Evaluating automatic road detection across a large aerial imagery collection

The automated extraction of roads from aerial imagery can be of value for tasks including mapping, surveillance and change detection. Unfortunately, there are no public databases or standard evaluation protocols for evaluating these techniques. Many techniques are further hindered by a reliance on manual initialisation, making large scale application of the techniques impractical. In this paper, we present a public database and evaluation protocol for the evaluation of road extraction algorithms, and propose an improved automatic seed finding technique to initialise road extraction, based on a combination of geometric and colour features.

Computational approaches to the visual validation of 3D virtual environments

Virtual environments can provide, through digital games and online social interfaces, extremely exciting forms of interactive entertainment. Because of their capability in displaying and manipulating information in natural and intuitive ways, such environments have found extensive applications in decision support, education and training in the health and science domains amongst others. Currently, the burden of validating both the interactive functionality and visual consistency of a virtual environment content is entirely carried out by developers and play-testers. While considerable research has been conducted in assisting the design of virtual world content and mechanics, to date, only limited contributions have been made regarding the automatic testing of the underpinning graphics software and hardware. The aim of this thesis is to determine whether the correctness of the images generated by a virtual environment can be quantitatively defined, and automatically measured, in order to facilitate the validation of the content. In an attempt to provide an environment-independent definition of visual consistency, a number of classification approaches were developed. First, a novel model-based object description was proposed in order to enable reasoning about the color and geometry change of virtual entities during a play-session. From such an analysis, two view-based connectionist approaches were developed to map from geometry and color spaces to a single, environment-independent, geometric transformation space; we used such a mapping to predict the correct visualization of the scene. Finally, an appearance-based aliasing detector was developed to show how incorrectness too, can be quantified for debugging purposes. Since computer games heavily rely on the use of highly complex and interactive virtual worlds, they provide an excellent test bed against which to develop, calibrate and validate our techniques. Experiments were conducted on a game engine and other virtual worlds prototypes to determine the applicability and effectiveness of our algorithms. The results show that quantifying visual correctness in virtual scenes is a feasible enterprise, and that effective automatic bug detection can be performed through the techniques we have developed. We expect these techniques to find application in large 3D games and virtual world studios that require a scalable solution to testing their virtual world software and digital content.

Combined time- and space-resolved Raman spectrometer for the non-invasive depth profiling of chemical hazards

A time-resolved inverse spatially offset Raman spectrometer was constructed for depth profiling of Raman-active substances under both the lab and the field environments. The system operating principles and performance are discussed along with its advantages relative to traditional continuous wave spatially offset Raman spectrometer. The developed spectrometer uses a combination of space- and time-resolved detection in order to obtain high-quality Raman spectra from substances hidden behind coloured opaque surface layers, such as plastic and garments, with a single measurement. The time-gated spatially offset Raman spectrometer was successfully used to detect concealed explosives and drug precursors under incandescent and fluorescent background light as well as under daylight. The average screening time was 50 s per measurement. The excitation energy requirements were relatively low (20 mW) which makes the probe safe for screening hazardous substances. The unit has been designed with nanosecond laser excitation and gated detection, making it of lower cost and complexity than previous picosecond-based systems, to provide a functional platform for in-line or in-field sensing of chemical substances.

Deep Raman spectroscopy for the non-invasive standoff detection of concealed chemical threat agents

Deep Raman spectroscopy has been utilized for the standoff detection of concealed chemical threat agents from a distance of 15 meters under real life background illumination conditions. By using combined time and space resolved measurements, various explosive precursors hidden in opaque plastic containers were identified non-invasively. Our results confirm that combined time and space resolved Raman spectroscopy leads to higher selectivity towards the sub-layer over the surface layer as well as enhanced rejection of fluorescence from the container surface when compared to standoff spatially offset Raman spectroscopy. Raman spectra that have minimal interference from the packaging material and good signal-to-noise ratio were acquired within 5 seconds of measurement time. A new combined time and space resolved Raman spectrometer has been designed with nanosecond laser excitation and gated detection, making it of lower cost and complexity than picosecond-based laboratory systems.

