High-accuracy Range Image Generation by Fusing Binocular and Motion Stereo Using Fisheye Stereo Camera

2020 ◽  
Author(s):  
Hirotaka Iida ◽  
Yonghoon Ji ◽  
Kazunori Umeda ◽  
Akira Ohashi ◽  
Daisuke Fukuda ◽  
...  
Keyword(s):  
High Accuracy ◽  
Range Image ◽  
Image Generation ◽  
Stereo Camera ◽  
Motion Stereo

High-Dynamic-Range Image Generation and Coding for Multi-exposure Multi-view Images

2016 ◽  
Vol 36 (7) ◽  
pp. 2786-2814 ◽  
Author(s):  
Jui-Chiu Chiang ◽  
Po-Han Kao ◽  
Yao-Sheng Chen ◽  
Wei-Ren Chen
Keyword(s):  
Dynamic Range ◽  
High Dynamic Range ◽  
Range Image ◽  
Image Generation ◽  
High Dynamic Range Image ◽  
High Dynamic

High Dynamic Range Image Generation Method by Fusing Multi-Level Gamma-Transformed Images

2018 ◽  
Vol 55 (4) ◽  
pp. 041014
Author(s):  
陈小楠 Chen Xiaonan ◽  
张淑芳 Zhang Shufang ◽  
雷志春 Lei Zhichun
Keyword(s):  
Dynamic Range ◽  
High Dynamic Range ◽  
Range Image ◽  
Image Generation ◽  
High Dynamic Range Image ◽  
High Dynamic ◽  
Multi Level

scholarly journals INDOOR LIDAR RELOCALIZATION BASED ON DEEP LEARNING USING A 3D MODEL

2020 ◽  
Vol XLIII-B1-2020 ◽  
pp. 541-547
Author(s):  
H. Zhao ◽  
D. Acharya ◽  
M. Tomko ◽  
K. Khoshelham
Keyword(s):  
Indoor Environment ◽  
3D Model ◽  
Indoor Localization ◽  
High Accuracy ◽  
Lidar Data ◽  
Indoor Environments ◽  
Navigation Systems ◽  
Range Image ◽  
Range Images ◽  
Mapping Systems

Abstract. Indoor localization, navigation and mapping systems highly rely on the initial sensor pose information to achieve a high accuracy. Most existing indoor mapping and navigation systems cannot initialize the sensor poses automatically and consequently these systems cannot perform relocalization and recover from a pose estimation failure. For most indoor environments, a map or a 3D model is often available, and can provide useful information for relocalization. This paper presents a novel relocalization method for lidar sensors in indoor environments to estimate the initial lidar pose using a CNN pose regression network trained using a 3D model. A set of synthetic lidar frames are generated from the 3D model with known poses. Each lidar range image is a one-channel range image, used to train the CNN pose regression network from scratch to predict the initial sensor location and orientation. The CNN regression network trained by synthetic range images is used to estimate the poses of the lidar using real range images captured in the indoor environment. The results show that the proposed CNN regression network can learn from synthetic lidar data and estimate the pose of real lidar data with an accuracy of 1.9 m and 8.7 degrees.

Sign in / Sign up

Export Citation Format

Share Document