Chandrika Kamath

Robust techniques for background subtraction in urban traffic video

Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications. A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model. There are many challenges in developing a good background subtraction algorithm. First, it must be robust against changes in illumination. Second, it should avoid detecting non-stationary background objects such as swinging leaves, rain, snow, and shadow cast by moving objects. Finally, its internal background model should react quickly to changes in background such as starting and stopping of vehicles. In this paper, we compare various background subtraction algorithms for detecting moving vehicles and pedestrians in urban traffic video sequences. We consider approaches varying from simple techniques such as frame differencing and adaptive median filtering, to more sophisticated probabilistic modeling techniques. While complicated techniques often produce superior performance, our experiments show that simple techniques such as adaptive median filtering can produce good results with much lower computational complexity.

Robust background subtraction with foreground validation for urban traffic video

Identifying moving objects in a video sequence is a fundamental and critical task in many computer-vision applications. Background subtraction techniques are commonly used to separate foreground moving objects from the background. Most background subtraction techniques assume a single rate of adaptation, which is inadequate for complex scenes such as a traffic intersection where objects are moving at different and varying speeds. In this paper, we propose a foreground validation algorithm that first builds a foreground mask using a slow-adapting Kalman filter, and then validates individual foreground pixels by a simple moving object model built using both the foreground and background statistics as well as the frame difference. Ground-truth experiments with urban traffic sequences show that our proposed algorithm significantly improves upon results using only Kalman filter or frame-differencing, and outperforms other techniques based on mixture of Gaussians, median filter, and approximated median filter.

Inducing oblique decision trees with evolutionary algorithms

This paper illustrates the application of evolutionary algorithms (EAs) to the problem of oblique decision-tree (DT) induction. The objectives are to demonstrate that EAs can find classifiers whose accuracy is competitive with other oblique tree construction methods, and that, at least in some cases, this can be accomplished in a shorter time. We performed experiments with a (1+1) evolution strategy and a simple genetic algorithm on public domain and artificial data sets, and compared the results with three other oblique and one axis-parallel DT algorithms. The empirical results suggest that the EAs quickly find competitive classifiers, and that EAs scale up better than traditional methods to the dimensionality of the domain and the number of instances used in training. In addition, we show that the classification accuracy improves when the trees obtained with the EAs are combined in ensembles, and that sometimes it is possible to build the ensemble of evolutionary trees in less time than a single traditional oblique tree.

An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems

There are numerous combinations of neural networks (NNs) and evolutionary algorithms (EAs) used in classification problems. EAs have been used to train the networks, design their architecture, and select feature subsets. However, most of these combinations have been tested on only a few data sets and many comparisons are done inappropriately measuring the performance on training data or without using proper statistical tests to support the conclusions. This paper presents an empirical evaluation of eight combinations of EAs and NNs on 15 public-domain and artificial data sets. Our objective is to identify the methods that consistently produce accurate classifiers that generalize well. In most cases, the combinations of EAs and NNs perform equally well on the data sets we tried and were not more accurate than hand-designed neural networks trained with simple backpropagation.

Retrieval using texture features in high-resolution multispectral satellite imagery

Texture features have long been used in remote sensing applications to represent and retrieve image regions similar to a query region. Various representations of texture have been proposed based on the Fourier power spectrum, spatial co-occurrence, wavelets, Gabor filters, etc. These representations vary in their computational complexity and their suitability for representing different region types. Much of the work done thus far has focused on panchromatic imagery at low to moderate spatial resolutions, such as images from Landsat 1-7 which have a resolution of 15-30 m/pixel, and from SPOT 1-5 which have a resolution of 2.5-20 m/pixel. However, it is not clear which texture representation works best for the new classes of high resolution panchromatic (60-100 cm/pixel) and multi-spectral (4 bands for red, green, blue, and near infra-red at 2.4-4 m/pixel) imagery. It is also not clear how the different spectral bands should be combined. In this paper, we investigate the retrieval performance of several different texture representations using multi-spectral satellite images from IKONOS. A query-by-example framework, along with a manually chosen ground truth dataset, allows different combinations of texture representations and spectral bands to be compared. We focus on the specific problem of retrieving inhabited regions from images of urban and rural scenes. Preliminary results show that 1) the use of all spectral bands improves the retrieval performance, and 2) co-occurrence, wavelet and Gabor texture features perform comparably.

