Jacobus J Barnard

Abstract:

We present a general model for tracking smooth trajectories of multiple targets in complex data sets, where tracks potentially cross each other many times. As the number of overlapping trajectories grows, exploiting smoothness becomes increasingly important to disambiguate the association of successive points. However, in many important problems an effective parametric model for the trajectories does not exist. Hence we propose modeling trajectories as independent realizations of Gaussian processes with kernel functions which allow for arbitrary smooth motion. Our generative statistical model accounts for the data as coming from an unknown number of such processes, together with expectations for noise points and the probability that points are missing. For inference we compare two methods: A modified version of the Markov chain Monte Carlo data association (MCMCDA) method, and a Gibbs sampling method which is much simpler and faster, and gives better results by being able to search the solution space more efficiently. In both cases, we compare our results against the smoothing provided by linear dynamical systems (LDS). We test our approach on videos of birds and fish, and on 82 image sequences of pollen tubes growing in a petri dish, each with up to 60 tubes with multiple crossings. We achieve 93% accuracy on image sequences with up to ten trajectories (35 sequences) and 88% accuracy when there are more than ten (42 sequences). This performance surpasses that of using an LDS motion model, and far exceeds a simple heuristic tracker. © 2011 IEEE.

Abstract:

We present a comprehensive strategy for evaluating image retrieval algorithms. Because automated image retrieval is only meaningful in its service to people, performance characterization must be grounded in human evaluation. Thus we have collected a large data set of human evaluations of retrieval results, both for query by image example and query by text. The data is independent of any particular image retrieval algorithm and can be used to evaluate and compare many such algorithms without further data collection. The data and calibration software are available on-line (http://kobus.ca/research/data). We develop and validate methods for generating sensible evaluation data, calibrating for disparate evaluators, mapping image retrieval system scores to the human evaluation results, and comparing retrieval systems. We demonstrate the process by providing grounded comparison results for several algorithms. © 2005 IEEE.

Abstract:

We present a new approach for modeling multi-modal data sets, focusing on the specific case of segmented images with associated text. Learning the joint distribution of image regions and words has many applications. We consider in detail predicting words associated with whole images (auto-annotation) and corresponding to particular image regions (region naming). Auto-annotation might help organize and access large collections of images. Region naming is a model of object recognition as a process of translating image regions to words, much as one might translate from one language to another. Learning the relationships between image regions and semantic correlates (words) is an interesting example of multi-modal data mining, particularly because it is typically hard to apply data mining techniques to collections of images. We develop a number of models for the joint distribution of image regions and words, including several which explicitly learn the correspondence between regions and words. We study multi-modal and correspondence extensions to Hofmann's hierarchical clustering/aspect model, a translation model adapted from statistical machine translation (Brown et al.), and a multi-modal extension to mixture of latent Dirichlet allocation (MoM-LDA). All models are assessed using a large collection of annotated images of real scenes. We study in depth the difficult problem of measuring performance. For the annotation task, we look at prediction performance on held out data. We present three alternative measures, oriented toward different types of task. Measuring the performance of correspondence methods is harder, because one must determine whether a word has been placed on the right region of an image. We can use annotation performance as a proxy measure, but accurate measurement requires hand labeled data, and thus must occur on a smaller scale. We show results using both an annotation proxy, and manually labeled data.

Abstract:

Fluorescent surfaces are common in the modern world, but they present problems for machine color constancy because fluorescent reflection typically violates the assumptions needed by most algorithms. The complexity of fluorescent reflection is likely one of the reasons why fluorescent surfaces have escaped the attention of computational color constancy researchers. In this paper we take some initial steps to rectify this omission. We begin by introducing a simple method for characterizing fluorescent surfaces. It is based on direct measurements, and thus has low error and avoids the need to develop a comprehensive and accurate physical model. We then modify and extend several modern color constancy algorithms to address fluorescence. The algorithms considered are CRULE and derivatives, Color by Correlation, and neural net methods. Adding fluorescence to Color by Correlation and neural net methods is relatively straight forward, but CRULE requires modification so that its complete reliance on diagonal models can be relaxed. We present results for both synthetic and real image data for fluorescent capable versions of CRULE and Color by Correlation, and we compare the results with the standard versions of these and other algorithms.

PMID: 18249720;Abstract:

We introduce a context for testing computational color constancy, specify our approach to the implementation of a number of the leading algorithms, and report the results of three experiments using synthesized data. Experiments using synthesized data are important because the ground truth is known, possible confounds due to camera characterization and pre-processing are absent, and various factors affecting color constancy can be efficiently investigated because they can be manipulated individual and precisely. The algorithms chosen for close study include two gray world methods, a limiting case of a version of the Retinex method, a number of variants of Forsyth's gamut-mapping method, Cardei et al.'s neural net method, and Finlayson et al.'s Color by Correlation method. We investigate the ability of these algorithms to make estimates of three different color constancy quantities: the chromaticity of the scene illuminant, the overall magnitude of that illuminant, and a corrected, illumination invariant, image. We consider algorithm performance as a function of the number of surfaces in scenes generated from reflectance spectra, the relative effect on the algorithms of added specularities, and the effect of subsequent clipping of the data. All data is available on-line at http://www.cs.sfu.ca/∼color/data, and implementations for most of the algorithms are also available (http://www.cs.sfu.ca/∼color/code).