The majority of the senior population lives alone at home. Falls can cause serious injuries, such as fractures or head injuries. These injuries can be an obstacle for a person to move around and normally practice his daily activities. Some of these injuries can lead to a risk of death if not handled urgently. In this paper, we propose a fall detection system for elderly people based on their postures. The postures are recognized from the human silhouette which is an advantage to preserve the privacy of the elderly. The effectiveness of our approach is demonstrated on two well-known datasets for human posture classification and three public datasets for fall detection, using a Support-Vector Machine (SVM) classifier. The experimental results show that our method can not only achieves a high fall detection rate but also a low false detection.

This paper presents a vision-based system for recognizing when elderly adults fall. A fall is characterized by shape deformation and high motion. We represent shape variation using three features, the aspect ratio of the bounding box, the orientation of an ellipse representing the body, and the aspect ratio of the projection histogram. For motion variation, we extract several features from three blocks corresponding to the head, center of the body, and feet using optical flow. For each block, we compute the speed and the direction of motion. Each activity is represented by a feature vector constructed from variations in shape and motion features for a set of frames. A support vector machine is used to classify fall and non-fall activities. Experiments on three different datasets show the effectiveness of our proposed method.

The problem of image denoising is largely discussed in the literature. It is a fundamental preprocessing task, and an important step in almost all image processing applications. Omnidirectional images offer a large field of view compared to conventional perspectives images, however, they contain important distortions and classical treatments are thus not appropriate for those deformed omnidirectional images. In this study we introduce an adaptation of an adaptation to Stein block thresholding method to omnidirectional images. We will adapt different treatments in order to take into account the nature of omnidirectional images.

The fall detection system composed in general from three models, the first is a detection moving object, the second is tracking moving object and the third is recognition person's behavior. In this paper, we will deal out the first module which is the main unit in the fall detection system, because it is where we detect the person in the image. There are a lot of approaches in this way, but their results are not perfect due to the change of the background model. Many works propose to improve those results, but these approaches are not satisfied in some states. In this way, we propose a novel approach by using the optical flow which can improve The result to extract the foreground human body without errors.

In this paper, we propose a human posture recognition based on the human shape. We represent human shape by using the projection histogram based on the bounding box, where we divide it horizontally and vertically in several lines oriented by several angles, and the intersection between them provides local features as a shape descriptor. By using the Support-Vector Machine (SVM) classifier, we map each histogram to one type of postures including lying, standing, bending and siting posture. We compare our method with two shape descriptors such as Shape Context(SC) and Ellipse-based projection histogram. To show the performance of our method, we based on two datasets and the results present that our method achieves a high accuracy in human posture recognition.