and activity processes like human action classification, human pose estimation and action recognition or action interpretation.

Speedy Object Detection based on Shape

This study is a part of design of an audio system for in-house object detection system for visually impaired, low vision personnel by birth or by an accident or due to old age. The input of the system will be scene and output as audio. Alert facility is provided based on severity levels of the objects (snake, broke glass etc) and also during difficulties. The study proposed techniques to provide speedy detection of objects based on shapes and its scale. Features are extraction to have minimum spaces using dynamic scaling. From a scene, clusters of objects are formed based on the scale and shape. Searching is performed among the clusters initially based on the shape, scale, mean cluster value and index of object(s). The minimum operation to detect the possible shape of the object is performed. In case the object does not have a likely matching shape, scale etc, then the several operations required for an object detection will not perform; instead, it will declared as a new object. In such way, this study finds a speedy way of detecting objects.