New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Defense against adversarial attacks on deep learning in computer vision. Computer vision applications rely heavily on deep learning, which is highly vulnerable to being fooled by adding subtle perturbations to object/image textures that are imperceptible to humans. This project aims to develop defense mechanisms to detect and remove adversarial patterns from the input images. The project expects to advance knowledge in understanding the vulnerabilities of deep learning, and to design deep learni ....Defense against adversarial attacks on deep learning in computer vision. Computer vision applications rely heavily on deep learning, which is highly vulnerable to being fooled by adding subtle perturbations to object/image textures that are imperceptible to humans. This project aims to develop defense mechanisms to detect and remove adversarial patterns from the input images. The project expects to advance knowledge in understanding the vulnerabilities of deep learning, and to design deep learning architectures that are inherently robust. The outcomes of this project will increase the security and reliability of computer vision by detecting, reporting and nullifying such attacks and will benefit the general public and industry on many fronts.Read moreRead less
How the brain generates robust behaviour in noisy sensory environments. This project aims to investigate the origins of variability in the control of movements. This project expects to generate new knowledge in the area of sensory and motor neuroscience by determining how variability in the activity of sensory and motor neurons accounts for variability in the initiation and control of eye movements. Expected outcomes of this project include international collaboration, development of new methods ....How the brain generates robust behaviour in noisy sensory environments. This project aims to investigate the origins of variability in the control of movements. This project expects to generate new knowledge in the area of sensory and motor neuroscience by determining how variability in the activity of sensory and motor neurons accounts for variability in the initiation and control of eye movements. Expected outcomes of this project include international collaboration, development of new methods for imaging neural activity in vivo, and refinement of theories concerning the cause and implications of noise in the brain. This should provide significant benefits such as a better understanding of why our movements are variable, and whether it is desirable or possible to minimise this variability. Read moreRead less
Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220101390
Funder
Australian Research Council
Funding Amount
$402,900.00
Summary
Towards Human-like Machine Perception for Embodied AI. This project aims to investigate human-like visual perception, whereby AI machines can see and interpret the world like a human. The expected outputs will empower AI machines with the abilities of human-centered visual recognition and annotation-efficient learning through a set of deep learning techniques, and the ability to actively gather visual information through a reinforcement learning methodology (for decision support). This research ....Towards Human-like Machine Perception for Embodied AI. This project aims to investigate human-like visual perception, whereby AI machines can see and interpret the world like a human. The expected outputs will empower AI machines with the abilities of human-centered visual recognition and annotation-efficient learning through a set of deep learning techniques, and the ability to actively gather visual information through a reinforcement learning methodology (for decision support). This research is fundamental to the creation of embodied AI machines, which are expected to provide assistance to humans in industry, education and health. It thus will indicate immediate applications embracing autonomous vehicles and domestic robotics, providing scientific, social and economic benefits for Australia.Read moreRead less
Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previous ....Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previously unseen environments, and the ability to control such agents with more human-like instructions. Such capabilities are desirable, and in some cases essential, for autonomous robots in a variety of important application areas including automated warehousing and high-level control of autonomous vehicles. Read moreRead less
3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intell ....3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intelligent Transportation, Environment Monitoring, and Augmented Reality, applicable in smart-city planning and medical applications such as computer-enhanced surgery. The goal is to build Australia's competitive advantage in the forefront of ICT research and technology innovation.Read moreRead less
Emergent cues underlying the perception of shape, colour, and material . This goal of this project is to identify the information the visual system uses to extract the three-dimensional structure and material composition of objects. This project aims to generate an advanced understanding of the information that supports these perceptual abilities and to advance our understanding how this information is learned from exposure to natural scenes. The findings of this work are expected to benefit ou ....Emergent cues underlying the perception of shape, colour, and material . This goal of this project is to identify the information the visual system uses to extract the three-dimensional structure and material composition of objects. This project aims to generate an advanced understanding of the information that supports these perceptual abilities and to advance our understanding how this information is learned from exposure to natural scenes. The findings of this work are expected to benefit our understanding of the human visual system, and to provide insights into the information needed to advance the development of deep neural networks (machine learning) that exploit the same information used by humans to guide our behavior and recognize objects and materials.Read moreRead less
Perceiving and misperceiving the causes of optical structure. This project aims to understand the conditions that cause humans to misperceive the shape and surface properties of real-world materials. Most natural materials are translucent to varying degrees, but little is known about how light is transported through them or how such materials are perceived or misperceived. This project will determine the conditions and causes responsible for the misperception of material properties and shape, an ....Perceiving and misperceiving the causes of optical structure. This project aims to understand the conditions that cause humans to misperceive the shape and surface properties of real-world materials. Most natural materials are translucent to varying degrees, but little is known about how light is transported through them or how such materials are perceived or misperceived. This project will determine the conditions and causes responsible for the misperception of material properties and shape, and will offer practical information about what can be done to minimise such misperceptions. The outcomes of the project are expected to lead to new techniques for depicting and manipulating real-world translucent materials in computer graphics, virtual reality, and gaming industries.Read moreRead less
Collaborative Sensing and Learning for Maritime Situational Awareness. We aim to demonstrate coordinated autonomous sensing of naval assets in dynamic maritime environments, reducing the operational load required to deliver a high quality maritime situational awareness. A realistic simulation based approach will help us develop novel artificial intelligence technology including: self-adaptive strategies for dynamic asset allocation, embedded smart sensing capabilities for naval observation syste ....Collaborative Sensing and Learning for Maritime Situational Awareness. We aim to demonstrate coordinated autonomous sensing of naval assets in dynamic maritime environments, reducing the operational load required to deliver a high quality maritime situational awareness. A realistic simulation based approach will help us develop novel artificial intelligence technology including: self-adaptive strategies for dynamic asset allocation, embedded smart sensing capabilities for naval observation systems and novel approaches to continuous collaborative learning from multi-spectral media. In addition to the emerging partnership between participants, the project will advance sovereign capability to develop maritime intelligence gathering technology for the Royal Australian Navy to underpin stability in our region. Read moreRead less