Walter Izquierdo Guerra

Bio: Walter Izquierdo Guerra is an academic researcher. The author has contributed to research in topics: Background subtraction. The author has an hindex of 1, co-authored 1 publications receiving 5 citations.

A Novel Approach to Robust Background Subtraction

Abstract: Nowadays, background model does not have any robust solution and constitutes one of the main problems in surveillance systems. Researchers work in several approaches in order to get better background pixel models. This is a previous step to apply the background subtraction technique and results are not as good as people expect. We propose a novel approach to the background subtraction technique without a strong dependence of the background pixel model. We compare our algorithm versus Wallflower algorithm [1]. We use the standards deviation of the difference as an independent initial parameter to reach an adjusted threshold for every moment. This solution is more efficient computationally than the wallflower approach.

Background Subtraction Based on a New Fuzzy Mixture of Gaussians for Moving Object Detection

Abstract: Moving foreground detection is a very important step for many applications such as human behavior analysis for visual surveillance, model-based action recognition, road traffic monitoring, etc Background subtraction is a very popular approach, but it is difficult to apply given that it must overcome many obstacles, such as dynamic background changes, lighting variations, occlusions, and so on In the presented work, we focus on this problem (foreground/background segmentation), using a type-2 fuzzy modeling to manage the uncertainty of the video process and of the data The proposed method models the state of each pixel using an imprecise and adjustable Gaussian mixture model, which is exploited by several fuzzy classifiers to ultimately estimate the pixel class for each frame More precisely, this decision not only takes into account the history of its evolution, but also its spatial neighborhood and its possible displacements in the previous frames Then we compare the proposed method with other close methods, including methods based on a Gaussian mixture model or on fuzzy sets This comparison will allow us to assess our method’s performance, and to propose some perspectives to this work

Optimal Threshold and LoG Based Feature Identification and Tracking of Bat Flapping Flight

Abstract: Flapping flight observed in bats offers a promising model for bio-inspiration of small air vehicles because of their high maneuverability, load carrying capacity, and energy efficiency. However, the flight mechanics of bats is very complex due to the highly articulated wing skeleton and the anisotropic, internally-actuated wing membrane. As a result of these complexities, the shape of bat wings can deform quickly and substantially which causes periodic occlusions and large baseline nonlinear deformations of point trajectories in image space. Tracking these points in image space is difficult because the resolution of the images (720 1280) and the frame rate (120Hz) used in these experiments are substantially lower than those used historically. This paper presents a computational approach that utilizes a novel combination of Laplacian-of-Gaussian (LoG) filtering and optimal threshold segmentation to locate markers in images. Using images from 32 cameras, our technique achieved an average hit rate of 83%, with an average false rate of 12%. Our algorithm is shown to perform better than other techniques, including those based on SIFT or LoG filtering alone. In addition to the improved feature detection algorithm, optical flow based tracking is bootstrapped with a spatially recursive unscented Kalman filter to track the identified points during state estimation. The spatially recursive estimator returns as many or more correct correspondences when compared to the standard unscented Kalman filter.

Background division, a suitable technique for moving object detection

Abstract: Nowadays, background model does not have any robust solution and constitutes one of the main problems in surveillance systems. Researchers are working in several approaches in order to get better background pixel models. This is a previous step to apply the background subtraction technique and results are not as good as expected. We concentrate our efforts on the second step for segmentation of moving objects and we propose background division to substitute background subtraction technique.This approach allows us to obtain clusters with lower intraclass variability and higher inter-class variability, this diminishes confusion between background and foreground, pixels. We compared results using our background division approach versus wallflowers algorithm as the baseline to compare.

Smooth Foreground-Background Segmentation for Video Processing

Abstract: We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques regard the pixels in an image as independent and disregard the fundamental concept of smoothness. In contrast, we model smoothness of the foreground and background with a Markov random field, in such a way that it can be globally optimized at video frame rate. As a background model, the mixture-of-Gaussian (MOG) model is adopted and enhanced with several improvements developed for other background models. Experimental results show that the MOG model is still competitive, and that segmentation with the smoothness prior outperforms other methods.

Performance comparison of the Teknomo-Fernandez algorithm on the RGB and HSV colour spaces

Abstract: Segmentation of the foreground objects is the primary step in many video analysis applications. The accuracy of the segmentation is dependent on an accurate background image that is used for background subtraction. The Teknomo-Fernandez (TF) algorithm is an efficient algorithm that quickly generates a good background image. A previous study showed the extendibility of the TF algorithm to higher number of frames per tournament, with the original 3 frames TF 3L to be the most efficient and best configuration for actual implementation. In this study, we examine the performance of the TF algorithm on both RGB and HSV colour spaces using the TF 3, 4 configuration and the Wallflower dataset. A simple background subtraction with threshold is implemented. The performances are measured numerically using the number of false negative and false positive pixel count against the provided ideal foreground image. The results show that the TF algorithm implemented using both RGB and HSV generates accurate background images in a wide range of video settings. The HSV implementation exhibits higher accuracies than the RGB implementation for majority of the test videos with the cost of an increase in processing time.