Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss-function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation.

Video super-resolution (VSR) is a prominent research topic in low-level computer vision, where deep learning technologies have played a significant role. The rapid progress in deep learning and its applications in VSR has led to a proliferation of tools and techniques in the literature. However, the usage of these methods is often not adequately explained, and decisions are primarily driven by quantitative improvements. Given the significance of VSR's potential influence across multiple domains, it is imperative to conduct a comprehensive analysis of the elements and deep learning methodologies employed in VSR research. This methodical analysis will facilitate the informed development of models tailored to specific application needs. In this paper, we present an overarching overview of deep learning-based video super-resolution models, investigating each component and discussing its implications. Furthermore, we provide a synopsis of key components and technologies employed by state-of-the-art and earlier VSR models. By elucidating the underlying methodologies and categorising them systematically, we identified trends, requirements, and challenges in the domain. As a first-of-its-kind survey of deep learning-based VSR models, this work also establishes a multi-level taxonomy to guide current and future VSR research, enhancing the maturation and interpretation of VSR practices for various practical applications.

Research has shown the multitude of applications that Internet of Things (IoT), cloud computing, and forecast technologies present in every sector. In agriculture, one application is the monitoring of factors that influence crop development to assist in making crop management decisions. Research on the application of such technologies in agriculture has been mainly conducted at small experimental sites or under controlled conditions. This research has provided relevant insights and guidelines for the use of different types of sensors, application of a multitude of algorithms to forecast relevant parameters as well as architectural approaches of IoT platforms. However, research on the implementation of IoT platforms at the commercial scale is needed to identify platform requirements to properly function under such conditions. This article evaluates an IoT platform (IRRISENS) based on fully replicable microservices used to sense soil, crop, and atmosphere parameters, interact with third-party cloud services for scheduling irrigation and, potentially, control irrigation automatically. The proposed IoT platform was evaluated during one growing season at four commercial-scale farms on two broadacre irrigated crops with very different water management requirements (rice and cotton). Five main requirements for IoT platforms to be used in agriculture at commercial scale were identified from implementing IRRISENS as an irrigation support tool for rice and cotton production: scalability, flexibility, heterogeneity, robustness to failure, and security. The platform addressed all these requirements. The results showed that the microservice-based approach used is robust against both intermittent and critical failures in the field that could occur in any of the monitored sites. Further, processing or storage overload caused by datalogger malfunctioning or other reasons at one farm did not affect the platform’s performance. The platform was able to deal with different types of data heterogeneity. Since there are no shared microservices among farms, the IoT platform proposed here also provides data isolation, maintaining data confidentiality for each user, which is relevant in a commercial farm scenario.

Advances in measurement systems and technologies are being avidly taken up in perennial tree crop research and industry applications. However, there is a lack of a standard model to support streamlined management and integration of the data generated from advanced measurement systems used in tree crop research. Furthermore, the rapid expansion in the diversity and volumes of data is increasingly highlighting the requirement for a comprehensive data model and an ecosystem for efficient orchard management and decision-making. This research focuses on the design and implementation of a novel proof-of-concept data ecosystem that enables improved data storage, management, integration, processing, analysis, and usage. Contemporary technologies proliferating in other sectors but that have had limited adoption in agricultural research have been incorporated into the model. The core of the proposed solution is a service-oriented API-driven system coupled with a standard-based digital orchard model. Applying this solution in Agriculture Victoria’s Tatura tree crop research farm (the Tatura SmartFarm) has significantly reduced overheads in research data management, enhanced analysis, and improved data resolution. This is demonstrated by the preliminary results presented for in-orchard and postharvest data collection applications. The data ecosystem developed as part of this research also establishes a foundation for early fruit traceability across industry and research.

This paper presents a novel approach to video super-resolution (VSR) by focusing on the selection of input frames, a process critical to VSR. VSR methods typically rely on deep learning techniques, those that are able to learn features from a large dataset of low-resolution (LR) and corresponding high-resolution (HR) videos and generate high-quality HR frames from any new LR input frames using the learned features. However, these methods often use as input the immediate neighbouring frames to a given target frame without considering the importance and dynamics of the frames across the temporal dimension of a video. This work aims to address the limitations of the conventional sliding-window mechanisms by developing input frame selection algorithms. By dynamically selecting the most representative neighbouring frames based on content-aware selection measures, our proposed algorithms enable VSR models to extract more informative and accurate features that are better aligned with the target frame, leading to improved performance and higher-quality HR frames. Through an empirical study, we demonstrate that the proposed dynamic content-aware selection mechanism improves super-resolution results without any additional architectural overhead, offering a counter-intuitive yet effective alternative to the long-established trend of increasing architectural complexity to improve VSR results.