A New Approach to Calibrate Range Image and Color Image from Kinect

Author(s):  
Li Shibo ◽  
Zhuo Qing
Keyword(s):  
2002 ◽  
Vol 35 (8) ◽  
pp. 1733-1741 ◽  
Author(s):  
G. Louverdis ◽  
M.I. Vardavoulia ◽  
I. Andreadis ◽  
Ph. Tsalides

2020 ◽  
Author(s):  
Anand Swaminathan ◽  
K.Venkata Subramaniyan ◽  
Tiruppathirajan G. ◽  
Rajkumar J

Image segmentation is an important pre-processing step towards higher level tasks such as object recognition, computer vision or image compression. Most of the existing segmentation algorithms deal with grayscale images only. But in the modern world, color images are extensively used in many situations. A new approach for color image segmentation is presented in this paper. There are many ways to deal with image segmentation problem and in these techniques; a particular class of algorithms traces their origin from region-based methods. These algorithms group homogeneous pixels, which are connected to primitive regions. They are easy to implement and are promising. Therefore, here one of the most efficient region-based segmentation algorithms is explained. The color image is quantized adaptively, using a wavelet transform. Then the region growing process is adopted. As preprocess, before actual region merging, small regions are eliminated by merging them with neighbor regions depending upon color similarity. After this, homogeneous regions are merged to get segmented output.


Author(s):  
Yanzhu Liu ◽  
Adams Wai Kin Kong ◽  
Chi Keong Goh

Ordinal regression aims to classify instances into ordinal categories. As with other supervised learning problems, learning an effective deep ordinal model from a small dataset is challenging. This paper proposes a new approach which transforms the ordinal regression problem to binary classification problems and uses triplets with instances from different categories to train deep neural networks such that high-level features describing their ordinal relationship can be extracted automatically. In the testing phase, triplets are formed by a testing instance and other instances with known ranks. A decoder is designed to estimate the rank of the testing instance based on the outputs of the network. Because of the data argumentation by permutation, deep learning can work for ordinal regression even on small datasets. Experimental results on the historical color image benchmark and MSRA image search datasets demonstrate that the proposed algorithm outperforms the traditional deep learning approach and is comparable with other state-of-the-art methods, which are highly based on prior knowledge to design effective features.


2014 ◽  
Vol 86 (8) ◽  
pp. 23-26 ◽  
Author(s):  
Ghada TH.Talee ◽  
Melad J. Jelmeran ◽  
Saja J. Mohammad

2013 ◽  
Vol 33 (2) ◽  
pp. 472-475
Author(s):  
Ling YANG ◽  
Yiguang LIU ◽  
Ronggang HUANG ◽  
Zengxi HUANG

2013 ◽  
Vol 457-458 ◽  
pp. 1012-1016
Author(s):  
Ying Wang ◽  
Daniel Ewert ◽  
Daniel Schilberg ◽  
Sabina Jeschke

Edges are crucial features for object segmentation and classification in both image and point cloud processing. Though many research efforts have been made in edge extraction and enhancement in both areas, their applications are limited respectively owing to their own technical properties. This paper presents a new approach to integrating the edge pixels in the 2D image into boundary data in the 3D point cloud by establishing the mapping relationship between these two types of data to represent the 3D edge features of the object. The 3D edge extraction based on the adoption of Microsoft Kinect as a 3D sensor - involves the following three steps: first, the generation of a range image from the point cloud of the object, second the edge extraction in the range image and edge extraction in the digital image, and finally edge data integration by referring to the correspondence map between point cloud data and image pixels.


Sign in / Sign up

Export Citation Format

Share Document