Changming Sun

• PhD
• The Commonwealth Scientific and Industrial Research Organisation

Image-based 3D reconstruction remains a competitive field of research as state-of-the-art algorithms continue to improve. This paper presents a voxel-based algorithm that adapts the earliest space-carving methods and utilises a minimal surface technique to obtain a cleaner result. Embedded Voxel Colouring is built in two stages: (a) progressive vox...

This paper presents a fast and reliable stereo matching algorithm which produces a dense disparity map by using fast cross correlation, rectangular subregioning (RSR) and 3D maximum-surface techniques in a coarse-to-fine scheme. Fast correlation is achieved by using the box-filtering technique whose speed is invariant to the size of the correlation...

Single shortest path extraction algorithms have been used in a number of areas such as network flow and image analysis. In image analysis, shortest path techniques can be used for object boundary detection, crack detection, or stereo disparity estimation. Sometimes one needs to find multiple paths as opposed to a single path in a network or an imag...

Semantic segmentation is of great importance in the field of autonomous driving, as it provides semantic information for a scene that intelligent vehicles needs to interact with. Although a large number of different semantic segmentation networks have been proposed, achieving high performance for semantic segmentation in real-time using a lightweig...

High-resolution RGB-D sensors are widely used in computer vision, manufacturing, and robotics. The depth maps from these sensors have inherently high measurement uncertainty that includes both systematic and non-systematic noise. These noisy depth estimates degrade the quality of scans, resulting in less accurate 3D reconstruction, making them unsu...

Object detection in infrared images poses a considerable challenge due to its small-scale targets, low contrast and poor signal-to-clutter ratio, often resulting in a high false alarm rate. To improve the detection accuracy on infrared small targets, we introduce Light-SGMTLM, a lightweight and saliency-guided multi-task learning model. This model...

The precise diagnosis of urinary stones is crucial for devising effective treatment strategies. The diagnostic process, however, is often complicated by the low contrast between stones and surrounding tissues, as well as the variability in stone locations across different patients. To address this issue, we propose a novel location embedding based...

It is very challenging to fully use cross-view information for stereo image super-resolution. Previous methods using pixel-based parallax-attention mechanisms do not consider neighborhood pixels. Also, they typically use convolutions for basic feature extraction, which may not be as effective as modern self-attention mechanisms in transformers. To...

In the dynamic landscape of saliency detection, convolutional neural networks have emerged as catalysts for innovation, but remain largely tailored for RGB imagery, falling short in the context of infrared images, particularly in memory-restricted environments. These existing approaches tend to overlook the wealth of contour information vital for a...

The goal of few-shot fine-grained image classification (FSFGIC) is to distinguish subordinate-level categories with subtle visual differences such as the species of bird and models of car with only a few samples. In this work, we argue that a designed network that has the ability to better distinguish feature descriptors of different categories wil...

Acquiring pixel-level annotations is often limited in applications such as histology studies that require domain expertise. Various semi-supervised learning approaches have been developed to work with limited ground truth annotations, such as the popular teacher-student models. However, hierarchical prediction uncertainty within the student model (...

Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples. Through feature representation learning, FSFGIC methods can make better use of limited sample information, learn more disc...

Zero-shot incremental learning aims to enable the model to generalize to new classes without forgetting previously learned classes. However, the semantic gap between old and new sample classes can lead to catastrophic forgetting. Additionally, existing algorithms lack capturing significant information from each sample image domain, impairing models...

Due to the lack of discriminative features in infrared images, most of existing trackers cannot separate a target from its background. There are some studies on generating discriminative features where feature fusion and attention are applied to enhance targets. However, the saliency information and information interaction which assist in locating...

Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to repr...

Accurate tumor segmentation is crucial for esophageal cancer radiotherapy treatment planning. The low contrast among the esophagus, tumors, and surrounding tissues, and irregular tumor shapes limit the performance of automatic segmentation methods. In this paper, we aim to exploit the irregular shapes of tumors to facilitate accurate segmentation....

Deep learning based stereo matching algorithms have been extensively researched in areas such as robot vision and autonomous driving due to their promising performance. However, these algorithms require a large amount of labeled data for training and encounter inadequate domain adaptability, which degraded their applicability and flexibility. This...

