Abstract

GARCES MATILLA, Aldo et al. Multiple people tracking in video surveillance applications with low-resolution cameras. Rev cuba cienc informat [online]. 2017, vol.11, n.2, pp.149-161. ISSN 2227-1899.

ABSTRACT People detection and tracking is of vital interest for its many applications, such as video surveillance, driver assisted systems, evaluation tools in the medicine, human-computer interaction. In this work is presented an application to carry out tasks of video surveillance with low resolution cameras. This application is based on video sequences captured from a distributed multi-camera vision system, allowing the people detection and tracking. The methods and techniques used in each stage are well known, these were built creatively in the different stages of processing, and these were improved for greater computational efficiency of the system. Within these receive special attention the background subtraction with Gaussian Mixture Model to objects detection and the Kalman filter to tracking, also the descriptors Histograms of Oriented Gradients and Support Vector Machine in people detection. To demonstrate the validity of the methods implemented is realized a variety of experiments with low-resolution cameras, getting satisfactory results. In the tracking stage of multiple persons only occurred error in 11% of detected people, mainly motivated by the occurrence of occlusions.

Keywords : object detection; tracking; people detection and video surveillance systems.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )