Muhammad Kamran Afzal

Dr. Muhammad Kamran Afzal

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
5 August 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
SBSaifullahi Bello
Saifullahi Bello
Cheng WangCheng Wang
Cheng Wang
XSXiaotian Sun
Xiaotian Sun
HDHaowen Deng
Haowen Deng
JAJibril Muhammad Adam
Jibril Muhammad Adam
NWNaftaly Muriuki Wambugu
Naftaly Muriuki Wambugu

1 June 2022 in Information Sciences
Verified
Journal Article
Closed access
MAMuhammad Kamran Afzal
Muhammad Kamran Afzal
JAJibril Muhammad Adam
Jibril Muhammad Adam
HAH.M. Rehan Afzal
H.M. Rehan Afzal
YZYu Zang
Yu Zang
SBSaifullahi Bello
Saifullahi Bello
Jonathan Li Jonathan Li
Jonathan Li

21 May 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MAMuhammad Kamran Afzal
Muhammad Kamran Afzal
WLWeiquan Liu
Weiquan Liu
YZYu Zang
Yu Zang
SCShuting Chen
Shuting Chen
HAH M Rehan Afzal
H M Rehan Afzal
Cheng WangCheng Wang
Cheng Wang
The convolutional neural networks (CNNs) functioning on geometric learning for the urban large-scale 3D meshes are indispensable because of their substantial, complex, and deformed shape constitutions. To address this issue, we proposed a novel Geometry-Aware Multi-Source Sparse-Attention CNN (GeoSparseNet) for the urban large-scale triangular mesh classification task. GeoSparseNet leverages the non-uniformity of 3D meshes to depict both broad flat areas and finely detailed features by adopting the multi-scale convolutional kernels. By operating on the mesh edges to prepare for subsequent convolutions, our method exploits the inherent geodesic connections by utilizing the Large Kernel Attention (LKA) based Pooling and Unpooling layers to maintain the shape topology for accurate classification predictions. Learning which edges in a mesh face to collapse, GeoSparseNet establishes a task-oriented process where the network highlights and enhances crucial features while eliminating unnecessary ones. Compared to previous methods, our innovative approach outperforms them significantly by directly processing extensive 3D mesh data, resulting in more discerning feature maps. We achieved an accuracy rate of 87.5% when testing on an urban large-scale model dataset of the Australian city of Adelaide.