Detecting weak target is an important and challenging problem in many applications such as radar, sonar etc. However, conventional detection methods are often ineffective in this case because of low signal-to-noise ratio (SNR). This paper presents a track-before-detect (TBD) algorithm based on an improved particle filter, i.e. cost-reference partic...

Semantic segmentation is a crucial task with wideranging applications, including autonomous driving and robot navigation. However, prevailing state-of-the-art methods primarily focus on monocular images, neglecting the untapped potential of stereo cameras commonly equipped in autonomous vehicles and robots, which capture binocular images. In this p...

Sarcopenia is a condition of age-associated muscle degeneration that shortens the life expectancy in those it affects, compared to individuals with normal muscle strength. Accurate screening for sarcopenia is a key process of clinical diagnosis and therapy. In this work, we propose a novel multi-modality contrastive learning (MM-CL) based method th...

Confidence calibration - the process to calibrate the output probability distribution of neural networks - is essential for safety-critical applications of such networks. Recent works verify the link between mis-calibration and overfitting. However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks. In t...

Interest point detection methods are gaining more attention and are widely applied in computer vision tasks such as image retrieval and 3D reconstruction. However, there still exist two main problems to be solved: (1) from the perspective of mathematical representations, the differences among edges, corners, and blobs have not been convincingly exp...

Interest point detection methods have received increasing attention and are widely used in computer vision tasks such as image retrieval and 3D reconstruction. In this work, second-order anisotropic Gaussian directional derivative filters with multiple scales are used to smooth the input image and a novel blob detection method is proposed. Extensiv...

Liver is an important metabolic organ in human body and is sensitive to toxic chemicals or drugs. Adverse reactions caused by drug hepatotoxicity will damage the liver and hepatotoxicity is the leading cause of removal of approved drugs from the market. Therefore, it is of great significance to identify liver toxicity as early as possible in the dr...

Interest point detection is one of the most fundamental and critical problems in computer vision and image processing. In this paper, we carry out a comprehensive review on image feature information (IFI) extraction techniques for interest point detection. To systematically introduce how the existing interest point detection methods extract IFI fro...

In viticulture, yield estimation is a key activity, which is important throughout the wine industry value chain. The earlier that an accurate yield estimation can be made the greater its value, increasing management options for grape growers and commercial options for winemakers. For the yield estimate based on in-field measurements at scale, the n...

Structured light 3D imaging is often used for obtaining accurate 3D information via phase retrieval. Single-pattern structured light 3D imaging is much faster than multi-pattern versions. Current phase retrieval methods for single-pattern structured light 3D imaging are however not accurate enough. Besides, the projector resolution in a structured...

Interest points (corners and blobs) play an important role in computer vision tasks such as image matching, image retrieval, and 3D reconstruction. Existing deep learning based interest point detection methods mainly focus on the interest point detection with high repeatability under image affine transformations while neglecting the importance of t...

Road extraction from remote sensing images plays a crucial role in navigation, traffic management, urban construction, and other fields. With the development of deep learning in the field of computer vision, road extraction from remote sensing images using deep learning models has become a hot research topic. The convolution-based U-shaped road ext...

Ovarian cancer is one of the most serious cancers that threaten women around the world. Epithelial ovarian cancer (EOC), as the most commonly seen subtype of ovarian cancer, has rather high mortality rate and poor prognosis among various gynecological cancers. Survival analysis outcome is able to provide treatment advices to doctors. In recent year...

Learning discriminative visual patterns from image local salient regions is widely used for fine-grained visual classification (FGVC) tasks such as plant or animal species classification. A large number of complex networks have been designed for learning discriminative feature representations. In this paper, we propose a novel local structure infor...

Arbitrarily oriented object detection in remote sensing images is a challenging task. At present, most of the algorithms are dedicated to improving the detection accuracy, while ignoring the detection speed. In order to further improve the detection accuracy and provide a more efficient model for scenes that require real-time detection, we propose...

Ovarian cancer is one of the most serious cancers that threaten women around the world. Epithelial ovarian cancer (EOC), as the most commonly seen subtype of ovarian cancer, has rather high mortality rate and poor prognosis among various gynecological cancers. Survival analysis outcome is able to provide treatment advices to doctors. In recent year...

