The Experts below are selected from a list of 7353 Experts worldwide ranked by ideXlab platform
Rustam Stolkin - One of the best experts on this subject based on the ideXlab platform.
-
Particle Filter Tracking of Camouflaged Targets by Adaptive Fusion of Thermal and Visible Spectra Camera Data
IEEE Sensors Journal, 2014Co-Authors: Mohammed Talha, Rustam StolkinAbstract:This paper presents a method for tracking a moving target by fusing bi-modal visual information from a deep infra-red thermal imaging camera and a conventional visible spectrum color camera. The tracking method builds on well-known methods for color-based tracking using particle filtering, but it extends these to handle fusion of color and thermal information when evaluating each particle. The key innovation is a method for continuously relearning local background models for each particle in each imaging modality, comparing these against a model of the foreground object being tracked, and thereby adaptively weighting the data fusion process in favor of whichever imaging modality is currently the most discriminating at each Successive Frame. The method is evaluated by testing on a variety of extremely challenging video sequences, in which people and other targets are tracked past occlusion, clutter, and distracters causing severe and sustained camouflage conditions in one or both imaging modalities.
-
Adaptive fusion of infra-red and visible spectra camera data for particle filter tracking of moving targets
2012 IEEE Sensors, 2012Co-Authors: Mohammed Talha, Rustam StolkinAbstract:This paper presents a method for tracking a moving target by fusing bi-modal visual information from a deep infrared thermal imaging camera, and a conventional visible spectrum colour camera. The tracking method builds on well-known methods for colour-based tracking using particle filtering, but extends these to handle fusion of colour and thermal information when evaluating each particle. The key innovation is a method for continuously relearning local background models for each particle in each imaging modality, comparing these against a model of the foreground object being tracked, and thereby adaptively weighting the data fusion process in favour of whichever imaging modality is currently the most discriminating at each Successive Frame. The method is evaluated by testing on a variety of extremely challenging video sequences, in which people and other targets are tracked past occlusion, clutter and distracters causing severe and sustained camouflage conditions in one or both imaging modalities.
-
Continuous Machine Learning in Computer Vision - Tracking with Adaptive Class Models
Scene Reconstruction Pose Estimation and Tracking, 2007Co-Authors: Rustam StolkinAbstract:A fundamental (and popular) task in computer and robot vision is the tracking of an object which moves relative to the camera, essentially segmenting the object region of each Successive Frame. There are a great many published approaches, which are often variations, combinations or advances on well known techniques such as background subtraction, image differencing, predictive filtering and Bayesian estimation. Generally, these techniques rely on simple models of the tracked object and/or models of the background. Many techniques in computer vision derive from ideas previously established in the pattern recognition community, where it is usual to learn models offline from historical training data sets. Hence these models, once learned, typically remain static during the online tracking process. Such static models are ultimately of limited robustness in real world computer vision tracking scenarios where the appearance of both the background and the tracked object may change significantly and frequently due to camera motion (resulting in background change), object motion or deformation, introduction and removal of additional objects and clutter (e.g. passing traffic on a road) and changes in lighting and visibility conditions (either changes in ambient conditions or, for example, spotlights mounted on and moving with an underwater robot). In contrast, this chapter will discuss a variety of tracking algorithms and techniques which are highly adaptable. These techniques have in common that they incorporate models which are continuously relearned from new input image Frames while simultaneously performing tracking on those Frames. These techniques are powerful, in that they offer a way of successfully adapting to a changing environment. However, the price paid for adaptability can be a tendency towards certain kinds of instability. In simple terms, any system that continuously relearns (e.g. models of the tracked object and the background), has a risk of relearning incorrectly (e.g. relearning that background looks like object). Therefore, this chapter will also discuss various techniques for automatically detecting and correcting such errors as they occur, and survey techniques by which algorithms might continuously monitor their own performance. It is also useful to consider continuous machine learning techniques in vision in terms of the rate of relearning. Firstly we will consider well established algorithms which incrementally re-learn models, very gradually, over many Frames. Later we will look at very recent work,
Biswa Ranjan Swain - One of the best experts on this subject based on the ideXlab platform.
