We present a method for foreground/background video segmentation (change detection) in real-time that can be used, in applications such as background subtraction or analysis of surveillance cameras. Our approach implements a probabilistic segmentation based on the Quadratic Markov Measure Field models. This framework regularizes the likelihood of each pixel belonging to each one of the classes (background or foreground). We propose a new likelihood that takes into account two cases: the first one is when the background is static and the foreground might be static or moving (Static Background Subtraction), the second one is when the background is unstable and the foreground is moving (Unstable Background Subtraction). Moreover, our likelihood is robust to illumination changes, cast shadows and camouflage situations. We implement a parallel version of our algorithm in CUDA using a NVIDIA Graphics Processing Unit in order to fulfill real-time execution requirements.

Change detection by probabilistic segmentation from monocular view

Accomplishments and challenges of computer stereo vision

Segmentation and grouping of image elements is required to proceed with image recognition. Due to the fact that the images are two dimensional (2D) representations of the real three dimensional (3D) scenes, the information of the third dimension, like geometrical relations between the objects that are important for reasonable segmentation and grouping, are lost in 2D image representations. Computer stereo vision implies on understanding information stored in 3D-scene. Techniques for stereo computation are observed in this paper. The methods for solving the correspondence problem in stereo image matching are presented. The process of 3D-scene reconstruction from stereo image pairs and extraction of parameters important for image understanding are described. Occluded and surrounding areas in stereo image pairs are stressed out as important for image understanding.

http://ieeexplore.ieee.org/iel5/5599415/5606063/05606082.pdf

A fast color information setup based on evolutionary programming (EP) like particles swarm optimization (EPSO) for the manipulator control system is examined in this paper. The first step for a manipulator to grasp and place color objects into the correct location is to correctly identify the RGB or the corresponding hue, saturation, value (HSV) color model. The commonly used method to determine the thresholds of HSV range is manual tuning, but it is time-consuming to find the best boundary to segment the color image. This paper proposes a new method to learn color information, which is executed by semiautomatic learning. At first, the watershed algorithm incorporates user interactions to segment the color image and obtain the target image. Then, the comparison between the target image and the original image is utilized to build a lookup table (LUT) of color information, where three HSV thresholds are learned by PSO methods. Because the convergence speed of well-known PSO algorithms is slow and may be stuck in the local minimum, we present the EPSO method realized by applying EP to the PSO method. Moreover, a novel approach is investigated to escape the local minimum supposing the particles are stuck in the local minimum. Finally, both the numerical and experimental results demonstrate that the developed approach can not only rapidly learn the thresholds to segment a color image but can also jump out the local minimum.

A Fast Color Information Setup Using EP-Like PSO for Manipulator Grasping Color Objects

This work addresses two main problems: (i) localization of two cameras observing a 3D scene composed by planar structures; (ii) recovering of the original structure of the scene, i.e. the scene reconstruction and segmentation stages. Although there exist some work intending to deal with these problems, most of them are based on: epipolar geometry, non-linear optimization, or linear systems that do not incorporate geometrical consistency.

In this paper, we propose an iterative linear algorithm exploiting geometrical and algebraic constraints induced by rigidity and planarity in the scene. Instead of solving a complex multi-linear problem, we solve iteratively several linear problems: coplanar features segmentation, planar projective transferring, epipole computation, and all plane intersections. Linear methods allow our approach to be suitable for real-time localization and 3D reconstruction. Furthermore, our approach does not compute the fundamental matrix; therefore it does not face stability problems commonly associated with explicit epipolar geometry computation.

Automatic Camera Localization, Reconstruction and Segmentation of Multi-planar Scenes Using Two Views

https://www.cimat.mx/~mrivera/journals/vigueras_seghomographics_pattrecg10ms.pdf

Javier Flavio Vigueras

Papers

Registration and interactive planar segmentation for stereo images of polyhedral scenes

Automatic Camera Localization, Reconstruction and Segmentation of Multi-planar Scenes Using Two Views