Pradipta Kumar Nanda

A Change Information Based Fast Algorithm for Video Object Detection and Tracking

In this paper, we present a novel algorithm for moving object detection and tracking. The proposed algorithm includes two schemes: one for spatio-temporal spatial segmentation and the other for temporal segmentation. A combination of these schemes is used to identify moving objects and to track them. A compound Markov random field (MRF) model is used as the prior image attribute model, which takes care of the spatial distribution of color, temporal color coherence and edge map in the temporal frames to obtain a spatio-temporal spatial segmentation. In this scheme, segmentation is considered as a pixel labeling problem and is solved using the maximum a posteriori probability (MAP) estimation technique. The MRF-MAP framework is computation intensive due to random initialization. To reduce this burden, we propose a change information based heuristic initialization technique. The scheme requires an initially segmented frame. For initial frame segmentation, compound MRF model is used to model attributes and MAP estimate is obtained by a hybrid algorithm [combination of both simulated annealing (SA) and iterative conditional mode (ICM)] that converges fast. For temporal segmentation, instead of using a gray level difference based change detection mask (CDM), we propose a CDM based on label difference of two frames. The proposed scheme resulted in less effect of silhouette. Further, a combination of both spatial and temporal segmentation process is used to detect the moving objects. Results of the proposed spatial segmentation approach are compared with those of JSEG method, and edgeless and edgebased approaches of segmentation. It is noticed that the proposed approach provides a better spatial segmentation compared to the other three methods.

Modified possibilistic fuzzy C-means algorithms for segmentation of magnetic resonance image

Graphical abstractDisplay Omitted HighlightsSimultaneous estimation of bias field and pixel labels of MR images is focus of work.We have attempted to model the tissue class uncertainty using the notion of fuzziness and bias field by the typicality measures.Joint effect of fuzzy and typicality measure have been taken care to propose three new schemes namely BCPFCM, BCPNFCM and BCSP-NFCM.These schemes have been able to estimate the bias field and obtain the segmented images. The brain magnetic resonance (MR) image has an embedded bias field. This field needs to be corrected to obtain the actual MR image for classification. Bias field, being a slowly varying nonlinear field, needs to be estimated. In this paper, we have proposed three schemes and in turn three algorithms to segment the given MR image while estimating the bias field. The problem is compounded when the MR image is corrupted with noise in addition to the inherent bias field. The notions of possibilistic and fuzzy membership have been combined to take care of the modeling of the bias field and noise. The weighted typicality measure together with the weighted fuzzy membership has been used to model the image. The above resulted in the proposed Bias Corrected Possibilistic Fuzzy C-Means (BCPFCM) strategy and the algorithm. Further reinforcing the neighbourhood data to the modeling aspect has resulted in the two other strategies namely Bias Corrected Possibilistic Neighborhood Fuzzy C-Means (BCPNFCM) and Bias Corrected Separately weighted Possibilistic Neighborhood Fuzzy C-Means (BCSPNFCM). The proposed algorithms have successfully been tested with synthetic data with bias field of low and high spatial frequency. Noisy brain MR images with Gaussian Noise of varying strength have been considered from the BrainWeb database. The algorithms have also been tested on real brain MR data set with axial and sagittal view and it has been found that the proposed algorithms produced segmentation results with less percentage of misclassification errors as compared to the Bias Corrected Fuzzy C-Means (BCFCM) algorithm proposed by Ahmed et al. 4. The performance of the proposed algorithms has been compared with algorithms from other paradigm in the context of Tanimotos index.

Entropy based region selection for moving object detection

This article addresses a problem of moving object detection by combining two kinds of segmentation schemes: temporal and spatial. It has been found that consideration of a global thresholding approach for temporal segmentation, where the threshold value is obtained by considering the histogram of the difference image corresponding to two frames, does not produce good result for moving object detection. This is due to the fact that the pixels in the lower end of the histogram are not identified as changed pixels (but they actually correspond to the changed regions). Hence there is an effect on object background classification. In this article, we propose a local histogram thresholding scheme to segment the difference image by dividing it into a number of small non-overlapping regions/windows and thresholding each window separately. The window/block size is determined by measuring the entropy content of it. The segmented regions from each window are combined to find the (entire) segmented image. This thresholded difference image is called the change detection mask (CDM) and represent the changed regions corresponding to the moving objects in the given image frame. The difference image is generated by considering the label information of the pixels from the spatially segmented output of two image frames. We have used a Markov Random Field (MRF) model for image modeling and the maximum a posteriori probability (MAP) estimation (for spatial segmentation) is done by a combination of simulated annealing (SA) and iterated conditional mode (ICM) algorithms. It has been observed that the entropy based adaptive window selection scheme yields better results for moving object detection with less effect on object background (mis) classification. The effectiveness of the proposed scheme is successfully tested over three video sequences.

Parallel genetic algorithm based adaptive thresholding for image segmentation under uneven lighting conditions

In this paper, two adaptive thresholding schemes have been proposed. These two schemes are based on adaptive selection of windows based on the proposed window merging and window growing. Windows are selected based on the entropy and feature entropy criterion. PGA and MMSE based segmentation schemes have been proposed to segment the windows selected a priori. The efficacy of the proposed approaches have been compared with the Huangs pyramidal window merging approach. It is found that the proposed approaches exhibited improved performance in the context of accuracy of segmentation.

