The unsuitability of using classic mutual information measure as a performance measure for image fusion is discussed. Analytical proof that classic mutual information cannot be considered a measure for image fusion performance is provided.

The problem of intent understanding between highly and fully automated vehicles and vulnerable road users (VRUs) such as pedestrians in urban traffic environment has got some momentum over the past few years. Previous work has been tackling the problem using two common approaches, namely dynamical motion modeling and motion planning. In this paper, a novel radical end-to-end data-driven approach is proposed for long-term intent prediction of VRUs in urban traffic environment based solely on their motion trajectories. In the proposed approach, we utilized the widely adopted architecture of recurrent neural networks with Long-Short Term Memory (LSTM) modules to form a deep stacked LSTM network. Three common approaches used in the literature were compared against our proposed approach over two different real-world datasets involving pedestrians collected from vehicle-based stereo cameras. The results over the testing datasets showed that the proposed approach achieved higher accuracies over most of the scenarios of the testing datasets with a small mean lateral position error of 0.48 meters. Moreover, the proposed approach showed also a significant generalization capability over totally unobserved testing scenes during the training phase with only 0.58 meters in mean lateral position error.

Interest in enhancing medical services and healthcare is emerging exploiting recent technological capabilities. An integrable fall detection sensor is an essential component toward achieving smart healthcare solutions. Traditional vision-based methods rely on tracking a skeleton and estimating the change in height of key body parts such as head, hips, and shoulders. These methods are often challenged by occluded body parts and abrupt posture changes. This paper presents a fall detection system consisting of a novel skeleton-free posture recognition method and an activity recognition stage. The posture recognition method analyzes local variations in depth pixels to identify the adopted posture. An input depth frame acquired using a Kinect-like sensor is densely represented using a depth comparison feature and fed to a random decision forest to discriminate among standing, sitting, and fallen postures. The proposed approach simplifies the posture recognition into a simple pixel labeling problem, after which determining the posture is as simple as counting votes from all labeled pixels. The falling event is recognized using a support vector machine. The proposed approach records a sensitivity rate of 99% on synthetic and live datasets as well as a specificity rate of 99% on synthetic datasets and 96% on popular live datasets without invasive accelerometer support.

Surgical tool segmentation is used for detection, tracking and pose estimation of the tools in the vicinity of surgical scenes. It is considered as an essential task in surgical phase recognition and flow identification. Surgical flow identification is an unresolved task in the domain of context-aware surgical systems, which is used extensively on computer assisted intervention (CAI). CAI is used for staff assignment, automated guidance during intervention, surgical alert systems, automatic indexing of surgical video databases and optimisation of the real-time scheduling of operating room. Semantic segmentation is used for accurate delineation of surgical tools from the background. In semantic segmentation, each label is assigned to a class as a tool or a background. In this presented work, we applied a hybrid method utilising both recurrent and convolutional networks to achieve higher accuracy of surgical tools segmentation. The proposed method is trained and tested using a public dataset MICCAI 2016 Endoscopic Vision Challenge Robotic Instruments dataset "EndoVis". We achieved better performance using the proposed method compared to state-of-the-art methods on the same dataset for benchmarking. We achieved a balanced accuracy of 93.3% and Jaccard index of 82.7%.

With the wide spread of affordable virtual reality headsets, virtual environments are rapidly changing the way humans interact with reality. Understanding the effects of virtual environments on the mental and cognitive state is essential. In addition, defining methods for measuring and assessing visual fatigue in virtual environments is still needed. While eye movements is tightly coupled to the mental state, analysis of eye movement can add insights for safer virtual environments. Biomechanical analysis has been used extensively in the analysis of human movement. Simulation of different scenarios like injuries and surgeries provided insights and solutions to problems that were otherwise impossible. This includes understanding the effects of changing insertion points of muscle on range of motion or how muscle activation can affect the motion produced. Extending the use of biomechanical simulation analysis into eye movement can be used to deepen our understanding of how virtual environments affects our visual and mental capabilities. This paper presents a thorough review on ocular biomechanics and ocular models in literature. We start with a brief introduction on the anatomy of the eye and eye kinematics. In addition, properties of the extraocular muscles (EOM) are described and the difference between EOMs and skeletal muscle is highlighted. The challenges facing biomechanical simulation and analysis of eye movement are presented along with the role of ocular models in assessing visual fatigue. Furthermore, the compatibility of available biomechanical tools to analyse ocular movements is discussed.