We propose a new method for fusing a LIDAR point cloud and camera-captured images in the deep convolutional neural network (CNN). The proposed method constructs a new layer called non-homogeneous pooling layer to transform features between bird view map and front view map. The sparse LIDAR point cloud is used to construct the mapping between the two maps. The pooling layer allows efficient fusi...

For the sake of providing 3D contents for up-coming 3D display devices, a real-time automatic depth fusion 2D-to-3D conversion system is needed on the home multimedia platform. We proposed a priority depth fusion algorithm with a 2D-to-3D conversion system which generates the depth map from most of the commercial video sequences. The results from different kinds of depth reconstruction methods ...

—Saliency computation has become a popular research field for many applications due to the useful information provided by saliency maps. For a saliency map, local relations around the salient regions in multi-channel perspective should be taken into consideration by aiming uniformity on the region of interest as an internal approach. And, irrelevant salient regions have to be avoided as much as...

In the recent years a number of novel, automatic map-inference techniques have been proposed, which derive road-network from a cohort of GPS traces collected by a fleet of vehicles. In spite of considerable attention, these maps are imperfect in many ways: they create an abundance of spurious connections, have poor coverage, and are visually confusing. Hence, commercial and crowd-sourced mappin...

We present a novel algorithm for image-based surface reconstruction from a set of calibrated images. The problem is formulated in Bayesian framework, where estimates of depth and visibility in a set of selected cameras are iteratively improved. The core of the algorithm is the minimisation of overall geometric L2 error between measured 3D points and the depth estimates. In the visibility estima...

0167-8655/$ see front matter 2012 Elsevier B.V. A http://dx.doi.org/10.1016/j.patrec.2012.06.003 ⇑ Corresponding author. E-mail addresses: [email protected] (F. Qi), gmshi@x 1 Principal corresponding author. Depth acquisition becomes inexpensive after the revolutionary invention of Kinect. For computer vision applications, depth maps captured by Kinect require additional processing to fill up mi...

The paper deals with special types of $L$-ordered sets, $L$-fuzzy complete lattices, and fuzzy directed complete posets.First, a theorem for constructing monotone maps is proved, a characterization for monotone maps on an $L$-fuzzy complete lattice is obtained, and it's proved that if $f$ is a monotone map on an $L$-fuzzy complete lattice $(P;e)$, then the least fixpoint of $f$ is meet of a spe...

A novel method to compute the clarity map from single image based on the local maxima and minima information inside image is proposed in this paper. The well-focused region can be easily identified according to the significant pixels inside the clarity map of image. Our method utilizes the clarity map difference between two source images as the focus criteria to implement multi-focus image fusi...

In the recent years a number of novel, automatic map-inference techniques have been proposed, which derive road-network from a cohort of GPS traces collected by a fleet of vehicles. In spite of considerable attention, these maps are imperfect in many ways: they create an abundance of spurious connections, have poor coverage, and are visually confusing. Hence, commercial and crowd-sourced mappin...