An optimal video-surveillance approach for HDR videos tone mapping

Recently, a new type of camera, which allows the recording of almost the entire range of luminosity of the acquired scene, has been introduced to the market. The produced High Dynamic Range images (HDRi), can simplify some video-surveillance tasks, such as object detection, recognition and tracking, since they can simultaneously capture the visual scene content of both dark and bright areas. Applications where lighting conditions cannot be controlled can greatly benefit from the adoption of HDR cameras. For example, the achievement of a good and constant visual quality of images is one of the key aspects in video-surveillance applications, because it allows to robustly detect salient events in the captured scenes. However, the use of HDR images in traditional video-surveillance systems requires the reduction of their dynamic range appropriately, by applying a tone mapping operator. In this paper a fast method for tone mapping HDR videos, which combines the benefits of both local and global operators, is presented. It is applied in the context of object detection and tracking. It also enhances the visual quality of the image in all light conditions, which facilitated surveillance tasks for both human and automatic operators.