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this article, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocula...

Acquiring pixel-level annotations for histological image segmentation is time- and labor- consuming. Semi-supervised learning enables learning from the unlabeled and limited amount of labeled data. A challenging issue is the inconsistent and uncertain predictions on unlabeled data. To enforce invariant predictions over the perturbations applied to...

Edge detection is one of the most important and fundamental problems in the field of computer vision and image processing. Edge contours extracted from images are widely used as critical cues for various image understanding tasks such as image segmentation, object detection, image retrieval, and corner detection. The purpose of this paper is to rev...

Corner detection algorithms based on multi-scale analysis attract more attentions due to their promising performance. However, they only consider amplitude information, neglect phase information, and partially utilize multi-scale decomposition coefficients to detect corners. This limits their detection accuracy, repeatability, and localization abil...

Few-shot learning for image classification aims at predicting unseen classes with only a few images. Recent works, especially the works on few-shot fine-grained image classification (FSFGIC), have achieved great progress. However, most of them neglected the spatial information and computed the distance between a query image and a support image dire...

Multi-scale analysis based corner detection algorithms yield impressive performance, however, they are time-consuming and not suitable for real-time computer vision tasks. The classical corner detection algorithms including FAST and Harris are computationally efficient, but their detection accuracy and repeatability are insufficient. This paper des...

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular...

The capability of generalization to unseen domains is crucial for deep learning models when considering real-world scenarios. However, current available medical image datasets, such as those for COVID-19 CT images, have large variations of infections and domain shift problems. To address this issue, we propose a prior knowledge driven domain adapta...

Edge detection plays an important role in image processing and computer vision tasks such as image matching and image segmentation. In this paper, we argue that edges in image should always be detected even under different image rotation transformations or noise conditions. Then a novel edge detection method is presented for improving the robustnes...

For the analysis of medical images, one of the most basic methods is to diagnose diseases by examining blood smears through a microscope to check the morphology, number, and ratio of red blood cells and white blood cells. Therefore, accurate segmentation of blood cell images is essential for cell counting and identification. The aim of this paper i...

Interest point detection is one of the most fundamental and critical problems in computer vision and image processing. In this paper, we carry out a comprehensive review on image feature information (IFI) extraction techniques for interest point detection. To systematically introduce how the existing interest point detection methods extract IFI fro...

Perception of content and structure in images with rainstreaks or raindrops is challenging, and it often calls for robust deraining algorithms to remove the diversified rainy effects. Much progress has been made on the design of advanced encoder–decoder single image deraining networks. However, most of the existing networks are built in a blind man...

The insufficiency of annotated medical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form 3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional fe...

The capability of generalization to unseen domains is crucial for deep learning models when considering real-world scenarios. However, current available medical image datasets, such as those for COVID-19 CT images, have large variations of infections and domain shift problems. To address this issue, we propose a prior knowledge driven domain adapta...

The insufficiency of annotated medical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form 3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional fe...

Corner detection is a critical component of many image analysis and image understanding tasks such as object recognition and image matching. Our research indicates that existing corner detection algorithms cannot properly depict the difference between edges and corners and this results in wrong corner detections. In this paper, the capability of se...

Despite the fact that great progress has been made on single image deraining tasks, it is still challenging for existing models to produce satisfactory results directly, and it often requires a single or multiple refinement stages to gradually improve the quality. However, in this paper, we demonstrate that existing image-level refinement with a st...

Accurate diagnosis and segmentation of skin lesion is critical for early detection and diagnosis of skin cancer. Recent multi-task learning methods require expensive annotations for skin lesion analysis while single-task driven models cannot fully utilize the potential knowledge. The aim of this study is to utilize the neglected knowledge by a flex...

Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this problem, in this paper we propose a new robust tensor decomposition method using generalized correntropy criterion (Corr-Tensor)....

Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, few studies investigate 3...

In this paper, a segmentation method for cell images using Markov random field (MRF) based on a Chinese restaurant process model (CRPM) is proposed. Firstly, we carry out the preprocessing on the cell images, and then we focus on cell image segmentation using MRF based on a CRPM under a maximum a posteriori (MAP) criterion. The CRPM can be used to...

Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the mean square error, which are both suboptimal when there are non-Gaussian noises or outliers in the observation data. To overcome these problems, a new OMP algorithm is developed based on the informati...

High-efficiency image corner detection, one of the most important and critical basic technology in industrial image processing, is to detect point features from an input image in real-time. In this article, we propose a new corner detection method which has both good performance of corner detection and real-time processing abilities. Firstly, the i...

Classification of HEp-2 cell patterns plays a significant role in the indirect immunofluorescence test for identifying autoimmune diseases in the human body. Many automatic HEp-2 cell classification methods have been proposed in recent years, amongst which deep learning based methods have shown impressive performance. This paper provides a comprehe...

Restoring a rainy image with raindrops or rainstreaks of varying scales, directions, and densities is an extremely challenging task. Recent approaches attempt to leverage the rain distribution (e.g., location) as prior to generate satisfactory results. However, concatenation of a single distribution map with the rainy image or with intermediate fea...

Symmetric positive definite (SPD) matrix has recently been used as an effective visual representation. When learning this representation in deep networks, eigen-decomposition of covariance matrix is usually needed for a key step called matrix normalisation. This could result in significant computational cost, especially when facing the increasing n...

Although recent works have made significant progress in encoding meaningful context information for instance segmentation in 2D images, the works for 3D point cloud counterpart lag far behind. Conventional methods use radius search or other similar methods for aggregating local information. However, these methods are unaware of the instance context...

Image corners have been widely used in various computer vision tasks. Current multi-scale analysis based corner detectors do not make full use of the multi-scale and multi-directional structural information. This degrades their detection accuracy and capability of refining corners. In this work, an improved shearlet transform with a flexible number...

Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this problem, in this paper we propose a new robust tensor decomposition method using generalized correntropy criterion (Corr-Tensor)....

Osteoporosis makes bones weak and brittle, increasing the risk of fracture. In this paper, we designed a hybrid model to diagnose osteoporosis based on bone radiograph images. Two types of features were used to distinguish between the “healthy” and the “sick”. One type of features was obtained from deep convolutional neural networks (CNNs), named C...

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or...

Corners are important features for image analysis and computer vision tasks. Local structure tensors with multiple scales are widely used in intensity-based corner detectors. In this paper, the properties of intensity variations of a step edge, L-type corner, Y- or T-type corner, X-type corner, and star-type corner are investigated. The properties...

In this paper, a new edge detection method is proposed where multi-scale anisotropic Gaussian kernels (AGKs) are used to obtain an edge map from an input image. The main advantage of the proposed method is that high edge detection accuracy and edge resolution are attained while maintaining good noise robustness. The proposed method consists of thre...

Despite the great success achieved by convolutional neural networks (CNN) in various image understanding tasks, it is still difficult to be applied to vein recognition tasks due to the problems of insufficient training datasets, intra-class variations, and inter-class similarities. Besides, due to the essential requirement on the storage of million...

Despite being highly secure, vein recognition suffers from high inter-class similarity and intra-class variation resulting from uncontrolled image capture, making the design of discriminative and robust representation very important. The recent success of convolutional neural network (CNN) for various image understanding tasks makes it a promising...

In this paper, we propose a novel color-texture image segmentation method based on local histograms. Starting with clustering-based color quantization, we extract a sufficient number of representative colors. For each pixel, through counting the number of pixels with each representative color within a circular neighborhood, a local histogram is obt...

Effectively describing and recognizing leaf shapes under arbitrary variations, particularly from a large database, remains an unsolved problem. In this research, we attempted a new strategy of describing leaf shapes by walking and measuring along a bunch of chords that pass through the shape. A novel chord bunch walks (CBW) descriptor is developed...

Saliency detection is important in computer vision. However, most of the existing saliency models are designed for visible images. It is still a challenging problem to apply saliency detection algorithms on infrared images. In this paper, an effective propagation based saliency detection method for infrared pedestrian images is proposed. Firstly, b...

