The 3-D LiDAR scanner and the 2-D chargecoupled device (CCD) camera are two typical types of sensors for surrounding-environment perceiving in robotics or autonomous driving. Commonly, they are jointly used to improve perception accuracy by simultaneously recording the distances of surrounding objects, as well as the color and shape information. In this paper, we use the correspondence between a 3-D LiDAR scanner and a CCD camera to rearrange the captured LiDAR point cloud into a dense depth map, in which each 3-D point corresponds to a pixel at the same location in the RGB image. In this paper, we assume that the LiDAR scanner and the CCD camera are accurately calibrated and synchronized beforehand so that each 3-D LiDAR point cloud is aligned with its corresponding RGB image. Each frame of the LiDAR point cloud is then projected onto the RGB image plane to form a sparse depth map. Then, a self-adaptive method is proposed to upsample the sparse depth map into a dense depth map, in which the RGB image and the anisotropic diffusion tensor are exploited to guide upsampling by reinforcing the RGB-depth compactness. Finally, convex optimization is applied on the dense depth map for global enhancement. Experiments on the KITTI and Middlebury data sets demonstrate that the proposed method outperforms several other relevant state-of-the-art methods in terms of visual comparison and rootmean-square error measurement.Index Terms-Intelligent vehicle, dense depth map, 3D-2D conversion, upsampling, global enhancement.

No abstract

In this paper we focus on what meaningful 2D perceptual information we can get from 3D LiDAR point cloud. Current work [1] [2] [3] have demonstrated that the depth, height and local surface normal value of a 3D data are useful features for improving Deep Neural Networks (DNNs) based object detection. We thus propose to organise LiDAR point as three different maps: dense depth map, height map and surface normal map. Specifically, given a pair of RGB image and sparse depth map projected from LiDAR point cloud, we propose a parameter self-adaptive method to upgrade sparse depth map to dense depth map, which is then passed to a convex optimisation framework to gain global enhancement. Height map is obtained by reprojecting each pixel in dense depth map into 3D coordinate, which enables us to record its height value, surface normal map is obtained by a trilateral filter constructed from depth map and RGB image. Finally, we validate our framework on both KITTI tracking dataset and Middlebury dataset 1 . To the best of our knowledge, we are the first to interpret 3D LiDAR point cloud as various 2D features and hope it will motivate more research on object detection by combing RGB image and 3D LiDAR point cloud.

Ancient paintings can provide valuable information for historians and archeologists to study the history and humanity of the corresponding eras. How to determine the era in which a painting was created is a critical problem, since the topic of a painting cannot be used as an effective basis without an era label. To address this problem, this article proposes a novel computational method by using multi-view local color features extracted from the paintings. First, we extract the multi-view local color features for all training images using a novel descriptor named Affine Lab-SIFT. Then we can learn the codebook from all these features by k -means clustering. Afterwards, we create a feature histogram for each image in the form of bag-of-visual-words and use a supervised fashion to train a classifier, which is used for further painting classification. Experimental results from two different datasets show the effectiveness of the proposed classification system and the advantage of the proposed features, especially in the case of small-size training samples.

No abstract