Rapid yet accurate speech indexing using dynamic match lattice spotting

The support for typically out-of-vocabulary query terms such as names, acronyms, and foreign words is an important requirement of many speech indexing applications. However, to date many unrestricted vocabulary indexing systems have struggled to provide a balance between good detection rate and fast query speeds. This paper presents a fast and accurate unrestricted vocabulary speech indexing technique named Dynamic Match Lattice Spotting (DMLS). The proposed method augments the conventional lattice spotting technique with dynamic sequence matching, together with a number of other novel algorithmic enhancements, to obtain a system that is capable of searching hours of speech in seconds while maintaining excellent detection performance

Localization and place recognition using an ultra-wide band (UWB) radar

This paper presents an approach to mobile robot localization, place recognition and loop closure using a monostatic ultra-wide band (UWB) radar system. The UWB radar is a time-of-flight based range measurement sensor that transmits short pulses and receives reflected waves from objects in the environment. The main idea of the poposed localization method is to treat the received waveform as a signature of place. The resulting echo waveform is very complex and highly depends on the position of the sensor with respect to surrounding objects. On the other hand, the sensor receives similar waveforms from the same positions.Moreover, the directional characteristics of dipole antenna is almost omnidirectional. Therefore, we can localize the sensor position to find similar waveform from waveform database. This paper proposes a place recognitionmethod based on waveform matching, presents a number of experiments that illustrate the high positon estimation accuracy of our UWB radar-based localization system, and shows the resulting loop detection performance in a typical indoor office environment and a forest.

Place categorization and semantic mapping on a mobile robot

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot with-out environment-specific training. Motivated by their ongoing success in various visual recognition tasks, we build our system upon a state-of-the-art convolutional network. We overcome its closed-set limitations by complementing the network with a series of one-vs-all classifiers that can learn to recognize new semantic classes online. Prior domain knowledge is incorporated by embedding the classification system into a Bayesian filter framework that also ensures temporal coherence. We evaluate the classification accuracy of the system on a robot that maps a variety of places on our campus in real-time. We show how semantic information can boost robotic object detection performance and how the semantic map can be used to modulate the robot’s behaviour during navigation tasks. The system is made available to the community as a ROS module.

Differential effects of monotony versus fatigue on driving performance and the effectiveness of various detection methods : implications for road safety in the ACT

Background Situational driving factors, including fatigue, distraction, inattention and monotony, are recognised killers in Australia, contributing to an estimated 40% of fatal crashes and 34% of all crashes . More often than not the main contributing factor is identified as fatigue, yet poor driving performance has been found to emerge early in monotonous conditions, independent of fatigue symptoms and time on task. This early emergence suggests an important role for monotony. However, much road safety research suggests that monotony is solely a task characteristic that directly causes fatigue and associated symptoms and there remains an absence of consistent evidence explaining the relationship. Objectives We report an experimental study designed to disentangle the characteristics and effects of monotony from those associated with fatigue. Specifically, we examined whether poor driving performance associated with hypovigilance emerges as a consequence of monotony, independent of fatigue. We also examined whether monotony is a multidimensional construct, determined by environmental characteristics and/or task demands that independently moderate sustained attention and associated driving performance. Method Using a driving simulator, participants completed four, 40 minute driving scenarios. The scenarios varied in the degree of monotony as determined by the degree of variation in road design (e.g., straight roads vs. curves) and/or road side scenery. Fatigue, as well as a number of other factors known to moderate vigilance and driving performance, was controlled for. To track changes across time, driving performance was assessed in five minute time periods using a range of behavioural, subjective and physiological measures, including steering wheel movements, lane positioning, electroencephalograms, skin conductance, and oculomotor activity. Results Results indicate that driving performance is worse in monotonous driving conditions characterised by low variability in road design. Critically, performance decrements associated with monotony emerge very early, suggesting monotony effects operate independent of fatigue. Conclusion Monotony is a multi-dimensional construct where, in a driving context, roads containing low variability in design are monotonous and those high in variability are non-monotonous. Importantly, low variability in road side scenery does not appear to exacerbate monotony or associated poor performance. However, high variability in road side scenery can act as a distraction and impair sustained attention and poor performance when driving on monotonous roads. Furthermore, high sensation seekers seem to be more susceptible to distraction when driving on monotonous roads. Implications of our results for the relationship between monotony and fatigue, and the possible construct-specific detection methods in a road safety context, will be discussed.