Feature selection in scientific applications

Numerous applications of data mining to scientific data involve the induction of a classification model. In many cases, the collection of data is not performed with this task in mind, and therefore, the data might contain irrelevant or redundant features that affect negatively the accuracy of the induction algorithms. The size and dimensionality of typical scientific data make it difficult to use any available domain information to identify features that discriminate between the classes of interest. Similarly, exploratory data analysis techniques have limitations on the amount and dimensionality of the data they can process effectively. In this paper, we describe applications of efficient feature selection methods to data sets from astronomy, plasma physics, and remote sensing. We use variations of recently proposed filter methods as well as traditional wrapper approaches, where practical. We discuss the general challenges of feature selection in scientific datasets, the strategies for success that were common among our diverse applications, and the lessons learned in solving these problems.

Understanding wind ramp events through analysis of historical data

As renewable resources start providing an increasingly larger percentage of our energy needs, we need to improve our understanding of these intermittent resources so we can manage them better. In the case of wind resources, large unscheduled changes in the energy output, called ramp events, make it challenging to keep the load and the generation balanced. In this paper, we show that simple statistical analysis of the wind energy generation can provide quantitative insights into these ramp events. In particular, this analysis can help answer questions such as the time period during the day when these events are likely to occur, the relative severity of positive and negative ramps, and the frequency of their occurrence.

Comparison of PDE-based non-linear anistropic diffusion techniques for image denoising

PDE-based, non-linear diffusion techniques are an effective way to denoise images.In a previous study, we investigated the effects of different parameters in the implementation of isotropic, non-linear diffusion. Using synthetic and real images, we showed that for images corrupted with additive Gaussian noise, such methods are quite effective, leading to lower mean-squared-error values in comparison with spatial filters and wavelet-based approaches. In this paper, we extend this work to include anisotropic diffusion, where the diffusivity is a tensor valued function which can be adapted to local edge orientation. This allows smoothing along the edges, but not perpendicular to it. We consider several anisotropic diffusivity functions as well as approaches for discretizing the diffusion operator that minimize the mesh orientation effects. We investigate how these tensor-valued diffusivity functions compare in image quality, ease of use, and computational costs relative to simple spatial filters, the more complex bilateral filters, wavelet-based methods, and isotropic non-linear diffusion based techniques.

Investigation of implicit active contours for scientific image segmentation.

The use of partial differential equations in image processing has become an active area of research in the last few years. In particular, active contours are being used for image segmentation, either explicitly as snakes, or implicitly through the level set approach. In this paper, we consider the use of the implicit active contour approach for segmenting scientific images of pollen grains obtained using a scanning electron microscope. Our goal is to better understand the pros and cons of these techniques and to compare them with the traditional approaches such as the Canny and SUSAN edge detectors. The preliminary results of our study show that the level set method is computationally expensive and requires the setting of several different parameters. However, it results in closed contours, which may be useful in separating objects from the background in an image.

Associating weather conditions with ramp events in wind power generation

As the percentage of wind energy on the power grid increases, the intermittent nature of this energy source can make it difficult to keep the generation and the load balanced. While wind speed forecasts can be helpful, they can often be inaccurate. In such cases, we are interested in providing the control room operators additional relevant information they can exploit to make well informed scheduling decisions. In this paper, we investigate if weather conditions in the region of the wind farms can be effective indicators of days when ramp events are likely. Using feature selection techniques from data mining, we show that some variables are more important than others and offer the potential of data-driven predictive models for days with ramp events.