This study provides both a spherical understanding about autonomous ship navigation for collision avoidance (CA) and a theoretical background of the reviewed work. Additionally, the human cognitive abilities and the collision avoidance regulations (COLREGs) for ship navigation are examined together with water based collision avoidance algorithms. The requirements for autonomous ship navigation are addressed in conjunction with the factors influencing ship collision avoidance. Humans are able to appreciate these factors and also perform ship navigation at a satisfactory level, but their critical decisions are highly subjective and can lead to error and potentially, to ship collision. The research for autonomous ship navigation may be grouped into the classical and soft computing based categories. Classical techniques are based on mathematical models and algorithms while soft-computing techniques are based on Artificial Intelligence (AI). The areas of AI for autonomous ship collision avoidance are examined in this paper are evolutionary algorithms, fuzzy logic, expert systems, and neural networks (NN), as well as a combination of them (hybrid system).

Visual place recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the concepts of localisation, loop closure, image retrieval and is a critical component of many autonomous navigation systems ranging from autonomous vehicles to drones and computer vision systems. While the concept of place recognition has been around for many years, VPR research has grown rapidly as a field over the past decade due to improving camera hardware and its potential for deep learning-based techniques, and has become a widely studied topic in both the computer vision and robotics communities. This growth however has led to fragmentation and a lack of standardisation in the field, especially concerning performance evaluation. Moreover, the notion of viewpoint and illumination invariance of VPR techniques has largely been assessed qualitatively and hence ambiguously in the past. In this paper, we address these gaps through a new comprehensive open-source framework for assessing the performance of VPR techniques, dubbed “VPR-Bench”. VPR-Bench (Open-sourced at: https://github.com/MubarizZaffar/VPR-Bench) introduces two much-needed capabilities for VPR researchers: firstly, it contains a benchmark of 12 fully-integrated datasets and 10 VPR techniques, and secondly, it integrates a comprehensive variation-quantified dataset for quantifying viewpoint and illumination invariance. We apply and analyse popular evaluation metrics for VPR from both the computer vision and robotics communities, and discuss how these different metrics complement and/or replace each other, depending upon the underlying applications and system requirements. Our analysis reveals that no universal SOTA VPR technique exists, since: (a) state-of-the-art (SOTA) performance is achieved by 8 out of the 10 techniques on at least one dataset, (b) SOTA technique in one community does not necessarily yield SOTA performance in the other given the differences in datasets and metrics. Furthermore, we identify key open challenges since: (c) all 10 techniques suffer greatly in perceptually-aliased and less-structured environments, (d) all techniques suffer from viewpoint variance where lateral change has less effect than 3D change, and (e) directional illumination change has more adverse effects on matching confidence than uniform illumination change. We also present detailed meta-analyses regarding the roles of varying ground-truths, platforms, application requirements and technique parameters. Finally, VPR-Bench provides a unified implementation to deploy these VPR techniques, metrics and datasets, and is extensible through templates.

This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12x average speedup relative to state-of-the-art methods.

Food safety is an important issue in today’s world. The traditional agri-food production system does not offer easy traceability of the produce at any point of the supply chain, and hence, during a food-borne outbreak, it is very difficult to sift through food production data to track produce and the origin of the outbreak. In recent years, the blockchain based food production system has resolved this challenge; however, none of the proposed methodologies makes the food production data easily accessible, traceable and verifiable by consumers or producers using mobile/edge devices. In this paper, we propose FoodSQRBlock (Food Safety Quick Response Block), a blockchain technology based framework that digitises the food production information and makes it easily accessible, traceable and verifiable by the consumers and producers by using QR codes. We also propose a large-scale integration of FoodSQRBlock in the cloud to show the feasibility and scalability of the framework, as well as give an experimental evaluation to prove this.

© 2015 The Authors The demographic change towards an aging population is creating a significant impact and introducing drastic challenges to our society. We therefore need to find ways to assist older people to stay independently and prevent social isolation of these population. Information and Communication Technologies (ICT) provide various solutions to help older adults to improve their quality of life, stay healthier, and live independently for a time. Ambient Assisted Living (AAL) is a field to investigate innovative technologies to provide assistance as well as healthcare and rehabilitation to impaired seniors. The paper provides a review of research background and technologies of AAL