Search

Background The application of image analysis technologies for the interpretation of microbiological cultures is evolving rapidly. The primary aim of this study was to establish whether the image analysis system named Automated Plate Assessment System (APAS; LBT Innovations Ltd., Australia) could be applied to screen urine cultures. A secondary aim was to evaluate differences between traditional plate reading (TPR) and the reading of cultures from images, or digital plate reading (DPR). Methods A total of 9,224 urine samples submitted for culture to three clinical laboratories, two in Australia and one in the USA, were included in the study. Cultures were prepared on sheep blood and MacConkey agar plates and read by panels of three microbiologists. The plates were then presented to APAS for image capture and analysis, and the images and results were stored for later review. Results Image analysis of cultures using APAS produced a diagnostic sensitivity and specificity of 99.0% and 84.5%, respectively. Colonies were detected by APAS on 99.0% of blood agar plates with growth and on 99.5% of MacConkey agar plates. DPR agreed with TPR for colony enumeration on 92.1% of the plates, with a sensitivity of 90.8% and specificity of 92.8% for case designation. However, several differences in the classification of colony morphologies using DPR were identified. Conclusions APAS was shown to be a reliable screening system for urine cultures. The study also showed acceptable concordance between DPR and TPR for colony detection, enumeration, and case designation.

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.

The subject of laboratory error was examined during a symposium at the ASM Microbe 2016 conference in Boston, MA. During the session, it became clear that discussion on this subject has not flourished within our field, possibly due to a lack of published experiences. We therefore submit our

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.

A number of problems in computer vision require the estimation of a set of matrices, each of which is defined only up to an individual scale factor and represents the parameters of a separate model, under the assumption that the models are intrinsically interconnected. One example of such a set is a family of fundamental matrices sharing an infinite homography. Here an approach is presented to estimating a general set of interdependent matrices defined to within separate scales. The input data is assumed to consist of individually estimated matrices for particular models, which when considered collectively may fail to satisfy the constraints representing the inter-model relationships. Two cost functions are proposed for upgrading, via optimisation, the data of this sort to a collection of matrices satisfying the inter- model constraints. One of these functions incorporates error covariances. Each function is invariant to any change of scale for the input estimates. The proposed approach is applied to the particular problem of estimating a set of fundamental matrices of the form of the example set above. Experimental results are given which demonstrate the effectiveness of the approach.

Surveillance camera technologies have reached the point whereby networks of a thousand cameras are not uncommon. Systems for collecting and storing the video generated by such networks have been deployed operationally, and sophisticated methods have been developed for interrogating individual video streams. The principal contribution of this paper is a scalable method for processing video streams collectively, rather than on a per camera basis, which enables a coordinated approach to large-scale video surveillance. To realise our ambition of thousand camera automated surveillance networks, we use distributed processing on a dedicated cluster. Our focus is on determining activity topology -the paths objects may take between cameras' fields of view. An accurate estimate of activity topology is critical to many surveillance functions, including tracking targets through the network, and may also provide a means for partitioning of distributed surveillance processing. We present several implementations using the exclusion algorithm to determine activity topology. Measurements reported for the key system component demonstrate scalability to networks with a thousand cameras. Whole-system measurements are reported for actual operation on over a hundred camera streams (this limit is based on the number of cameras and computers presently available to us, not scalability). Finally, we explore how to scale our approach to support multi-thousand camera networks.

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.