Search

Neuromorphic vision sensors, commonly referred to as Event Cameras (ECs), have gained prominence as a field of research in Computer Vision. This popularity stems from the numerous unique characteristics including High Dynamic Range, High Temporal Resolution, and Low Latency. Of particular interest is their temporal resolution, which proves ideal for human monitoring applications. Capturing rapid facial movements and eye gaze can be effectively achieved with ECs. Recent studies involving the use of ECs for object detection and tracking have demonstrated success in tasks involving Eye Motion Analysis such as Eye tracking, Blink detection, Gaze estimation and Pupil tracking. The objective of this study is to provide a comprehensive review of the current research in the aforementioned tasks, focusing on the potential utilization of ECs for future tasks involving rapid eye motion detection, such as detection and classification of saccades. We highlight studies that may serve as a foundation for undertaking such a task, such as pupil tracking and gaze estimation. We also highlight in our review some common challenges encountered such as the availability of datasets and review some of the methods used in solving this problem. Finally, we discuss some limitations of this field of research and conclude with future directions including real-world applications and potential research directions.

Moving object path prediction in traffic scenes from the perspective of a moving vehicle can improve safety on the road, which is the aim of Advanced Driver Assistance Systems (ADAS). However, this task still remains a challenge. Work has been carried out on the use of x,y positional information of the moving objects only. However, besides positional information there is more information that surrounds a vehicle that can be leveraged in the prediction along with the x,y features. This is known as contextual information. In this work, a deep exploration of these features is carried out by evaluating different types of data, using different fusion strategies. The core architectures of this model are CNN and LSTM architectures. It is concluded that in the prediction task, not only are the features important, but the way they are fused in the developed architecture is also of importance.

In this paper, we investigate different scenarios of anomaly detection on decentralised Internet of Things (IoT) applications. Specifically, an anomaly detector is devised to detect different types of anomalies for an IoT data management system, based on the decentralised alternating direction method of multipliers (ADMM), which was proposed in our previous work. The anomaly detector only requires limited information from the IoT system, and can be operated using both a mathematical-rule-based approach and the deep learning approach proposed in the paper. Our experimental results show that detection based on mathematical approach is simple to implement, but it also comes with lower detection accuracy (78.88%). In contrast, the deep-learning-enabled approach can easily achieve a higher detection accuracy (96.28%) in the real world working environment.

Exercise-based cardiac rehabilitation requires patients to perform a set of certain prescribed exercises a specific number of times. Local muscular endurance exercises are an important part of the rehabilitation program. Automatic exercise recognition and repetition counting, from wearable sensor data, is an important technology to enable patients to perform exercises independently in remote settings, e.g., their own home. In this paper, we first report on a comparison of traditional approaches to exercise recognition and repetition counting (supervised ML and peak detection) with Convolutional Neural Networks (CNNs). We investigated CNN models based on the AlexNet architecture and found that the performance was better than the traditional approaches, for exercise recognition (overall F1-score of 97.18%) and repetition counting (±1 error among 90% observed sets). To the best of our knowledge, our approach of using a single CNN method for both recognition and repetition counting is novel. Also, we make the INSIGHT-LME dataset publicly available to encourage further research.

Understanding hydrological processes in large, open areas, such as catchments, and further modelling these processes are still open research questions. The system proposed in this work provides an automatic end-to-end pipeline from data collection to information extraction that can potentially assist hydrologists to better understand the hydrological processes using a data-driven approach. In this work, the performance of a low-cost off-the-shelf self contained sensor unit, which was originally designed and used to monitor liquid levels, such as AdBlue, fuel, lubricants etc., in a sealed tank environment, is first examined. This process validates that the sensor does provide accurate water level information for open water level monitoring tasks. Utilising the dataset collected from eight sensor units, an end-to-end pipeline of automating the data collection, data processing and information extraction processes is proposed. Within the pipeline, a data-driven anomaly detection method that automatically extracts rapid changes in measurement trends at a catchment scale. The lag-time of the test site (Dodder catchment Dublin, Ireland) is also analyzed. Subsequently, the water level response in the catchment due to storm events during the 27 month deployment period is illustrated. To support reproducible and collaborative research, the collected dataset and the source code of this work will be publicly available for research purposes.

In this paper we present a framework that allows for the automatic identification of sporting activities using commonly available smartphones. We extract discriminative informational features from smartphone accelerometers using the Discrete Wavelet Transform (DWT). Despite the poor quality of their accelerometers, smartphones were used as capture devices due to their prevalence in today’s society. Successful classification on this basis potentially makes the technology accessible to both elite and non-elite athletes. Extracted features are used to train different categories of classifiers. No one classifier family has a reportable direct advantage in activity classification problems to date; thus we examine classifiers from each of the most widely used classifier families. We investigate three classification approaches; a commonly used SVM-based approach, an optimized classification model and a fusion of classifiers. We also investigate the effect of changing several of the DWT input parameters, including mother wavelets, window lengths and DWT decomposition levels. During the course of this work we created a challenging sports activity analysis dataset, comprised of soccer and field-hockey activities. The average maximum F-measure accuracy of 87% was achieved using a fusion of classifiers, which was 6% better than a single classifier model and 23% better than a standard SVM approach.

Environmental monitoring is evolving towards large-scale and low-cost sensor networks operating reliability and autonomously over extended periods of time. Sophisticated analytical instrumentation such as chemo-bio sensors present inherent limitations because of the number of samples that they can take. In order to maximize their deployment lifetime, we propose the coordination of multiple heterogeneous information sources. We use rainfall radar images and information from a water depth sensor as input to a neural network (NN) to dictate the sampling frequency of a phosphate analyzer at the River Lee in Cork, Ireland. This approach shows varied performance for different times of the year but overall produces output that is very satisfactory for the application context in question. Our study demonstrates that even with limited training data, a system for controlling the sampling rate of the nutrient sensor can be set up and can improve the efficiency of the more sophisticated nodes of the sensor network.

The cost of monitoring greenhouse gas emissions from landfill sites is of major concern for regulatory authorities. The current monitoring procedure is recognised as labour intensive, requiring agency inspectors to physically travel to perimeter borehole wells in rough terrain and manually measure gas concentration levels with expensive hand-held instrumentation. In this article we present a cost-effective and efficient system for remotely monitoring landfill subsurface migration of methane and carbon dioxide concentration levels. Based purely on an autonomous sensing architecture, the proposed sensing platform was capable of performing complex analytical measurements in situ and successfully communicating the data remotely to a cloud database. A web tool was developed to present the sensed data to relevant stakeholders. We report our experiences in deploying such an approach in the field over a period of approximately 16 months.

This paper presents an approach to movie video indexing that utilises audiovisual analysis to detect important and meaningful temporal video segments, that we term events. We consider three event classes, corresponding to dialogues, action sequences, and montages, where the latter also includes musical sequences. These three event classes are intuitive for a viewer to understand and recognise whilst accounting for over 90% of the content of most movies. To detect events we leverage traditional filmmaking principles and map these to a set of computable low-level audiovisual features. Finite state machines (FSMs) are used to detect when temporal sequences of specific features occur. A set of heuristics, again inspired by filmmaking conventions, are then applied to the output of multiple FSMs to detect the required events. A movie search system, named MovieBrowser, built upon this approach is also described. The overall approach is evaluated against a ground truth of over twenty-three hours of movie content drawn from various genres and consistently obtains high precision and recall for all event classes. A user experiment designed to evaluate the usefulness of an event-based structure for both searching and browsing movie archives is also described and the results indicate the usefulness of the proposed approach.