Sorry, you need to enable JavaScript to visit this website.

Even though Unmanned Surface Vehicles (USVs) are increasingly used to perform various laborious and expensive off-shore tasks, they still require an extensive dedicated crew supporting and ensuring the safety of their operations. The recent developments in computer vision and robotics further fueled the interest on developing \textit{autonomous} USVs that will overcome the aforementioned limitations, unleashing their full potential. One of the most vital and fundamental tasks in order to automate and ensure the safety of USV operations is to perform water segmentation.

Building floor plans with locations of safety, security, and energy assets such as IoT sensors, fire alarms, etc. are vital for climate control, emergency response, safety, and maintenance of building infrastructure. Existing approaches to building survey are tedious, error prone, and involve an operator with a clipboard and pen, enumerating and localizing assets in each room. We propose an interactive method for a human operator to use an app on a smartphone, which can detect, classify, and localize assets of interest, to expedite such a task.

Non-maximum suppression (NMS) is a post-processing step in almost every visual object detector. Its goal is to drastically prune the number of overlapping detected candidate regions-of-interest (ROIs) and replace them with a single, more spatially accurate detection. The default algorithm (Greedy NMS) is fairly simple and suffers from drawbacks, due to its need for manual tuning. Recently, NMS has been improved using deep neural networks that learn how to solve a spatial overlap-based detections rescoring task in a supervised manner, where only ROI coordinates are exploited as input.

This paper combines spatially-variant filtering and non-local low-rank regularization (NLR) to exploit non-local similarity in natural images in addressing the problem of image interpolation. We propose to build a carefully designed spatially-variant, non-local filtering scheme to generate a reliable estimate of the interpolated image and utilize NLR to refine the estimation. Our work uses a simple, parallelizable algorithm without the need to solve complicated optimization problems.

The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conventional approach of hard-coding motion routines, we propose a deep learning method for obtaining control policies by directly mimicking raw video demonstrations. Previous methods in this domain rely on extracting low-dimensional features from expert videos followed by a separate hand-crafted reward estimation step.

In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image. Observing that existing colourisation methods sometimes exhibit a lack of colourfulness, this paper proposes a method to improve colourisation results. In particular, the method uses Generative Adversarial Neural Networks (GANs) and focuses on improvement of training stability to enable better generalisation in large multi-class image datasets.