Detecting pedestrians in images plays a very important role 6 in many computer vision applications such as video surveillance, smart 7 cars and robotics. Feature extraction is the key for this task. Promis8 ing features should be discriminative, robust and easy to compute. This 9 paper presents a novel and efficient feature, termed pyramid center10 symmetric local binary\ternary patterns (pyram...

This paper presents a new image fusion algorithm by combining contourlet transform with Kernel Principle Component Analysis to enhance perception in case of night vision applications. Contourlet Transform improves visual perception preserving the edge and texture information as compared to wavelet transform, while Kernel Principle Component Analysis helps to develop effective fusion decision ru...

We propose a new type of wave-front sensor (WFS) derived from the pyramid WFS (PWFS). This new WFS, called the flattened pyramid-WFS (FPWFS), has a reduced pyramid angle in order to optically overlap the four pupil images into an unique intensity. This map is then used to derive the phase information. In this Letter, this new WFS is compared to three existing WFSs, namely the PWFS, the modulate...

The area-based methods, such as that using the Laplacian pyramid and Fourier transform-based phase matching, benefit by highlighting high spatial frequencies to reduce sensitivity to the feature inconsistency problem in the multisensor image registration. The feature extraction and matching methods are more powerful and versatile to process poor quality IR images. We implement multi-scale hiera...

We explored preschool’s children’s understanding of the correspondence of 3-D objects and 2-D faces in a novel task. In the “footprints” task children were shown a geometric solid, such as a pyramid or a prism, and asked to select which shape the solid would make if it were dipped in ink and stamped on a piece of paper. Through a latent class analysis of children’s errors we found children diff...

Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid...