Graham McNeill

Hierarchical Procrustes Matching for Shape Retrieval

We introduce Hierarchical Procrustes Matching (HPM), a segment-based shape matching algorithm which avoids problems associated with purely global or local methods and performs well on benchmark shape retrieval tests. The simplicity of the shape representation leads to a powerful matching algorithm which incorporates intuitive ideas about the perceptual nature of shape while being computationally efficient. This includes the ability to match similar parts even when they occur at different scales or positions. While comparison of multiscale shape representations is typically based on specific features, HPM avoids the need to extract such features. The hierarchical structure of the algorithm captures the appealing notion that matching should proceed in a global to local direction.

Storyboard sketches for Content Based Video Retrieval

We present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an algorithm for matching descriptions of sketched objects to video. We demonstrate our model fitting to clips under static and moving camera conditions, exhibiting linear and oscillatory motion. We evaluate retrieval on two real video data sets, and on a video data set exhibiting controlled variation in shape, color, motion and clutter.

Free-hand sketch grouping for video retrieval

We present an algorithm for extracting object descriptions from free-hand sketches of remembered scenes, drawn as video retrieval queries. Our sketches depict scene content, as well as indicators of motion. We report an exploratory study investigating how people sketch to depict recalled events. We incorporate several observations from this study into the design of a novel sketch parsing algorithm. We draw upon a temporal HMM classifier to recognise common pictograms, and graph-cut to identify more general objects.

Estimating local commuting patterns from geolocated Twitter data

The emergence of large stores of transactional data generated by increasing use of digital devices presents a huge opportunity for policymakers to improve their knowledge of the local environment and thus make more informed and better decisions. A research frontier is hence emerging which involves exploring the type of measures that can be drawn from data stores such as mobile phone logs, Internet searches and contributions to social media platforms and the extent to which these measures are accurate reflections of the wider population. This paper contributes to this research frontier, by exploring the extent to which local commuting patterns can be estimated from data drawn from Twitter. It makes three contributions in particular. First, it shows that heuristics applied to geolocated Twitter data offer a good proxy for local commuting patterns; one which outperforms the current best method for estimating these patterns (the radiation model). This finding is of particular significance because we make use of relatively coarse geolocation data (at the city level) and use simple heuristics based on frequency counts. Second, it investigates sources of error in the proxy measure, showing that the model performs better on short trips with higher volumes of commuters; it also looks at demographic biases but finds that, surprisingly, measurements are not significantly affected by the fact that the demographic makeup of Twitter users differs significantly from the population as a whole. Finally, it looks at potential ways of going beyond simple frequency heuristics by incorporating temporal information into models.

Generating tile maps

Tile maps are an important tool in thematic cartography with distinct qualities (and limitations) that distinguish them from better‐known techniques such as choropleths, cartograms and symbol maps. Specifically, tile maps display geographic regions as a grid of identical tiles so large regions do not dominate the viewers attention and small regions are easily seen. Furthermore, complex data such as time series can be shown on each tile in a consistent format, and the grid layout facilitates comparisons across tiles. Whilst a small number of handcrafted tile maps have become popular, the time‐consuming process of creating new tile maps limits their wider use. To address this issue, we present an algorithm that generates a tile map of the specified type (e.g. square, hexagon, triangle) from raw shape data. Since the ‘best’ tile map depends on the specific geography visualized and the task to be performed, the algorithm generates and ranks multiple tile maps and allows the user to choose the most appropriate. The approach is demonstrated on a range of examples using a prototype browser‐based application.