Rhys Hill

In situ image-based modeling

We present an interactive image-based modelling method for generating 3D models within an augmented reality system. Applying real time camera tracking, and high-level automated image analysis, enables more powerful modelling interactions than have previously been possible. The result is an immersive modelling process which generates accurate three dimensional models of real objects efficiently and effectively. In demonstrating the modelling process on a range of indoor and outdoor scenes, we show the flexibility it offers in enabling augmented reality applications in previously unseen environments.

Activity Topology Estimation for Large Networks of Cameras

Estimating the paths that moving objects can take through the fields of view of possibly non-overlapping cameras, also known as their activity topology, is an important step in the effective interpretation of surveillance video. Existing approaches to this problem involve tracking moving objects within cameras, and then attempting to link tracks across views. In contrast we propose an approach which begins by assuming all camera views are potentially linked, and successively eliminates camera topologies that are contradicted by observed motion. Over time, the true patterns of motion emerge as those which are not contradicted by the evidence. These patterns may then be used to initialise a finer level search using other approaches if required. This method thus represents an efficient and effective way to learn activity topology for a large network of cameras, particularly with a limited amount of data.

Ranking consistency for image matching and object retrieval

The goal of object retrieval is to rank a set of images by the similarity of their contents to those of a query image. However, it is difficult to measure image content similarity due to visual changes caused by varying viewpoint and environment. In this paper, we propose a simple, efficient method to more effectively measure content similarity from image measurements. Our method is based on the ranking information available from existing retrieval systems. We observe that images within the set which, when used as queries, yield similar ranking lists are likely to be relevant to each other and vice versa. In our method, ranking consistency is used as a verification method to efficiently refine an existing ranking list, in much the same fashion that spatial verification is employed. The efficiency of our method is achieved by a list-wise min-Hash scheme, which allows rapid calculation of an approximate similarity ranking. Experimental results demonstrate the effectiveness of the proposed framework and its applications. HighlightsWe propose an image matching and retrieval framework based on ranking consistency.A list-wise min-Hash method ensures the efficiency of ranking verification.Our method is flexible and thus has a variety of retrieval-related applications.

Interactive modelling for AR applications

We present a method for estimating the 3D shape of an object from a sequence of images captured by a hand-held device. The method is well suited to augmented reality applications in that minimal user interaction is required, and the models generated are of an appropriate form. The method proceeds by segmenting the object in every image as it is captured and using the calculated silhouette to update the current shape estimate. In contrast to previous silhouettebased modelling approaches, however, the segmentation process is informed by a 3D prior based on the previous shape estimate. A voting scheme is also introduced in order to compensate for the inevitable noise in the camera position estimates. The combination of the voting scheme with the closed-loop segmentation process provides a robust and flexible shape estimation method. We demonstrate the approach on a number of scenes where segmentation without a 3D prior would be challenging.

Measuring Latency for Video Surveillance Systems

The increased flexibility and other benefits offered by IP network cameras makes them a common choice for installation in new and expanded surveillance networks. One commonly quoted limitation of IP cameras is their high latency when compared to their analogue counterparts. This causes some reluctance to install or upgrade to digital cameras, and is slowing the adoption of live, intelligent analysis techniques in video surveillance systems. This paper presents methods for measurement of the latency in systems based upon digital IP or analogue cameras. These methods are camera-agnostic and require no specialised hardware. We use these methods to compare a variety of camera models. The results demonstrate that whilst analogue cameras do have a lower latency, most IP cameras are within acceptable tolerances. The source of the latency within an IP camera is also analysed, with prospects for improvement identified.

Finding camera overlap in large surveillance networks

Recent research on video surveillance across multiple cameras has typically focused on camera networks of the order of 10 cameras. In this paper we argue that existing systems do not scale to a network of hundreds, or thousands, of cameras. We describe the design and deployment of an algorithm called exclusion that is specifically aimed at finding correspondence between regions in cameras for large camera networks. The information recovered by exclusion can be used as the basis for other surveillance tasks such as tracking people through the network, or as an aid to human inspection. We have run this algorithm on a campus network of over 100 cameras, and report on its performance and accuracy over this network.

Fast approximate L∞ minimization: Speeding up robust regression

Minimization of the L∞ norm, which can be viewed as approximately solving the non-convex least median estimation problem, is a powerful method for outlier removal and hence robust regression. However, current techniques for solving the problem at the heart of L∞ norm minimization are slow, and therefore cannot be scaled to large problems. A new method for the minimization of the L∞ norm is presented here, which provides a speedup of multiple orders of magnitude for data with high dimension. This method, termed Fast L∞Minimization, allows robust regression to be applied to a class of problems which was previously inaccessible. It is shown how the L∞ norm minimization problem can be broken up into smaller sub-problems, which can then be solved extremely efficiently. Experimental results demonstrate the radical reduction in computation time, along with robustness against large numbers of outliers in a few model-fitting problems.

Automatic camera placement for large scale surveillance networks

Automatic placement of surveillance cameras in arbitrary buildings is a challenging task, and also one that is essential for efficient deployment of large scale surveillance networks. Existing approaches for automatic camera placement are either limited to a small number of cameras, or constrained in terms of the building layouts to which they can be applied. This paper describes a new method for determining the best placement for large numbers of cameras within arbitrary building layouts. The method takes as input a 3D model of the building, and uses a genetic algorithm to find a placement that optimises coverage and (if desired) overlap between cameras. Results are reported for an implementation of the method, including its application to a wide variety of complex buildings, both real and synthetic.

Estimating camera overlap in large and growing networks

Large-scale intelligent video surveillance requires an accurate estimate of the relationships between the fields of view of the cameras in the network. The exclusion approach is the only method currently capable of performing online estimation of camera overlap for networks of more than 100 cameras, and implementations have demonstrated the capability to support networks of 1000 cameras. However, these implementations include a centralised processing component, with the practical result that the resources (in particular, memory) of the central processor limit the size of the network that can be supported. In this paper, we describe a new, partitioned, implementation of exclusion, suitable for deployment to a cluster of commodity servers. Results for this implementation demonstrate support for significantly larger camera networks than was previously feasible. Furthermore, the nature of the partitioning scheme enables incremental extension of system capacity through the addition of more servers, without interrupting the existing system. Finally, formulae for requirements of system memory and bandwidth resources, verified by experimental results, are derived to assist engineers seeking to implement the technique.

Tracking hand-off in large surveillance networks

This paper investigates the use of pairwise camera overlap estimates for supporting target tracking across large networks of surveillance cameras. We compare the use of camera overlap topology information to a method based on matching target appearance histograms, and also evaluate the effect of combining both methods. Tracking accuracy results are reported in terms of precision and recall for a 24 camera network. Camera overlap information is shown to deliver significant advantages for tracking when compared with simply matching target appearance histograms, due to its robustness to low quality imagery. We show empirically that this is the case even for automatically derived overlap estimates containing errors.