Efficient road detection and tracking for unmanned aerial vehicle

Abstract - An unmanned aerial vehicle (UAV) has many applications in a variety of fields. Detection and tracking of a specific road in UAV videos play an important role in automatic UAV navigation, traffic monitoring, and ground–vehicle tracking, and also is very helpful for constructing road networks for modeling and simulation. In this paper, an efficient road detection and tracking framework in UAV videos is proposed. In particular, a graph-cut–based detection approach is given to accurately extract a specified road region during the initialization stage and in the middle of tracking process, and a fast homography-based road-tracking scheme is developed to automatically track road areas. The high efficiency of our framework is attributed to two aspects: the road detection is performed only when it is necessary and most work in locating the road is rapidly done via very fast homography-based tracking. Experiments are conducted on UAV videos of real road scenes we captured and downloaded from the Internet. The promising results indicate the effectiveness of our proposed framework, with the precision of 98.4% and processing 34 frames per second for 1046 x 595 videos on average.

Vehicle motion simulators, a key step towards road vehicle dynamics improvement

Real road vehicle tests are time consuming, laborious, and costly, and involve several safety concerns. Road vehicle motion simulators (RVMS) could assist with vehicle testing, and eliminate or reduce the difficulties traditionally associated with conducting vehicle tests. However, such simulators must exhibit a high level of fidelity and accuracy in order to provide realistic and reliable outcomes. In this paper, we review existing RVMS and discuss each of the major RVMS subsystems related to the research and development of vehicle dynamics. The possibility of utilising motion simulators to conduct ride and handling test scenarios is also investigated.

Extending light-weighting and mass-production of ultra high strength steels via condition-based maintenance

The use of ultra high strength steels (UHSS) in the automotive industry presents a significant opportunity for continued vehicle light-weighting, due to possible strength-to-weight improvements of three to four times that of conventional sheet steel grades. This performance benefit is achievable whist maintaining most of the advantages of low-cost mass-production associated with the cold stamping of sheet steel for automotive body components. However, the introduction of UHSS can result in significantly increased wear of the stamping tools, which is difficult to predict at the design stage and can lead to unexpected process failure during mass-production. Therefore, there is a need to be able to monitor and predict the onset of severe wear, such that the best course of condition-based maintenance can be scheduled and unscheduled stoppages due to tool wear eradicated. This paper describes a novel active monitoring system that is being developed by researchers at Deakin University, The Australian National University and Ford Motor Company, Asia Pacific and Africa. The aim of the active monitoring system is to detect the initial onset of a change of state, such as wear, through the measurement of variables such as punch force and audio signals. A semi-industrial stamping process, using a progressive die setup and high strength steel sheet with hardened tool steel tooling, is the experimental basis for the initial model and system development.

The Production of novel structures from high strength and ultrafine-grained sheet metal through roll forming.

This work addresses the development of new ultra-fine grained/ nano-structured high strength aluminium alloys designed for automotive applications and explores the frontiers of the roll forming process.