-
Simulation based algorithm for tracking fish population in unconstrained underwater
2015 International Conference on Microwave Optical and Communication Engineering (ICMOCE), 2015Co-Authors: Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Sakuntala Mahapatra, Biswa Ranjan SwainAbstract:Tracking of object in underwater is a emerging idea. There are several type of approaches used for this but they have high computational complexity. But scientist needs to study fish populations underwater in different environmental conditions. In this paper we proposed a simple algorithm for tracking and detecting multi moving fishes. A huge number of fishes can be tracked by comparing its mean in the Successive Frame of the video. The obtained output states a measurement of the difference of two mean values. The object window contains the matrix of the intensity value. Then this value is transformed into a set of feature vector. Finally the above two set of features is compared in the Successive Frame for a good match to its nearest locality. The MatLab 8.0 simulation result shows that the proposed method is capable of accurately detecting with high detection rate as compared to existing approaches with noisy and dense environment.
-
Multi object tracking using multi threaded parallel approach
2015 International Conference on Electrical Electronics Signals Communication and Optimization (EESCO), 2015Co-Authors: Biswa Ranjan Swain, Sumant Kumar Mohapatra, Anuja Kumar Acharya, Sushil Kumar MahapatraAbstract:In this Paper, we proposed a method for tracking multi object using multithreading concept in a video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi object using multithreading concept by comparing it's mean in the Successive Frame of the video. It is observed that an object can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving object quickly.
-
Multi moving bacteria and WBC tracking using MTP approach for proper diagnosis in blood
2015 IEEE Power Communication and Information Technology Conference (PCITC), 2015Co-Authors: Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Biswa Ranjan Swain, Sukant Kumar BeheraAbstract:In this Paper, we proposed a method for tracking multi moving bacteria and white blood cell (WBC) using Multi threading parallel (MTP) concept in a microscopic blood cell video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi moving bacteria using multi threading concept by comparing its mean in the Successive Frame in the video. It is observed that bacteria can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving bacteria and WBC quickly for proper diagnosis.
-
A Simulation based model for bacteria tracking using MTP approach in blood
2015 International Conference on Communications and Signal Processing (ICCSP), 2015Co-Authors: Biswa Ranjan Swain, Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Sukant BeheraAbstract:In this Paper, we proposed a method for tracking multi moving bacteria and white blood cell (WBC) using Multi threading parallel (MTP) concept in a microscopic blood cell video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi moving bacteria using multi threading concept by comparing its mean in the Successive Frame in the video. It is observed that a bacteria can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving bacteria and WBC quickly as compared to the existing approaches for proper diagnosis.
-
Simulation Based Algorithm for Tracking Multi-Moving Object Using Gaussian Filtering with Lucas-Kanade Approach
Procedia Computer Science, 2015Co-Authors: Sakuntala Mahapatra, Sumant Kumar Mohapatra, Biswa Ranjan Swain, Sushil Kumar MahapatraAbstract:Abstract In this paper, we proposed a method which is used for tracking and detecting multi moving object using Gaussian filtering with Lucas-Kanade approach in a flying bird video. The proposed method is based on output from mean of one Frame compared with the result of another Frame obtained from optical flow estimator using Gaussian filtering to track the original object. Then after the resulting output of the comparator is fed to perform morphological closing to structuring the elements using strel function .The model is designed such to track multi moving object using Lucas-kanade approach by comparing it's mean in the Successive Frame of the video with the help of Gaussian filtering. From our knowledge, this proposed method is capable of detecting multi moving object quickly than recently used statistical approaches and also work in noisy environment.
Sushil Kumar Mahapatra - One of the best experts on this subject based on the ideXlab platform.