Classification of HEp-2 cell patterns plays a significant role in the indirect immunofluorescence test for identifying autoimmune diseases in the human body. Many automatic HEp-2 cell classification methods have been proposed in recent years, amongst which deep learning based methods have shown impressive performance. This paper provides a comprehe...

Despite the significant progress achieved in image de-raining by training an encoder-decoder network within the image-to-image translation formulation, blurry results with missing details indicate the deficiency of the existing models. By interpreting the de-raining encoder-decoder network as a conditional generator, within which the decoder acts a...

In automated photogrammetry of a small object, rotating the object provides an easier setting and more stable camera positions than moving the camera around the object. However, the static features in the background can confuse the structure from motion, which leads to the failure of reconstruction. We are addressing the problem by proposing a mask...

Traditional matrix-based dimensional reduction methods, e.g., two-dimensional principal component analysis (2DPCA) and two-dimensional singular value decomposition (2DSVD), minimize mean square errors (MSE), which is sensitive to outliers. To overcome this problem, in this paper we propose a new robust 2DSVD method based on the kernel mean p power...

Partial occlusions in face images pose a great problem for most face recognition algorithms due to the fact that most of these algorithms mainly focus on solving a second order loss function, e.g., mean square error (MSE), which will magnify the effect from occlusion parts. In this paper, we proposed a kernel non-second order loss function for spar...

Erectile dysfunction (ED) affects millions of men worldwide. Men with ED generally complain failure to attain or maintain an adequate erection during sexual activity. The prevalence of ED is strongly correlated with age, affecting about 40% of men at age 40 and nearly 70% at age 70. A variety of chronic diseases, including diabetes, ischemic heart...

Image corner detection is very important in the fields of image analysis and computer vision. Curvature calculation techniques are used in many contour-based corner detectors. We identify that existing calculation of curvature is sensitive to local variation and noise in the discrete domain and does not perform well when corners are closely located...

A method for determining a level of solar radiation at a point of interest (POI). Multiple sky images are captured by a distributed network of digital cameras. Sun location parameters are determined. A three-dimensional (3D) sky model is generated based on the sky images. Generating the 3D sky model includes generating 3D object data based on the s...

Retinal image processing is very important in the field of clinical medicine. As the first step in retinal image processing, image enhancement is essential. Because the details of a retinal image are complex and difficult to enhance, we present a robust retinal image enhancement algorithm via a dual-tree complex wavelet transform (DTCWT) and morpho...

Gliomas have the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features and...

Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in dense estimation. Although reducing the feature map resolution (i.e., applying a large overall stride) via subsamp...

For image segmentation, fuzzy c-means (FCM) clustering algorithms have been proved to be effective. However, FCM clustering algorithms are sensitive to noises and initialization. They cannot effectively segment cell images with inhomogeneous gray value distributions and complex touching cells. Aiming to overcome these disadvantages, this paper prop...

Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D and 3D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, 3D networks have s...

The orthogonal matching pursuit (OMP) is an important sparse approximation algorithm to recover sparse signals from compressed measurements. However, most MP algorithms are based on the mean square error (MSE) to minimize the recovery error, which is suboptimal when there are outliers. In this paper, we present a new robust OMP algorithm based on k...

To solve the problem of transmission errors in stereoscopic images, this paper proposes a novel error concealment (EC) method using superpixel segmentation and adaptive disparity selection (SSADS). Our algorithm consists of two steps. The first step is disparity estimation for each pixel in a reference image. In this step, the numbers of superpixel...

We propose a new approach for automatic refinement of unorganized point clouds captured by LiDAR scanning systems. Given a point cloud, our method first abstracts the input data into super voxels via over segmentations, and then builds a K-nearest neighbor graph on these voxel nodes. Abstracting into voxel representation provides a means to generat...

Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant differences in optimisation difficulties. In this work, we present a conceptually simple yet efficient framework that simultaneously processe...

In this paper, we propose an adaptive image smoothing method for infrared (IR) and visual ship target images, aiming to effectively suppress noise as well as preserve important target structures, thus benefiting image segmentation. First, by analyzing the specific features of ship target images, a block based method combining local region mean and...

Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant dif- ferences in optimisation difficulties. In this work, we present a conceptually simple yet efficient framework that simultaneously proces...