An integrated approach for precise road reconstruction from aerial imagery and LiDAR data

Accurate and detailed road models play an important role in a number of geospatial applications, such as infrastructure planning, traffic monitoring, and driver assistance systems. In this thesis, an integrated approach for the automatic extraction of precise road features from high resolution aerial images and LiDAR point clouds is presented. A framework of road information modeling has been proposed, for rural and urban scenarios respectively, and an integrated system has been developed to deal with road feature extraction using image and LiDAR analysis. For road extraction in rural regions, a hierarchical image analysis is first performed to maximize the exploitation of road characteristics in different resolutions. The rough locations and directions of roads are provided by the road centerlines detected in low resolution images, both of which can be further employed to facilitate the road information generation in high resolution images. The histogram thresholding method is then chosen to classify road details in high resolution images, where color space transformation is used for data preparation. After the road surface detection, anisotropic Gaussian and Gabor filters are employed to enhance road pavement markings while constraining other ground objects, such as vegetation and houses. Afterwards, pavement markings are obtained from the filtered image using the Otsu's clustering method. The final road model is generated by superimposing the lane markings on the road surfaces, where the digital terrain model (DTM) produced by LiDAR data can also be combined to obtain the 3D road model. As the extraction of roads in urban areas is greatly affected by buildings, shadows, vehicles, and parking lots, we combine high resolution aerial images and dense LiDAR data to fully exploit the precise spectral and horizontal spatial resolution of aerial images and the accurate vertical information provided by airborne LiDAR. Objectoriented image analysis methods are employed to process the feature classiffcation and road detection in aerial images. In this process, we first utilize an adaptive mean shift (MS) segmentation algorithm to segment the original images into meaningful object-oriented clusters. Then the support vector machine (SVM) algorithm is further applied on the MS segmented image to extract road objects. Road surface detected in LiDAR intensity images is taken as a mask to remove the effects of shadows and trees. In addition, normalized DSM (nDSM) obtained from LiDAR is employed to filter out other above-ground objects, such as buildings and vehicles. The proposed road extraction approaches are tested using rural and urban datasets respectively. The rural road extraction method is performed using pan-sharpened aerial images of the Bruce Highway, Gympie, Queensland. The road extraction algorithm for urban regions is tested using the datasets of Bundaberg, which combine aerial imagery and LiDAR data. Quantitative evaluation of the extracted road information for both datasets has been carried out. The experiments and the evaluation results using Gympie datasets show that more than 96% of the road surfaces and over 90% of the lane markings are accurately reconstructed, and the false alarm rates for road surfaces and lane markings are below 3% and 2% respectively. For the urban test sites of Bundaberg, more than 93% of the road surface is correctly reconstructed, and the mis-detection rate is below 10%.

SAIVT-QUT@TRECVid 2012 : interactive surveillance event detection

In this paper, we propose an approach which attempts to solve the problem of surveillance event detection, assuming that we know the definition of the events. To facilitate the discussion, we first define two concepts. The event of interest refers to the event that the user requests the system to detect; and the background activities are any other events in the video corpus. This is an unsolved problem due to many factors as listed below: 1) Occlusions and clustering: The surveillance scenes which are of significant interest at locations such as airports, railway stations, shopping centers are often crowded, where occlusions and clustering of people are frequently encountered. This significantly affects the feature extraction step, and for instance, trajectories generated by object tracking algorithms are usually not robust under such a situation. 2) The requirement for real time detection: The system should process the video fast enough in both of the feature extraction and the detection step to facilitate real time operation. 3) Massive size of the training data set: Suppose there is an event that lasts for 1 minute in a video with a frame rate of 25fps, the number of frames for this events is 60X25 = 1500. If we want to have a training data set with many positive instances of the event, the video is likely to be very large in size (i.e. hundreds of thousands of frames or more). How to handle such a large data set is a problem frequently encountered in this application. 4) Difficulty in separating the event of interest from background activities: The events of interest often co-exist with a set of background activities. Temporal groundtruth typically very ambiguous, as it does not distinguish the event of interest from a wide range of co-existing background activities. However, it is not practical to annotate the locations of the events in large amounts of video data. This problem becomes more serious in the detection of multi-agent interactions, since the location of these events can often not be constrained to within a bounding box. 5) Challenges in determining the temporal boundaries of the events: An event can occur at any arbitrary time with an arbitrary duration. The temporal segmentation of events is difficult and ambiguous, and also affected by other factors such as occlusions.

