Article
Engineering, Electrical & Electronic
Tingting Hu, Ryuji Fuchikami, Takeshi Ikenaga
Summary: The ultralow delay tracking system is gaining attention in robotics and factory automation, allowing seamless actuation in visual feedback applications. Tracking accuracy and rotational robustness are crucial in these applications. However, current research focuses mainly on the accuracy of still images and neglects tracking errors caused by changes during processing. This study aims to develop a 1-ms rotation-robust Lucas Kanade (LK)-based tracking algorithm and architecture to minimize the error between virtual and real space.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Mahboubeh Khajavi, Alireza Ahmadyfard
Summary: This paper presents a simulation of human face evolution from youth to old age. The goal is to accurately estimate a person's face at the target age while maintaining their appearance. The proposed method involves selecting proper feature points, using the active appearance model (AAM) method and templates to represent different age groups. The results of the survey show that the method has a high accuracy in age recognition and real image recognition.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Computer Science, Interdisciplinary Applications
Mohammadreza Amjadian, Seyed Masood Mostafavi, Jiangbo Chen, Zahra Kavehvash, Jingyi Zhu, Lidai Wang
Summary: This paper proposes a novel super-resolution volumetric photoacoustic microscopy based on structured illumination theory, utilizing optical excitation and Fourier-domain reconstruction algorithm to improve lateral resolution and reduce computational load. Experimental results demonstrate significant enhancements in lateral resolution and signal-to-noise ratio of the imaging system.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Physics, Multidisciplinary
Shipei Dang, Jia Qian, Tong Peng, Chen Bai, Junwei Min, Haixia Wang, Baoli Yao, Dan Dan
Summary: Optical sectioning structured illumination microscopy (OS-SIM) has gained significant interest in fast 3D microscopy. The conventional method for reconstructing optical sectioning images using the root-mean-square (RMS) algorithm in the spatial domain tends to have residual background noise. To address this issue, we propose a Fourier domain based algorithm (Fourier-OS-SIM) that improves background noise suppression compared to the RMS algorithm. Experimental results confirm the feasibility and effectiveness of the algorithm, and suggest potential applications in biomedical or industrial fields.
FRONTIERS IN PHYSICS
(2022)
Article
Computer Science, Information Systems
Umer Sadiq Khan, Xingjun Zhang, Yuanqi Su
Summary: The study utilizes the active contour model for salient object detection, proposing a novel numerical solution scheme derivative that optimizes the active contour (Snake) differential equations through fast Fourier transformation, and extracting salient objects in natural scenes. Compared to existing methods, the proposed approach achieves at least a 3% increase in accuracy, runs fast, with an average running time of one twelfth of the baseline.
Article
Acoustics
Yang Yang, Shuo Yang, Yuanming Ding
Summary: This study presents a blind separation algorithm in the spatial fractional Fourier domain, which can improve the signal-to-reverberation ratio, especially performing better at lower SRR levels compared to time-frequency domain blind separation algorithms.
ACOUSTICS AUSTRALIA
(2021)
Article
Engineering, Electrical & Electronic
Monika Jain, Arjun Tyagi, A. Subramanyam, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: Explored the application of channel regularization and graph regularization methods in visual object tracking, improving the performance and discriminative power of learned filters, effectively solving the issue of uneven weight assignment to feature channels.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Tharindu Fernando, Sridha Sridharan, Simon Denman, Houman Ghaemmaghami, Clinton Fookes
Summary: This paper introduces a novel framework for detecting lung sound events by using a multi-branch TCN architecture and feature fusion to identify discrete events in lung sound recordings. The proposed method shows promising results on multiple benchmarks, aiding in the identification of respiratory diseases. The feature concatenation strategy effectively suppresses non-informative features, leading to the construction of a lightweight network.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Computer Science, Information Systems
Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: In this study, a subject-independent seizure predictor using Geometric Deep Learning (GDL) is proposed. The models achieve state-of-the-art performance on two benchmark datasets and this is the first study that proposes synthesizing subject-specific graphs for seizure prediction. Furthermore, the model interpretation shows potential contribution of this method towards Scalp EEG-based seizure localization.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Robotics
Chanoh Park, Peyman Moghadam, Jason Williams, Soohwan Kim, Sridha Sridharan, Clinton Fookes
Summary: The article introduces a novel map-centric SLAM framework, ElasticLiDAR++, which overcomes the challenges of multimodal sensor fusion and LiDAR motion distortion. Using a local continuous-time trajectory representation, the method achieves nonredundant yet dense mapping through a surface resolution preserving matching algorithm and surfel fusion model.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Computer Science, Artificial Intelligence
Kien Nguyen, Clinton Fookes, Sridha Sridharan, Arun Ross
Summary: In this paper, we design a fully complex-valued neural network specifically for iris recognition. By capturing both phase and magnitude information, our network outperforms real-valued networks in representing the biometric content of iris texture. The experiments on benchmark datasets show that our proposed network improves the performance of iris recognition when compared to traditional methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: Generative Adversarial Networks (GANs) are a revolutionary innovation in machine learning that enable the generation of artificial data. In the medical field, where collecting and annotating real data is difficult, artificial data synthesis is valuable. However, the capabilities of generative models for data generation, especially in biosignal modality transfer, have not been fully exploited in biomedical research. In this study, we analyze and evaluate the application of adversarial learning on biosignal data, focusing on synthesizing 1D biosignal data and modality transfer. Our results show superior performance in biosignal generation and modality transfer, making clinical monitoring more convenient for patients.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Amena Khatun, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: In this paper, an end-to-end pose-driven attention-guided generative adversarial network is proposed to generate multiple poses of a person. The attention mechanism is used to learn and transfer the subject pose, and a semantic-consistency loss is proposed to preserve the semantic information during pose transfer. Appearance and pose discriminators are utilized to ensure the realism and consistency of the transferred images. Incorporating the proposed approach in a person re-identification framework achieves realistic pose transferred images and state-of-the-art re-identification results.
