Inferring driver behaviours, intent and risk in complex traffic scenarios. This project intends to develop methods to evaluate risk during driving. The next generation of vehicles will be fitted with sophisticated perception and egocentric information. This will be combined with inter-vehicle communication enabling cooperative safety, used in conjunction with intelligent infrastructure. This technology is expected to be mandated in the United States starting from 2017. This project plans to deve ....Inferring driver behaviours, intent and risk in complex traffic scenarios. This project intends to develop methods to evaluate risk during driving. The next generation of vehicles will be fitted with sophisticated perception and egocentric information. This will be combined with inter-vehicle communication enabling cooperative safety, used in conjunction with intelligent infrastructure. This technology is expected to be mandated in the United States starting from 2017. This project plans to develop unsupervised learning algorithms to infer high-level driver behaviours, intent and contextual information to automatically evaluate levels of risk under complex driving scenarios. It plans to validate the results using naturalistic driving datasets taken in large-scale deployments around the world. This innovation may improve automotive safety and facilitate the deployment of autonomous vehicles.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100007
Funder
Australian Research Council
Funding Amount
$303,000.00
Summary
The Future of Urban Routing and Navigation. This project aims to develop new efficient techniques for mixed-initiative routing in large transportation networks. Current state-of-the-art techniques for real-world journey planning take user requirements as input and generate a few proposed journeys as output. However, the most useful decision-support systems are mixed-initiative: the Information Technology (IT) system and user work together to find the best decisions. In the context of journey pla ....The Future of Urban Routing and Navigation. This project aims to develop new efficient techniques for mixed-initiative routing in large transportation networks. Current state-of-the-art techniques for real-world journey planning take user requirements as input and generate a few proposed journeys as output. However, the most useful decision-support systems are mixed-initiative: the Information Technology (IT) system and user work together to find the best decisions. In the context of journey planning, interaction with the user is needed to find the best combination of private, public and active transportation; understand trade-offs between cost, starting time, journey time, convenience and reliability; and react to delays and disruptions. This project aims to develop dynamic decision-support systems that will help travellers reach their destinations cheaper, faster and more conveniently.Read moreRead less
Autonomous Functions for Smart Cars. The aim of this project is to develop autonomous functions for smart cars, such as lane departure warning, driver fatigue warning, and automatic lane following. Every year 70,000 people are killed in road accidents, 95% of which can be attributed to driver error. The potential outcomes of this project therefore significant. Many of the theoretical methods required for this project have been developed by our group. However, further theoretical refinements fo ....Autonomous Functions for Smart Cars. The aim of this project is to develop autonomous functions for smart cars, such as lane departure warning, driver fatigue warning, and automatic lane following. Every year 70,000 people are killed in road accidents, 95% of which can be attributed to driver error. The potential outcomes of this project therefore significant. Many of the theoretical methods required for this project have been developed by our group. However, further theoretical refinements followed by experimental verification is necessary. For smart cars to be accepted, the systems must be demonstrated to be reliable and to operate in a wide range of conditions.Read moreRead less
Visual tracking of multiple objects: A stochastic geometrical approach. Reliable real-time visual multiple-object tracking techniques will open up new applications that enhance the quality of life such as driving safety, traffic monitoring, home security, security and surveillance of public facilities. These new applications have huge commercial potentials, and the technology developed from this project will provide the catalyst for vibrant new industries to grow. In addition, the expertise deve ....Visual tracking of multiple objects: A stochastic geometrical approach. Reliable real-time visual multiple-object tracking techniques will open up new applications that enhance the quality of life such as driving safety, traffic monitoring, home security, security and surveillance of public facilities. These new applications have huge commercial potentials, and the technology developed from this project will provide the catalyst for vibrant new industries to grow. In addition, the expertise developed from the project will provide a competitive edge for Australian industries in aerospace, oceanography, robotics, remote sensing, and biomedical engineering. Read moreRead less
A Novel System for Surveillance of Moving Objects. Surveillance of moving objects is critical in numerous applications such as detection and recognition of motor vehicles. It is important for detection to be fast and accurate with low cost. In this project, we aim to implement a surveillance system consisting of an efficient algorithm on a PC network with a camera. Our detection algorithm will be achieved with an advanced and computationally powerful image representation for fast computation. It ....A Novel System for Surveillance of Moving Objects. Surveillance of moving objects is critical in numerous applications such as detection and recognition of motor vehicles. It is important for detection to be fast and accurate with low cost. In this project, we aim to implement a surveillance system consisting of an efficient algorithm on a PC network with a camera. Our detection algorithm will be achieved with an advanced and computationally powerful image representation for fast computation. Its accuracy will be enhanced by adapting a well recognized theory for fast removal of image noise. Our implementation on the PC network will provide a flexible and extensible platform for parallel computing to further reduce detection time while keeping costs low.Read moreRead less
AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing n ....AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing novel deep learning algorithms. The new algorithms will benefit a wide range of applications, e.g. to effectively use car crash training samples for accurately identifying potential road crashes in transport and to effectively use rare medical imaging training data for robustly diagnosing diseases in health.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
Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-s ....Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-supervised learning that are robust to failures and provide explainable decisions for object detection and scene segmentation. The outcomes are expected to advance theory in robust deep learning and benefit 3D mapping, surveying, infrastructure monitoring, transport and robotics industries.Read moreRead less
Optimising train driver vigilance system: reactivation of a fatigued driver. Fatigue poses frequent problems in train drivers. The repetitive nature of the train-driving task is a precursor of fatigue. This application proposes a novel design concept for the current train driver vigilance system manufactured by our industry partner. The proposed new vigilance system will not only assure that the driver is awake by warning of fatigue states, but will also act as an important cue in the control of ....Optimising train driver vigilance system: reactivation of a fatigued driver. Fatigue poses frequent problems in train drivers. The repetitive nature of the train-driving task is a precursor of fatigue. This application proposes a novel design concept for the current train driver vigilance system manufactured by our industry partner. The proposed new vigilance system will not only assure that the driver is awake by warning of fatigue states, but will also act as an important cue in the control of the train. Incorporating fatigue detection in the vigilance monitor is of commercial value to our industry partner. Furthermore, this study will help improve the safety culture of the railway environment.Read moreRead less
Advanced techniques for imaging radar interferometry. The Earth's surface is changing all the time, both slowly and dramatically, due to activities such as groundwater extraction, underground mining and earthquakes. This project will develop advanced, cost-effective and accurate imaging radar techniques that can measure subtle surface changes frequently, in order to safeguard significant infrastructure.