Hao Yang

Mr. Hao Yang

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 October 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FHFang Huang
Fang Huang
HYHao Yang
Hao Yang
XTXicheng Tan
Xicheng Tan
SPShuying Peng
Shuying Peng
JTJian Tao
Jian Tao
SPSiyuan Peng
Siyuan Peng
In recent years, the rapid development of unmanned aerial vehicle (UAV) technologies has made data acquisition increasingly convenient, and three-dimensional (3D) reconstruction has emerged as a popular subject of research in this context. These 3D models have many advantages, such as the ability to represent realistic scenes and a large amount of information. However, traditional 3D reconstruction methods are expensive, and require long and complex processing. As a result, they cannot rapidly respond when used in time-sensitive applications, e.g., those for such natural disasters as earthquakes, debris flow, etc. Computer vision-based simultaneous localization and mapping (SLAM) along with hardware development based on embedded systems, can provide a solution to this problem. Based on an analysis of the principle and implementation of the visual SLAM algorithm, this study proposes a fast method to quickly reconstruct a dense 3D point cloud model on a UAV platform combined with an embedded graphics processing unit (GPU). The main contributions are as follows: (1) to resolve the contradiction between the resource limitations and the computational complexity of visual SLAM on UAV platforms, the technologies needed to compute resource allocation, communication between nodes, and data transmission and visualization in an embedded environment were investigated to achieve real-time data acquisition and processing. Visual monitoring to this end is also designed and implemented. (2) To solve the problem of time-consuming algorithmic processing, a corresponding parallel algorithm was designed and implemented based on the parallel programming framework of the compute unified device architecture (CUDA). (3) The visual odometer and methods of 3D “map” reconstruction were designed using under a monocular vision sensor to implement the prototype of the fast 3D reconstruction system. Based on preliminary results of the 3D modeling, the following was noted: (1) the proposed method was feasible. By combining UAV, SLAM, and parallel computing, a simple and efficient 3D reconstruction model of an unknown area was obtained for specific applications. (2) The parallel SLAM algorithm used in this method improved the efficiency of the SLAM algorithm. On the one hand, the SLAM algorithm required 1/6 of the time taken by the structure-from-motion algorithm. On the other hand, the speedup obtained using the parallel SLAM algorithm based on the embedded GPU on our test platform was 7.55 × that of the serial algorithm. (3) The depth map results show that the effective pixel with an error less than 15cm is close to 60%.

20 July 2011 in Robot
Verified
Journal Article
Closed access
HYHao Yang
Hao Yang
FZFeng Zhang
Feng Zhang
JYJuntao Ye
Juntao Ye

28 May 2021
Verified
Conference Paper
Closed access
XZXiaohong Zhou
Xiaohong Zhou
HYHengxin Yang
Hengxin Yang
HYHao Yang
Hao Yang
A large amount of the 3D point cloud data obtained by 3D laser scanning technology are redundant, which is not conducive to computer storage and calculation and reduces the reconstruction efficiency. Considering the low accuracy of several point cloud reduction method and the lack of details, proposing a point cloud grid reduction method based on feature parameters. Firstly, the point cloud topological relationship is established by calculating the point cloud normal vector and curvature according to the KD-tree, and the product of multiple parameters which are used as the feature parameters; then, the voxel grid algorithm is used to divide the point cloud data and distinguish them according to the average curvature in each grid feature area and non-feature area; finally, different methods are used to simplify the point cloud in different areas. Through the comparative analysis of experiments, this paper shows that the method can improve the reconstruction efficiency, effectively avoid holes, and better retain the detailed features of the point cloud.