Ali Zia

Dr. Ali Zia

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
1 July 2020 in Energy
Verified
Journal Article
Closed access
UTUsman Bashir Tayab
Usman Bashir Tayab
AZAli Zia
Ali Zia
FYFuwen Yang
Fuwen Yang
JLJunwei Lu
Junwei Lu
MKMuhammad Kashif
Muhammad Kashif

29 February 2024 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
AZAli Zia
Ali Zia
AKAbdelwahed Khamis
Abdelwahed Khamis
JNJames Nichols
James Nichols
UTUsman Bashir Tayab
Usman Bashir Tayab
ZHZeeshan Hayder
Zeeshan Hayder
LPLars Petersson
Lars Petersson
Topological deep learning (TDL) is an emerging area that combines the principles of Topological data analysis (TDA) with deep learning techniques. TDA provides insight into data shape; it obtains global descriptions of multi-dimensional data whilst exhibiting robustness to deformation and noise. Such properties are desirable in deep learning pipelines, but they are typically obtained using non-TDA strategies. This is partly caused by the difficulty of combining TDA constructs (e.g. barcode and persistence diagrams) with current deep learning algorithms. Fortunately, we are now witnessing a growth of deep learning applications embracing topologically-guided components. In this survey, we review the nascent field of topological deep learning by first revisiting the core concepts of TDA. We then explore how the use of TDA techniques has evolved over time to support deep learning frameworks, and how they can be integrated into different aspects of deep learning. Furthermore, we touch on TDA usage for analyzing existing deep models; deep topological analytics. Finally, we discuss the challenges and future prospects of topological deep learning.

4 September 2017 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
SASuhad Lateef Al-Khafaji
Suhad Lateef Al-Khafaji
JZJun Zhou
Jun Zhou
AZAli Zia
Ali Zia
ALAlan Wee-Chung Liew
Alan Wee-Chung Liew
Spectral-spatial feature extraction is an important task in hyperspectral image processing. In this paper we propose a novel method to extract distinctive invariant features from hyperspectral images for registration of hyperspectral images with different spectral conditions. Spectral condition means images are captured with different incident lights, viewing angles, or using different hyperspectral cameras. In addition, spectral condition includes images of objects with the same shape but different materials. This method, which is named spectral-spatial scale invariant feature transform (SS-SIFT), explores both spectral and spatial dimensions simultaneously to extract spectral and geometric transformation invariant features. Similar to the classic SIFT algorithm, SS-SIFT consists of keypoint detection and descriptor construction steps. Keypoints are extracted from spectral-spatial scale space and are detected from extrema after 3D difference of Gaussian is applied to the data cube. Two descriptors are proposed for each keypoint by exploring the distribution of spectral-spatial gradient magnitude in its local 3D neighborhood. The effectiveness of the SS-SIFT approach is validated on images collected in different light conditions, different geometric projections, and using two hyperspectral cameras with different spectral wavelength ranges and resolutions. The experimental results show that our method generates robust invariant features for spectral-spatial image matching.

1 December 2013
Verified
Conference Paper
Closed access
JLJie Liang
Jie Liang
AZAli Zia
Ali Zia
JZJun Zhou
Jun Zhou
XSXavier Sirault
Xavier Sirault
Plant phenomics research requires different types of sensors be employed to measure the physical traits of plant surface and to estimate the plant biomass. Of particular interest is the hyperspectral imaging device which captures wavelength indexed band images that characterise material properties of objects under study. In this paper, we introduce a proof of concept research that builds 3D plant model directly from hyperspectral images captured in a controlled lab environment. We show that hyperspectral imaging has shown clear advantages in segmenting plant from its background and is promising in generating comprehensive 3D plant models.

1 January 2015
Verified
Conference Paper
Closed access
AZAli Zia
Ali Zia
JLJie Liang
Jie Liang
JZJun Zhou
Jun Zhou
YGYongsheng Gao
Yongsheng Gao
3D reconstruction from hyper spectral images has seldom been addressed in the literature. This is a challenging problem because 3D models reconstructed from different spectral bands demonstrate different properties. If we use a single band or covert the hyper spectral image to gray scale image for the reconstruction, fine structural information may be lost. In this paper, we present a novel method to reconstruct a 3D model from hyper spectral images. Our proposed method first generates 3D point sets from images at each wavelength using the typical structure from motion approach. A structural descriptor is developed to characterize the spatial relationship between the points, which allows robust point matching between two 3D models at different wavelength. Then a 3D registration method is introduced to combine all band-level models into a single and complete hyper spectral 3D model. As far as we know, this is the first attempt in reconstructing a complete 3D model from hyper spectral images. This work allows fine structural-spectral information of an object be captured and integrated into the 3D model, which can be used to support further research and applications.

13 April 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
AZAli Zia
Ali Zia
JZJun Zhou
Jun Zhou
YGYongsheng Gao
Yongsheng Gao
This article investigates spectral chromatic and spatial defocus aberration in a monocular hyperspectral image (HSI) and proposes methods on how these cues can be utilized for relative depth estimation. The main aim of this work is to develop a framework by exploring intrinsic and extrinsic reflectance properties in HSI that can be useful for depth estimation. Depth estimation from a monocular image is a challenging task. An additional level of difficulty is added due to low resolution and noises in hyperspectral data. Our contribution to handling depth estimation in HSI is threefold. Firstly, we propose that change in focus across band images of HSI due to chromatic aberration and band-wise defocus blur can be integrated for depth estimation. Novel methods are developed to estimate sparse depth maps based on different integration models. Secondly, by adopting manifold learning, an effective objective function is developed to combine all sparse depth maps into a final optimized sparse depth map. Lastly, a new dense depth map generation approach is proposed, which extrapolate sparse depth cues by using material-based properties on graph Laplacian. Experimental results show that our methods successfully exploit HSI properties to generate depth cues. We also compare our method with state-of-the-art RGB image-based approaches, which shows that our methods produce better sparse and dense depth maps than those from the benchmark methods.