Design and modeling of collaboration architecture for security

Threats against computer networks evolve very fast and require more and more complex measures. We argue that teams respectively groups with a common purpose for intrusion detection and prevention improve the measures against rapid propagating attacks similar to the concept of teams solving complex tasks known from field of work sociology. Collaboration in this sense is not easy task especially for heterarchical environments. We propose CIMD (collaborative intrusion and malware detection) as a security overlay framework to enable cooperative intrusion detection approaches. Objectives and associated interests are used to create detection groups for exchange of security-related data. In this work, we contribute a tree-oriented data model for device representation in the scope of security. We introduce an algorithm for the formation of detection groups, show realization strategies for the system and conduct vulnerability analysis. We evaluate the benefit of CIMD by simulation and probabilistic analysis.

An Android application sandbox system for suspicious software detection

Smartphones are steadily gaining popularity, creating new application areas as their capabilities increase in terms of computational power, sensors and communication. Emerging new features of mobile devices give opportunity to new threats. Android is one of the newer operating systems targeting smartphones. While being based on a Linux kernel, Android has unique properties and specific limitations due to its mobile nature. This makes it harder to detect and react upon malware attacks if using conventional techniques. In this paper, we propose an Android Application Sandbox (AASandbox) which is able to perform both static and dynamic analysis on Android programs to automatically detect suspicious applications. Static analysis scans the software for malicious patterns without installing it. Dynamic analysis executes the application in a fully isolated environment, i.e. sandbox, which intervenes and logs low-level interactions with the system for further analysis. Both the sandbox and the detection algorithms can be deployed in the cloud, providing a fast and distributed detection of suspicious software in a mobile software store akin to Google's Android Market. Additionally, AASandbox might be used to improve the efficiency of classical anti-virus applications available for the Android operating system.

Teams rather than individuals : collaborative intrusion detection

We propose CIMD (Collaborative Intrusion and Malware Detection), a scheme for the realization of collaborative intrusion detection approaches. We argue that teams, respectively detection groups with a common purpose for intrusion detection and response, improve the measures against malware. CIMD provides a collaboration model, a decentralized group formation and an anonymous communication scheme. Participating agents can convey intrusion detection related objectives and associated interests for collaboration partners. These interests are based on intrusion objectives and associated interests for collaboration partners. These interests are based on intrusion detection related ontology, incorporating network and hardware configurations and detection capabilities. Anonymous Communication provided by CIMD allows communication beyond suspicion, i.e. the adversary can not perform better than guessing an IDS to be the source of a message at random. The evaluation takes place with the help of NeSSi² (www.nessi2.de), the Network Security Simulator, a dedicated environment for analysis of attacks and countermeasures in mid-scale and large-scale networks. A CIMD prototype is being built based on the JIAC agent framework(www.jiac.de).

Reducing alcohol-related driving on China's roads : Traffic police officers' perceptions and practice