-
Multimoving Human Sperm Tracking Using CGM-CS Approach and Comparative Analysis for Proper Diagnosis in Infertility
2016 2nd International Conference on Computational Intelligence and Networks (CINE), 2016Co-Authors: Sushil Kumar Mahapatra, Sumant Kumar Mohapatra, Sakuntala Mahapatra, Rabindra BhojrayAbstract:In this paper, we introduced an algorithm for tracking and detecting multi moving human sperm using Course Grained Multi Threading Cam Shift (CGM-CS) approach in a microscopic human sperm moving video. This method is fully based on adaptive Cam Shift algorithm using color model. This algorithm is design to track and detect the sperms by using multi threading concept. The multi threading concept is compared continuously to its mean value in the Successive Frame in the appropriate video. The result obtained by the proposed method is also compared with the Maximum Intensity Region (MIR) algorithm, Lukas-Kanade (LK) algorithm and Kernel Based (KB) algorithm. Experimental results demonstrate that the CGM-CS algorithm is capable of tracking the sperm with high detection rate with minimum time taken as compared to existing approaches.
-
Simulation based algorithm for tracking fish population in unconstrained underwater
2015 International Conference on Microwave Optical and Communication Engineering (ICMOCE), 2015Co-Authors: Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Sakuntala Mahapatra, Biswa Ranjan SwainAbstract:Tracking of object in underwater is a emerging idea. There are several type of approaches used for this but they have high computational complexity. But scientist needs to study fish populations underwater in different environmental conditions. In this paper we proposed a simple algorithm for tracking and detecting multi moving fishes. A huge number of fishes can be tracked by comparing its mean in the Successive Frame of the video. The obtained output states a measurement of the difference of two mean values. The object window contains the matrix of the intensity value. Then this value is transformed into a set of feature vector. Finally the above two set of features is compared in the Successive Frame for a good match to its nearest locality. The MatLab 8.0 simulation result shows that the proposed method is capable of accurately detecting with high detection rate as compared to existing approaches with noisy and dense environment.
-
Multi object tracking using multi threaded parallel approach
2015 International Conference on Electrical Electronics Signals Communication and Optimization (EESCO), 2015Co-Authors: Biswa Ranjan Swain, Sumant Kumar Mohapatra, Anuja Kumar Acharya, Sushil Kumar MahapatraAbstract:In this Paper, we proposed a method for tracking multi object using multithreading concept in a video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi object using multithreading concept by comparing it's mean in the Successive Frame of the video. It is observed that an object can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving object quickly.
-
Multi moving bacteria and WBC tracking using MTP approach for proper diagnosis in blood
2015 IEEE Power Communication and Information Technology Conference (PCITC), 2015Co-Authors: Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Biswa Ranjan Swain, Sukant Kumar BeheraAbstract:In this Paper, we proposed a method for tracking multi moving bacteria and white blood cell (WBC) using Multi threading parallel (MTP) concept in a microscopic blood cell video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi moving bacteria using multi threading concept by comparing its mean in the Successive Frame in the video. It is observed that bacteria can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving bacteria and WBC quickly for proper diagnosis.
-
A Simulation based model for bacteria tracking using MTP approach in blood
2015 International Conference on Communications and Signal Processing (ICCSP), 2015Co-Authors: Biswa Ranjan Swain, Sumant Kumar Mohapatra, Sushil Kumar Mahapatra, Sukant BeheraAbstract:In this Paper, we proposed a method for tracking multi moving bacteria and white blood cell (WBC) using Multi threading parallel (MTP) concept in a microscopic blood cell video. This method is based on continuously adaptive mean shift algorithm using color model which is designed to track multi moving bacteria using multi threading concept by comparing its mean in the Successive Frame in the video. It is observed that a bacteria can be tracked in the next Frame, when the mean shift vector converges. Simulation result shows that the proposed method is capable of detecting multi moving bacteria and WBC quickly as compared to the existing approaches for proper diagnosis.
