作者：
Rahma KalboussiAymen AzazaMehrez AbdellaouiAli DouikENISO
Ecole Nationale d'Ingénieurs de Sousse NOCCS Networked Objects Control and Communication Systems Laboratory Soussel Tunisiay ENIM
Ecole Nationale d'Ingénieurs de Monastir NOCCS Laboratory Monastir Tunisia ENISO
NOCCS Laboratory Sousse Tunisia
In the last decades, saliency detection was extensively studied. The number of computational models that help to detect salient regions in still images is increasing, whereas, detecting salient regions in videos is in...
详细信息
In the last decades, saliency detection was extensively studied. The number of computational models that help to detect salient regions in still images is increasing, whereas, detecting salient regions in videos is in its early stages. In this paper we propose a video saliency detection method using local motion estimation. Starting from a patch, the problem of saliency detection is modeled as a growing region starting from a region which contains the higher motion information to the background. Local saliency is measured by combining local motion estimation and local surrounding contrast which leads to the construction of foreground and background patches. Experiments have proved that The proposed method outperforms state-of-the-art methods over two benchmark datasets.
In a cognitive radio (CR) scenario, we study the joint problem of spectrum sensing and jamming detection. Modelling the scenario as a multiple hypothesis testing problem, we analyse the probability of detection of the...
详细信息
In a cognitive radio (CR) scenario, we study the joint problem of spectrum sensing and jamming detection. Modelling the scenario as a multiple hypothesis testing problem, we analyse the probability of detection of the optimal detector in the sense of Neyman-Pearson theorem. We derive one exact form in terms of a series and a closed-form version. Moreover, we evaluate the asymptotic probability of detection, as it results in a simpler form to handle. In all of the above analysis, we consider the spatially correlated observation data. We further consider two practical scenarios where first we have no knowledge of the jammer's signal, and second where we have no knowledge of the noise power. We apply generalized likelihood ratio test in both of the cases. Simulation results confirm the accuracy of our asymptotic performance derivations.
暂无评论