bufan zhao

Mr. bufan zhao

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
16 April 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
BZbufan zhao
bufan zhao
XHXianghong Hua
Xianghong Hua
KYKegen Yu
Kegen Yu
WXWei Xuan
Wei Xuan
Xijiang ChenXijiang Chen
Xijiang Chen
WTWuyong Tao
Wuyong Tao
Indoor scene segmentation based on 3-D laser point cloud is important for rebuilding and classification, especially for permanent building structure. However, the existing segmentation methods mainly focus on the large-scale planar structures but ignore the other sharp structures and details, which would cause accuracy degradation in scene reconstruction. To handle this issue, an iterative Gaussian mapping-based segmentation strategy has been proposed in this article, which goes from rough segmentation to refined one iteratively to decompose the indoor scene into detectable point cloud clusters layer by layer. An improved model fitting algorithm based on the maximum likelihood estimation sampling consensus (MLESAC) algorithm is proposed for refined segmentation, which is called the Prior-MLESAC algorithm, to deal with the extraction of both vertical and nonvertical planar and cylindrical structures. The experimental results demonstrate that planar and cylindrical structures are segmented more completely by the proposed strategy, and more details of the indoor structure are restored than other existing methods.

15 September 2023 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Closed access
BZbufan zhao
bufan zhao
XCXijiang Chen
Xijiang Chen
XHXianghong Hua
Xianghong Hua
WXWei Xuan
Wei Xuan
DLDerek Lichti
Derek Lichti

12 June 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WTWuyong Tao
Wuyong Tao
XHXianghong Hua
Xianghong Hua
KYKegen Yu
Kegen Yu
Xijiang ChenXijiang Chen
Xijiang Chen
BZbufan zhao
bufan zhao
In the last decades, 3-D object recognition has received significant attention. Particularly, in the presence of clutter and occlusion, 3-D object recognition is a challenging task. In this article, we present an object recognition pipeline to identify the objects from cluttered scenes. A highly descriptive, robust, and computationally efficient local shape descriptor (LSD) is first designed to establish the correspondences between a model point cloud and a scene point cloud. Then, a clustering method, which utilizes the local reference frames (LRFs) of the keypoints, is proposed to select the correct correspondences. Finally, an index is developed to verify the transformation hypotheses. The experiments are conducted to validate the proposed object recognition method. The experimental results demonstrate that the proposed LSD holds high descriptor matching performance and the clustering method can well group the correct correspondences. The index is also very effective to filter the false transformation hypotheses. All these enhance the recognition performance of our method.

12 December 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Xiaoxing HeXiaoxing He
Xiaoxing He
XHXianghong Hua
Xianghong Hua
JMJean-Philippe Montillet
Jean-Philippe Montillet
KYKegen Yu
Kegen Yu
JZJingui Zou
Jingui Zou
BZbufan zhao
bufan zhao
This work mainly discusses an innovative teaching platform on Unmanned Aerial Vehicle digital mapping for Remote Sensing (RS) education at Wuhan University, underlining the fast development of RS technology. Firstly, we introduce and discuss the future development of the Virtual Simulation Experiment Teaching Platform for Unmanned Aerial Vehicle (VSETP-UAV). It includes specific topics such as the Systems and function Design, teaching and learning strategies, and experimental methods. This study shows that VSETP-UAV expands the usual content and training methods related to RS education, and creates a good synergy between teaching and research. The results also show that the VSETP-UAV platform is of high teaching quality producing excellent engineers, with high international standards and innovative skills in the RS field. In particular, it develops students’ practical skills with technical manipulations of dedicated hardware and software equipment (e.g., UAV) in order to assimilate quickly this particular topic. Therefore, students report that this platform is more accessible from an educational point-of-view than theoretical programs, with a quick way of learning basic concepts of RS. Finally, the proposed VSETP-UAV platform achieves a high social influence, expanding the practical content and training methods of UAV based experiments, and providing a platform for producing high-quality national talents with internationally recognized topics related to emerging engineering education.

24 August 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Xijiang ChenXijiang Chen
Xijiang Chen
BZbufan zhao
bufan zhao
The contour feature points of object point cloud are the main features of human perception on target, and play an important role in many fields such as indoor model reconstruction, object detection and location. In this paper, we present a new method to extract the contour feature points of point cloud, which mainly includes two main contents: (1) The conspicuous and inconspicuous boundary points are extracted according to the characteristics of distribution of the azimuth between adjacent vectors in two-dimentional view. (2) According to the direction of main feature vector, a two-dimensional projection plane of adjacent points in the bounding sphere is constructed, and the crease points are extracted according to the constraint parameters model of distribution mechanism of adjacent points in the two-dimensional view. We evaluate the performance of the proposed method using objects of different sizes in real world scenarios. Simultaneously, the extraction effect of contour feature points is compared with other methods, and the results show that the extraction and anti-noise performance of the proposed method is superior to the other methods. Simultaneously, it is suitable not only for regular flat-shaped buildings but also for objects with irregular curvilinear architecture. Moreover, the proposed method involves only one parameter that needs to be tuned, and the parameter can be quickly obtained based on the distance resolution.

31 August 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
BZbufan zhao
bufan zhao
XHXianghong Hua
Xianghong Hua
KYKegen Yu
Kegen Yu
WTWuyong Tao
Wuyong Tao
XHXiaoxing He
Xiaoxing He
PTPengju Tian
Pengju Tian
The interpretation of deep learning network is an important part in understanding the convolutional neural networks (CNNs). As an exploratory research, this article explored the interpretation method in 3-D point cloud deep learning networks, for the purpose of evaluating the performance of convolution functions in 3-D point cloud CNNs. Specifically, a 3-D point cloud classification network with two branches is used as the interpretation network in two aspects; 1) information entropy is introduced to diagnose the internal representation in the middle layer of CNN; and 2) the external consistency of convolution function is measured by per-point classification accuracy with class activation mapping technique. Four typical convolution functions are tested by the interpretation network on ModelNet40 dataset and the experimental results demonstrate that the proposed evaluation method is reliable. Feature transformation ability and feature recognition ability of convolution functions are extracted by visualization evaluation and proposed measurable metrics evaluation.