No abstract

No abstract

No abstract

At present, stereo video sequences are actively used in the movie industry, in geographical information systems, and in navigation systems, among others. A novel method improves the frames interpolation by forming an invariant set of local motion vectors. First, the motion in a scene is estimated by block-matching algorithm. Second, accurate estimations by using Hu moments (for a noisy video sequence Zernike moments) are calculated. Such approach provides smooth motion that significantly improves the resulting stereo video sequence. Experimental results show the efficiency of frames interpolation based on such approach. The detection of local motion vectors achieves 86 % accuracy.

No abstract

<p><strong>Abstract.</strong> Pedestrian detection and tracking remains a highlight research topic due to its paramount importance in the fields of video surveillance, human-machine interaction, and tracking analysis. At present time, pedestrian detection is still an open problem because of many challenges of image representation in the outdoor and indoor scenes. In recent years, deep learning, in particular Convolutional Neural Networks (CNNs) became the state-of-the-art in terms of accuracy in many computer vision tasks. The unsupervised learning of CNNs is still an open issue. In this paper, we study a matter of feature extraction using a special activation function. Most of CNNs share the same architecture, when each convolutional layer is followed by a nonlinear activation layer. The activation function Rectified Linear Unit (ReLU) is the most widely used as a fast alternative to sigmoid function. We propose a bounded randomized leaky ReLU working in such manner that the angle of linear part with the highest input values is tuned during learning stage, and this linear part can be directed not only upward but also downward using a variable bias for its starting point. The bounded randomized leaky ReLU was tested on Caltech Pedestrian Dataset with promising results.</p>

No abstract

No abstract