PATTERN RECOGNITION
(2023)
Article
Robotics
Kavisha Vidanapathirana, Peyman Moghadam, Sridha Sridharan, Clinton Fookes
Summary: This paper presents an efficient spectral method called SpectralGV for geometric verification and re-ranking. It is able to identify the correct candidate among potential matches retrieved by global similarity search without requiring resource intensive point cloud registration.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: Electrocardiograms (ECGs) are a viable method for diagnosing cardiovascular diseases (CVDs). Machine learning algorithms, such as deep neural networks trained on ECG signals, have shown promising results in identifying CVDs. However, existing models for ECG anomaly detection require long training times and computational resources. To overcome this, we propose a novel deep learning architecture that utilizes dilated convolution layers, allowing for learning from short ECG segments and flexibly diagnosing CVDs.
IEEE SENSORS JOURNAL
(2023)
Article
Geochemistry & Geophysics
Tharindu Fernando, Clinton Fookes, Harshala Gammulle, Simon Denman, Sridha Sridharan
Summary: With advancements in low-power embedded computing devices and remote sensing instruments, the traditional satellite image processing pipeline is being replaced by on-board processing of data, enabling timely intelligence extraction on the satellite itself. The on-board processing of multispectral satellite images is limited to classification and segmentation tasks, but we aim to extend it to panoptic segmentation and evaluate the applicability of state-of-the-art models in an on-board setting. Our proposed multimodal teacher network and online knowledge distillation framework improve segmentation accuracy and demonstrate significant improvements in segmentation quality metrics for on-board processing.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Kien Nguyen, Tharindu Fernando, Clinton Fookes, Sridha Sridharan
Summary: Modern automated surveillance techniques rely on deep learning methods, but these methods are susceptible to adversarial attacks. Attackers can bypass detection and recognition of surveillance systems by altering their appearance or behavior, posing a threat to security. This article reviews recent attempts and findings in physical adversarial attacks on surveillance systems, and proposes strategies for defense and evaluation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Huy Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes
Summary: This study proposes a new benchmark dataset, AG-ReID, for person re-identification across aerial and ground cameras. The dataset, collected by a UAV and a ground-based CCTV camera, presents a novel elevated-viewpoint challenge and employs an explainable algorithm to address it.
2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME
(2023)
Proceedings Paper
Automation & Control Systems
Joshua Knights, Kavisha Vidanapathirana, Milad Ramezani, Sridha Sridharan, Clinton Fookes, Peyman Moghadam
Summary: Wild-Places is a challenging large-scale dataset specifically designed for lidar place recognition in unstructured, natural environments. It contains eight lidar sequences with a total of 63K submaps and provides accurate ground truth for both loop closure detection and re-localisation tasks.
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023)
(2023)
Article
Computer Science, Information Systems
Ivan Himawan, Ruizhe Wang, Sridha Sridharan, Clinton Fookes
Summary: This study proposes a joint training scheme for an any-to-one voice conversion system with LPCNet to enhance the naturalness, speaker similarity, and intelligibility of converted speech. By incorporating speaker-independent features derived from an automatic speech recognition model, the conversion model accurately captures the linguistic contents of the given utterance and maps them to the acoustic representations used by LPCNet. Experimental results demonstrate that the proposed model enables real-time voice conversion and outperforms existing state-of-the-art approaches.
Article
Computer Science, Information Systems
Dung Nguyen, Duc Thanh Nguyen, Rui Zeng, Thanh Thi Nguyen, Son N. Tran, Thin Nguyen, Sridha Sridharan, Clinton Fookes
Summary: This paper proposes a novel deep neural network architecture for integrating visual and audio signal streams for emotion recognition, achieving state-of-the-art performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)