Alcohol-related driving is a longstanding, serious problem in China (Li, Xie, Nie, & Zhang, 2012). On 1st May, 2011 a national law was introduced to criminalize drunk driving, and imposed serious penalties including jail for driving with a blood alcohol level of above 80mg/100ml. This pilot study, undertaken a year after introduction of the law, sought traffic police officers’ perceptions of drink driving and the practice of breath alcohol testing (BAT) in a large city in Guangdong Province, southern China. A questionnaire survey and semi-structured interviews were used to gain an in-depth understanding of issues relevant to alcohol-related driving. Fifty-five traffic police officers were recruited for the survey and six traffic police officers with a variety of working experience including roadside alcohol breath testing, traffic crash investigation and police resourcing were interviewed individually. The officers were recruited by the first author with the assistance of the staff from Guangdong Institute of Public Health, Centre for Disease Control and Prevention (CDC). Interview participants reported three primary reasons why people drink and drive: 1) being prepared to take the chance of not being apprehended by police; 2) the strong traditional Chinese drinking culture; and 3) insufficient public awareness about the harmfulness of drink driving. Problems associated with the process of breath alcohol testing (BAT) were described and fit broadly into two categories: resourcing and avoiding detection. It was reported that there were insufficient traffic police officers to conduct routine traffic policing, including alcohol testing. Police BAT equipment was considered sufficient for routine traffic situations but not highway traffic operations. Local media and posters are used by the Public Security Bureau which is responsible for education about safe driving but participants thought that the education campaigns are limited in scope. Participants also described detection avoidance strategies used by drivers including: changing route; ignoring a police instruction to stop; staying inside the vehicle with windows and doors locked to avoid being tested; intentionally not performing breath tests correctly; and arguing with officers. This pilot study provided important insights from traffic police in one Chinese city which suggest there may be potential unintended effects of introducing more severe penalties including a range of strategies reportedly used by drivers to avoid detection. Recommendations for future research include a larger study to confirm these findings and examine the training and education of drivers; the focus and reach of publicity; and possible resource needs to support police enforcement.

A practical comparison of manual and autonomous methods for acoustic monitoring

1. Autonomous acoustic recorders are widely available and can provide a highly efficient method of species monitoring, especially when coupled with software to automate data processing. However, the adoption of these techniques is restricted by a lack of direct comparisons with existing manual field surveys. 2. We assessed the performance of autonomous methods by comparing manual and automated examination of acoustic recordings with a field-listening survey, using commercially available autonomous recorders and custom call detection and classification software. We compared the detection capability, time requirements, areal coverage and weather condition bias of these three methods using an established call monitoring programme for a nocturnal bird, the little spotted kiwi(Apteryx owenii). 3. The autonomous recorder methods had very high precision (>98%) and required <3% of the time needed for the field survey. They were less sensitive, with visual spectrogram inspection recovering 80% of the total calls detected and automated call detection 40%, although this recall increased with signal strength. The areal coverage of the spectrogram inspection and automatic detection methods were 85% and 42% of the field survey. The methods using autonomous recorders were more adversely affected by wind and did not show a positive association between ground moisture and call rates that was apparent from the field counts. However, all methods produced the same results for the most important conservation information from the survey: the annual change in calling activity. 4. Autonomous monitoring techniques incur different biases to manual surveys and so can yield different ecological conclusions if sampling is not adjusted accordingly. Nevertheless, the sensitivity, robustness and high accuracy of automated acoustic methods demonstrate that they offer a suitable and extremely efficient alternative to field observer point counts for species monitoring.

Development of a rapid and validated method for investigating the metabolism of scoparone in rat using ultra-performance liquid chromatography/electrospray ionization quadruple time-of-flight mass spectrometry

Scoparone (6,7-dimethoxycoumarin) is known to have a wide range of pharmacological properties. In this study, a rapid and validated ultra-performance liquid chromatography/electrospray ionization quadruple time-of-flight mass spectrometry (UPLC/ESI-QTof-MS) method was developed to investigate the metabolism of scoparone in rat for the first time. The new method reduced the sample handling and analytical time by three- to six-fold, and the detection limit by five- to 1000-fold, compared to published methods. Far more metabolites were detected and identified compared to published data, which were preliminarily identified as scopoletin, isoscopoletin, isofraxidin, and fraxidin, respectively, when subjected to tandem mass spectrometry analyses. It is found that the metabolic trajectory of scoparone in rat focused on phase I metabolism which is obviously different from published results, and revealed a wide range of pharmacological properties of scoparone partly attributed to the bioactivities of its metabolites.

