Detection and classification of road signs in natural environments

An automatic road sign recognition system first locates road signs within images captured by an imaging sensor on-board of a vehicle, and then identifies the detected road signs. This paper presents an automatic neural-network-based road sign recognition system. First, a study of the existing road sign recognition research is presented. In this study, the issues associated with automatic road sign recognition are described, the existing methods developed to tackle the road sign recognition problem are reviewed, and a comparison of the features of these methods is given. Second, the developed road sign recognition system is described. The system is capable of analysing live colour road scene images, detecting multiple road signs within each image, and classifying the type of road signs detected. The system consists of two modules: detection and classification. The detection module segments the input image in the hue-saturation-intensity colour space, and then detects road signs using a Multi-layer Perceptron neural-network. The classification module determines the type of detected road signs using a series of one to one architectural Multi-layer Perceptron neural networks. Two sets of classifiers are trained using the Resillient-Backpropagation and Scaled-Conjugate-Gradient algorithms. The two modules of the system are evaluated individually first. Then the system is tested as a whole. The experimental results demonstrate that the system is capable of achieving an average recognition hit-rate of 95.96% using the scaled-conjugate-gradient trained classifiers.

Road-sign identification using ensemble learning

Ensemble learning that combines the decisions of multiple weak classifiers to from an output, has recently emerged as an effective identification method. This paper presents a road-sign identification system based upon the ensemble learning approach. The system identifies the regions of interest that are extracted from the scene into the road-sign groups that they belong to. A large road-sign image dataset is formed and used to train and test the system. Fifteen groups of road signs are chosen for identification. Five experiments are performed and the results are presented and discussed.

Early symptomatic presbyopes - what correction modality works best?

Purpose: To compare the performance of a low-addition silicone hydrogel multifocal soft lens with other soft lens correction options in a group of habitual soft lens wearers of distance correction who are symptomatic of early presbyopia.

Method: This clinical study was designed as a prospective, double-masked, randomized, crossover, dispensing trial consisting of four 1-week phases, one for each of the correction modalities: a low-addition silicone hydrogel multifocal soft lens, monovision, habitual correction, and optimized distance visual correction. The prescriptions of all modalities were finalized at a single fitting visit, and the lenses were worn according to a randomized schedule. All lenses were made from lotrafilcon B material. A series of objective vision tests were conducted: high- and low-contrast LogMAR under high- and low-room lighting conditions, stereopsis, and critical print size. A number of other data collection methods used were novel: some data were collected under controlled laboratory-based conditions and others under real-world conditions, some of which were completed on a BlackBerry hand-held communication device.

Results: All participants were able to be fit with all four correction modalities. Objective vision tests showed no statistical difference between the lens modalities except in the case of low-contrast near LogMAR acuity under low-lighting levels where monovision (+0.29 ± 0.10) performed better than the multifocal (+0.33 ± 0.11, P=0.027) and the habitual (+0.37 ± 0.12, P<0.001) modalities. Subjective ratings indicated a statistically better performance provided by the multifocal correction compared with monovision, particularly for the vision associated with driving tasks such as driving during the daytime (93.3 ± 8.8 vs. 84.2 ± 23.7, P=0.05), at nighttime (88.8 ± 11.7 vs. 74.9 ± 23.6, P=0.001), any associated haloes or glare (92.0 ± 10.6 vs. 78.0 ± 22.8, P=0.003), and observing road signs (90.1 ± 11.8 vs. 79.4 ± 20.2, P=0.027). Preference for the multifocal compared with monovision was also reported when watching television (95.0 ± 6.4 vs. 82.6 ± 20.1, P=0.001) and when changing focus from distance to near (87.0 ± 13.4 vs. 66.1 ± 32.2, P<0.001).

Conclusions: For this group of early presbyopes, the AIR OPTIX AQUA MULTIFOCAL-Low Add provided a successful option for visual correction, which was supported by the results of subjective ratings, many of which were made during or immediately after performing such activities as reading, using a computer, watching television, and driving. These results suggest that making a prediction of success or not based on consulting room acuity tests alone is probably unwise.

Hybrid life-cycle inventory for road construction and use

Life-cycle assessment (LCA) is a technique that is used worldwide by clients and their design team to assess the impact of
their projects on the environment. The main advantage of LCA is in supporting decision making with quantitative data. LCA inventories
can be either fully developed or streamlined. Fully developed LCAs are time-consuming and costly to prepare. Streamlined LCAs can be
used as an effective decision-making tool when considering environmental performance during the design process, but with a loss of
inventory completeness. Acknowledging the advantages and disadvantages of both types of LCA, this paper proposes a hybrid LCA
method that uses input-output data to fill in those gaps routinely left in conventional LCA inventories.

The long and winding road : the development of a comprehensive, adequate and representative system of highly protected marine protected areas in Victoria, Australia

In 2002, the state of Victoria, Australia increased its “no-take” marine protected areas (MPAs) 100 fold to cover over 5% of its coastal waters in a comprehensive, adequate and representative system of marine national parks and sanctuaries. Given the ambitious targets set for MPA establishment globally in 2003 at the World Summit for Sustainable Development this apparently remarkable achievement could be an example to other nations and states attempting to establish substantial MPA systems.

This paper describes and discusses the factors that contributed to the establishment of the Victorian system and the relevance of these factors to other jurisdictions.

The road to internet banking: understanding emerging customer issues

This paper presents findings from an empirical study of banking customer experiences with the adoption of Internet banking. Using a qualitative, interpretive grounded theory approach and single and group interviews, the study explores customer perceptions and experiences and provides an understanding of how and why specific factors affect their decision whether or not to bank on the Internet in the current era. The findings are used to develop a theoretical framework which conceptualizes and links consumer issues influencing the adoption of this application, and we also provide a set of recommendations for banks. Specifically, the findings suggest that convenience – in particular, time savings – is the major motivator to bank on the Internet, while there are a range of other influential factors which could be modulated by banks. The results also highlight increasing online risk acceptance by customers and the growing importance of deep levels of customer support for online services. Key gender differences in attitudes to Internet banking are highlighted. This study suggests that organizations will improve their management of customer attitudes to new Internet service applications by understanding the need to proactively address customer fears and misconceptions about the technologies involved.

At home on the road? Can drivers' relationships with their cars be associated with territoriality?

The current research explores the relationship between people and their cars within the framework of Altman's theory of human territoriality. It further develops the research of Sandqvist by examining the descriptions given by people with differing ownership and uses of their cars and exploring the congruence between these and the characteristics used to describe human territories. Thirteen focus groups were held with young drivers between the ages of 18 and 25 years, drivers over the age of 25 who are parents of pre-license age children, drivers over the age of 25 who do not regularly transport children, and drivers of work vehicles. Analyses of discussions revealed that drivers’ descriptions of the relationship with their car could be matched with Brown and Altman's descriptions of territory types. However, variations existed both between and within individuals as to the application of the labels ‘primary’, ‘secondary’ and ‘public’ territory to the car. Implications for the understanding of road user behaviour and the further development of theory on the car as a place or an object in terms of territoriality are discussed.