Evaluation of the performance of a dengue outbreak detection tool for China

An outbreak detection and response system, using time series moving percentile method based on historical data, in China has been used for identifying dengue fever outbreaks since 2008. For dengue fever outbreaks reported from 2009 to 2012, this system achieved a sensitivity of 100%, a specificity of 99.8% and a median time to detection of 3 days, which indicated that the system was a useful decision tool for dengue fever control and risk-management programs in China.

Study on the method of freeway incident detection using wireless positioning terminal

Improving the performance of a incident detection system was essential to minimize the effect of incidents. A new method of incident detection was brought forward in this paper based on an in-car terminal which consisted of GPS module, GSM module and control module as well as some optional parts such as airbag sensors, mobile phone positioning system (MPPS) module, etc. When a driver or vehicle discovered the freeway incident and initiated an alarm report the incident location information located by GPS, MPPS or both would be automatically send to a transport management center (TMC), then the TMC would confirm the accident with a closed-circuit television (CCTV) or other approaches. In this method, detection rate (DR), time to detect (TTD) and false alarm rate (FAR) were more important performance targets. Finally, some feasible means such as management mode, education mode and suitable accident confirming approaches had been put forward to improve these targets.

Improved detection and tracking of objects in surveillance video

Surveillance networks are typically monitored by a few people, viewing several monitors displaying the camera feeds. It is then very difficult for a human operator to effectively detect events as they happen. Recently, computer vision research has begun to address ways to automatically process some of this data, to assist human operators. Object tracking, event recognition, crowd analysis and human identification at a distance are being pursued as a means to aid human operators and improve the security of areas such as transport hubs. The task of object tracking is key to the effective use of more advanced technologies. To recognize an event people and objects must be tracked. Tracking also enhances the performance of tasks such as crowd analysis or human identification. Before an object can be tracked, it must be detected. Motion segmentation techniques, widely employed in tracking systems, produce a binary image in which objects can be located. However, these techniques are prone to errors caused by shadows and lighting changes. Detection routines often fail, either due to erroneous motion caused by noise and lighting effects, or due to the detection routines being unable to split occluded regions into their component objects. Particle filters can be used as a self contained tracking system, and make it unnecessary for the task of detection to be carried out separately except for an initial (often manual) detection to initialise the filter. Particle filters use one or more extracted features to evaluate the likelihood of an object existing at a given point each frame. Such systems however do not easily allow for multiple objects to be tracked robustly, and do not explicitly maintain the identity of tracked objects. This dissertation investigates improvements to the performance of object tracking algorithms through improved motion segmentation and the use of a particle filter. A novel hybrid motion segmentation / optical flow algorithm, capable of simultaneously extracting multiple layers of foreground and optical flow in surveillance video frames is proposed. The algorithm is shown to perform well in the presence of adverse lighting conditions, and the optical flow is capable of extracting a moving object. The proposed algorithm is integrated within a tracking system and evaluated using the ETISEO (Evaluation du Traitement et de lInterpretation de Sequences vidEO - Evaluation for video understanding) database, and significant improvement in detection and tracking performance is demonstrated when compared to a baseline system. A Scalable Condensation Filter (SCF), a particle filter designed to work within an existing tracking system, is also developed. The creation and deletion of modes and maintenance of identity is handled by the underlying tracking system; and the tracking system is able to benefit from the improved performance in uncertain conditions arising from occlusion and noise provided by a particle filter. The system is evaluated using the ETISEO database. The dissertation then investigates fusion schemes for multi-spectral tracking systems. Four fusion schemes for combining a thermal and visual colour modality are evaluated using the OTCBVS (Object Tracking and Classification in and Beyond the Visible Spectrum) database. It is shown that a middle fusion scheme yields the best results and demonstrates a significant improvement in performance when compared to a system using either mode individually. Findings from the thesis contribute to improve the performance of semi-automated video processing and therefore improve security in areas under surveillance.

Abandoned object detection using multi-layer motion detection

Abandoned object detection (AOD) systems are required to run in high traffic situations, with high levels of occlusion. Systems rely on background segmentation techniques to locate abandoned objects, by detecting areas of motion that have stopped. This is often achieved by using a medium term motion detection routine to detect long term changes in the background. When AOD systems are integrated into person tracking system, this often results in two separate motion detectors being used to handle the different requirements. We propose a motion detection system that is capable of detecting medium term motion as well as regular motion. Multiple layers of medium term (static) motion can be detected and segmented. We demonstrate the performance of this motion detection system and as part of an abandoned object detection system.