Ozone-induced dissociation of conjugated lipids reveals significant reaction rate enhancements and characteristic odd-electron product ions

Ozone-induced dissociation (OzID) is an alternative ion activation method that relies on the gas phase ion-molecule reaction between a mass-selected target ion and ozone in an ion trap mass spectrometer. Herein, we evaluated the performance of OzID for both the structural elucidation and selective detection of conjugated carbon-carbon double bond motifs within lipids. The relative reactivity trends for \[M + X](+) ions (where X = Li, Na, K) formed via electrospray ionization (ESI) of conjugated versus nonconjugated fatty acid methyl esters (FAMEs) were examined using two different OzID-enabled linear ion-trap mass spectrometers. Compared with nonconjugated analogues, FAMEs derived from conjugated linoleic acids were found to react up to 200 times faster and to yield characteristic radical cations. The significantly enhanced reactivity of conjugated isomers means that OzID product ions can be observed without invoking a reaction delay in the experimental sequence (i.e., trapping of ions in the presence of ozone is not required). This possibility has been exploited to undertake neutral-loss scans on a triple quadrupole mass spectrometer targeting characteristic OzID transitions. Such analyses reveal the presence of conjugated double bonds in lipids extracted from selected foodstuffs. Finally, by benchmarking of the absolute ozone concentration inside the ion trap, second order rate constants for the gas phase reactions between unsaturated organic ions and ozone were obtained. These results demonstrate a significant influence of the adducting metal on reaction rate constants in the fashion Li > Na > K.

The impact of viral respiratory infection on the severity and recovery from an asthma exacerbation

Background Viral respiratory illness triggers asthma exacerbations, but the influence of respiratory illness on the acute severity and recovery of childhood asthma is unknown. Our objective was to evaluate the impact of a concurrent acute respiratory illness (based on a clinical definition and PCR detection of a panel of respiratory viruses, Mycoplasma pneumoniae and Chlamydia pneumoniae) on the severity and resolution of symptoms in children with a nonhospitalized exacerbation of asthma. Methods Subjects were children aged 2 to 15 years presenting to an emergency department for an acute asthma exacerbation and not hospitalized. Acute respiratory illness (ARI) was clinically defined. Nasopharyngeal aspirates (NPA) were examined for respiratory viruses, Chlamydia and Mycoplasma using PCR. The primary outcome was quality of life (QOL) on presentation, day 7 and day 14. Secondary outcomes were acute asthma severity score, asthma diary, and cough diary scores on days 5, 7,10, and 14. Results On multivariate regression, presence of ARI was statistically but not clinically significantly associated with QOL score on presentation (B = 0.36, P = 0.025). By day 7 and 14, there was no difference between groups. Asthma diary score was significantly higher in children with ARI (B = 0.41, P = 0.039) on day 5 but not on presentation or subsequent days. Respiratory viruses were detected in 54% of the 78 NPAs obtained. There was no difference in the any of the asthma outcomes of children grouped by positive or negative NPA. Conclusions The presence of a viral respiratory illness has a modest influence on asthma severity, and does not influence recovery from a nonhospitalized asthma exacerbation.

Quantitative stem-loop RT-PCR for detection of microRNAs

Plant microRNAs (miRNAs) are a class of endogenous small RNAs that are essential for plant development and survival. They arise from larger precursor RNAs with a characteristic hairpin structure and regulate gene activity by targeting mRNA transcripts for cleavage or translational repression. Efficient and reliable detection and quantification of miRNA expression has become an essential step in understanding their specific roles. The expression levels of miRNAs can vary dramatically between samples and they often escape detection by conventional technologies such as cloning, northern hybridization and microarray analysis. The stem-loop RT-PCR method described here is designed to detect and quantify mature miRNAs in a fast, specific, accurate and reliable manner. First, a miRNA-specific stem-loop RT primer is hybridized to the miRNA and then reverse transcribed. Next, the RT product is amplified and monitored in real time using a miRNA-specific forward primer and the universal reverse primer. This method enables miRNA expression profiling from as little as 10 pg of total RNA and is suitable for high-throughput miRNA expression analysis.