Parallelized Crowding Scheme Using a New Interconnection Model

In this article, a new interconnection model is proposed for Parallel Genetic Algorithm based crowding scheme. The crowding scheme is employed to maintain stable subpopulations at niches of a multi modal nonlinear function. The computational burden is greatly reduced by parallelizing the scheme based on the notion of coarse grained parallelization. The proposed interconnection model with a new crossover operator known as Generalized Crossover (GC) was found to maintain stable subpopulation for different classes and its performance was superior to that of the with two point crossover operators. Convergence properties of the algorithm is established and simulation results are presented to demonstrate the efficacy of the scheme.

Moving object detection using spatio-temporal multilayer compound Markov Random Field and histogram thresholding based change detection

In this article, we propose a Multi Layer Compound Markov Random Field (MLCMRF) Model to spatially segment different image frames of a given video sequence. The segmented image frames are combined with the change between the frames to detect the moving objects from a video. The proposed MLCMRF uses five Markov models in a single framework, one in spatial direction using color feature, four in temporal direction (using two color features and two edges/line fields). Hence, the proposed MLCMRF is a combination of spatial distribution of color, temporal color coherence and edge maps in the temporal frames. The use of such an edge preserving model helps in enhancing the object boundary in spatial segmentation and hence can detect moving objects with less effect of silhouette. A difference between the frames is used to generate the CDM and is subsequently updated with the previous frame video object plane (VOP) and the spatial segmentation of the consecutive frames, to detect the moving objects from the target image frames. Results of the proposed spatial segmentation approach are compared with those of the existing state-of-the-art techniques and are found to be better.

Bias field estimation and segmentation of MR image using modified fuzzy-C means algorithms

The brain Magnetic Resonance (MR) image has an embedded bias field. This field need to be corrected to obtain the actual MR image for classification. In this paper, we have proposed three new schemes to simultaneously estimate the bias field and obtain segmentation. These algorithms are modification of Ahmed et al.s [4] Bias Corrected FCM (BCFCM) algorithm. The first proposed scheme considers the weighted typicality measure for the data set. This results in Bias Corrected Possibilistic FCM (BCPFCM) algorithm. Besides, to improve the segmentation accuracy, we have considered the joint effect of weighted membership and typicality of the neighborhood pixels resulting in Bias Corrected Possibilistic Neighborhood FCM (BCPNFCM) algorithm. The third notion considers the weighted membership and weighted typicality separately weighted for the neighboring pixels in addition to the pixel in consideration. The corresponding algorithm is Bias Corrected Separately weighted Possibilistic Neighborhood FCM (BCSPNFCM) algorithm. The proposed algorithms have successfully been tested on synthetic image and also found to produce appreciable results in case of axial brain MR image data as compared to BCFCM algorithm.

Embedded local feature based background modeling for video object detection

Background modeling has been one of the approaches for detecting foreground in a video. The challenge is when some of the entities of background are dynamic instead of being static. In this paper, we propose a feature embedding scheme to model background having some dynamic objects and varying illumination conditions. The two local feature extracting operators such as Local Binary Pattern (LBP) operator and Gabor filter have been appropriately embedded to model texture backgrounds with dynamic entities. The embedding has been in non linear frame work and the notion of information theoretic measure has been used to take care of the above two condition in the background. This background model has learned to efficiently model the background of the video. The performance of the proposed feature embedded algorithm has been found to be better than those of Huerta et al.s [11] algorithm and Heikkila et al.s [12] algorithm. Simulation results have been presented for video frames of PETS sequences.

Detection of Earth Surface Cracks Using Parallel Genetic Algorithm Based Thresholding

A Parallel Genetic Algorithm (PGA) based scheme for detection of cracks in images is proposed. The proposed segmentation scheme is a feature based one and the optimum threshold is determined from the the feature histogram. Parallel Genetic Algorithm (PGA) based clustering is proposed to detect two peaks and thereafter the optimal threshold is determined by Minimum Mean Square Error (MMSE) based strategy. The proposed method has been tested successfully with various images. The performance of the proposed method is compared with that of Otsu’s, Kwon’s, Feature Less(FL) and Feature Based(FB) approaches and it is found that the proposed method outperformed all these methods for crack detection.

Variable Variance Adaptive Mean-Shift and possibilistic fuzzy C-means based recursive framework for brain MR image segmentation

Abstract Segmentation of brain MR image tissues has been a challenge because of the embedded nonlinear bias field acquired during the image acquisition process. This problem is further compounded due to the presence of noise. In order to deal with such issues, we have proposed a Variable Variance Adaptive Mean-Shift (VVAMS) algorithm which not only removes noise but also reinforces the clustering attribute by its mode seeking ability. We have formulated the problem for jointly estimating the bias field, tissue class labels and noise free pixels. Since, all the parameters are unknown and interdependent it is hard to obtain optimal estimates. In this regard, we have proposed a recursive framework to obtain the estimates of the parameters, which are partial optimal ones. In the first step of the recursion, the possibilistic fuzzy clustering algorithms has been applied to determine different clusters and bias field. These clusters are noisy and hence in the second step of the recursion, VVAMS algorithm has been applied on each cluster to eliminate noise and reinforce the modes of the clusters. These two steps constitute one combined iteration. Theoretically, the recursive framework is supposed to converge after large number of recursions but in practice it converges after a few iterations. This proposed scheme has successfully been tested with 50 biased noisy slices from Brainweb database and some real brain MR image data from IBSR database. The results have been quantitatively evaluated by percentage of misclassification, Rand Index, t -test, fuzzy partition coefficient ( V pc ), fuzzy partition entropy ( V pe ) and Tanimoto index. The quantitative evaluations of the tissue class labels demonstrate the superiority of proposed scheme over the existing methods.