Dynamic Performance Measures for Object Tracking Systems

Performance evaluation of object tracking systems is typically performed after the data has been processed, by comparing tracking results to ground truth. Whilst this approach is fine when performing offline testing, it does not allow for real-time analysis of the systems performance, which may be of use for live systems to either automatically tune the system or report reliability. In this paper, we propose three metrics that can be used to dynamically asses the performance of an object tracking system. Outputs and results from various stages in the tracking system are used to obtain measures that indicate the performance of motion segmentation, object detection and object matching. The proposed dynamic metrics are shown to accurately indicate tracking errors when visually comparing metric results to tracking output, and are shown to display similar trends to the ETISEO metrics when comparing different tracking configurations.

Improved simultaneous computation of motion detection and optical flow for object tracking

Object tracking systems require accurate segmentation of the objects from the background for effective tracking. Motion segmentation or optical flow can be used to segment incoming images. Whilst optical flow allows multiple moving targets to be separated based on their individual velocities, optical flow techniques are prone to errors caused by changing lighting and occlusions, both common in a surveillance environment. Motion segmentation techniques are more robust to fluctuating lighting and occlusions, but don't provide information on the direction of the motion. In this paper we propose a combined motion segmentation/optical flow algorithm for use in object tracking. The proposed algorithm uses the motion segmentation results to inform the optical flow calculations and ensure that optical flow is only calculated in regions of motion, and improve the performance of the optical flow around the edge of moving objects. Optical flow is calculated at pixel resolution and tracking of flow vectors is employed to improve performance and detect discontinuities, which can indicate the location of overlaps between objects. The algorithm is evaluated by attempting to extract a moving target within the flow images, given expected horizontal and vertical movement (i.e. the algorithms intended use for object tracking). Results show that the proposed algorithm outperforms other widely used optical flow techniques for this surveillance application.

Sequential decision fusion for controlled detection errors

Information fusion in biometrics has received considerable attention. The architecture proposed here is based on the sequential integration of multi-instance and multi-sample fusion schemes. This method is analytically shown to improve the performance and allow a controlled trade-off between false alarms and false rejects when the classifier decisions are statistically independent. Equations developed for detection error rates are experimentally evaluated by considering the proposed architecture for text dependent speaker verification using HMM based digit dependent speaker models. The tuning of parameters, n classifiers and m attempts/samples, is investigated and the resultant detection error trade-off performance is evaluated on individual digits. Results show that performance improvement can be achieved even for weaker classifiers (FRR-19.6%, FAR-16.7%). The architectures investigated apply to speaker verification from spoken digit strings such as credit card numbers in telephone or VOIP or internet based applications.

Toward robust image detection of crown-of-thorns starfish for autonomous population monitoring

Robust texture recognition in underwater image sequences for marine pest population control such as Crown-Of-Thorns Starfish (COTS) is a relatively unexplored area of research. Typically, humans count COTS by laboriously processing individual images taken during surveys. Being able to autonomously collect and process images of reef habitat and segment out the various marine biota holds the promise of allowing researchers to gain a greater understanding of the marine ecosystem and evaluate the impact of different environmental variables. This research applies and extends the use of Local Binary Patterns (LBP) as a method for texture-based identification of COTS from survey images. The performance and accuracy of the algorithms are evaluated on a image data set taken on the Great Barrier Reef.

GPS fault detection with IMU and aircraft dynamics

Approaches with Vertical Guidance (APV) can provide greater safety and cost savings to general aviation through accurate GPS horizontal and vertical navigation. However, GPS needs augmentation to achieve APV fault detection requirements. Aircraft Based Augmentation Systems (ABAS) fuse GPS with additional sensors at the aircraft. Typical ABAS designs assume high-quality inertial sensors with Kalman filters but these are too expensive for general aviation. Instead of using high-quality (and expensive) sensors, the purpose of this paper is to investigate augmenting GPS with a low-quality MEMS IMU and Aircraft Dynamic Model (ADM). The IMU and ADM are fused together using a multiple model fusion strategy in a bank of Extended Kalman Filters (EKF) with the Normalized Solution Separation (NSS) fault detection scheme. A tightly-coupled configuration with GPS is used and frequent GPS updates are applied to the IMU and ADM to compensate for their errors. Based upon a simulated APV approach, the performance of this architecture in detecting a GPS ramp fault is investigated showing a performance improvement over a GPS-only “snapshot” implementation of the NSS method. The effect of fusing the IMU with the ADM is evaluated by comparing a GPS-IMU-ADM EKF with a GPS-IMU EKF where a small improvement in protection levels is shown.