Vijay Kumar Sharma - One of the best experts on this subject based on the ideXlab platform.
-
Methods for Feature Selection and Appearance Model in Visual Object Tracking.
2019Co-Authors: Vijay Kumar SharmaAbstract:The objective of visual object tracking is to find the location, orientation and scale (size) of an object in Successive video Frames. There are several applications of object tracking in computer vision. Some of them include human-computer interaction (HCI), visual surveillance, action recognition, vehicle navigation, video compression and face recognition. The object tracking has been an active research area due to several challenges involved. One of the most encountered challenges is the object appearance variation which occurs from one Frame to another in the form of deformation, motion blur, pose change, and illumination variation. Scale change, partial occlusion and clutter are the other challenges that an object tracking algorithm has to deal with. Therefore, the appearance model is the most important component in the visual object tracking. Based on the learning mechanism used, a tracker can be called as generative or discriminative. The generative tracking method learns an object appearance model, composed of different object variations, without considering its surrounding background.The discriminative object tracking is based of construction of discriminative classifier using both target instance as well as the instances from the surrounding background. An object tracker can use both mechanisms for better tracking performance. This research work focuses on discriminative feature selection and online appearance model construction for robust visual object tracking. A fast online algorithm to select discriminative feature in multiple instance learning (MIL) Framework is proposed. The algorithm is based on maximizing the discriminative classifier score. The tracking performance is better than the existing features election methods in this Framework. Unlike other methods, it does not use sigmoid function, and therefore, it is suitable for VLSI implementation. The use of kernel trick on Haar-like features for target tracking is introduced. Furthermore, use of Haar-features in half target spaces is explored. In the same MIL Framework, to get the actual target size in Successive video Frames, a scaling strategy is applied. By having the feature matching using kernel, Haar-features in half target spaces and scale adaptation method in a single tracking Framework, a better tracking performance is achieved, as compared to the state-of-the-art trackers. Visual tracking algorithm using discriminative and generative appearances is explored. The discriminative model is a linear support vector machine(SVM) classifier trained in the first video Frame only. In the Successive Frames, online appearance model is learned using similarity measure between newly tracked sample, negative examples and parameter of the trained SVM. Based on learned appearance model, a likelihood model is constructed for selecting a tracking instance. The appearance model is also learned on HOG features using discriminative parameter update. A training algorithm is proposed to online learn the parameter vector of SVM when new examples are available in each Frame of a video. This is an iterative method which is based on maximizing the sum of projection lengths of a positive example and a negative example which are closest to the hyperplane formed by parameter to be updated. Using learned parameter vector, likelihood model is constructed and applied to get the tracking instance. An object representation is also learned based on sparse DCT coefficients. The learned structure is to lower the effect of occlusion while preventing the basic appearance. Using sparse 2-dimensional discrete cosine transform (2D DCT) coefficients as discriminative features, a visual object tracker is proposed. A simple method to select the discriminative DCT features is also proposed. The discriminative coefficients are selected in each Frame based on their mean of probabilities with parameters of positive (target) and negative (background) instances. A discriminative classifier is constructed by using selected features. Some intermediate tracking instances are obtained by (a) computing feature similarity using kernel and (b) finding the maximum classifier score. The final tracked instance is obtained by comparing their 1-dimensional array correlation with the raw pixel based appearance models. The final tracked instance is also obtained based on score of adiscriminative classifier learned in Successive Frame susing HOG features. A method to train a weight vector is proposed. It is based on kernel similarity measure between parameter vector and examples. In each video Frame, the parameter vector is updatedif(a)thereceivedpositiveexamplehaslowersimilarityscorethanthatofprevious positive example with lowest score and(b)received negative example has higher similarity score than that of previous negative example with highest score. The similarity scores of such example vectors (positive and negative) are also used to construct a discriminative model. Also, Successive addition of tracked samples weighted with their similarity scores in each Frame forms a raw pixel based appearance model. The proposed likelihood model for finding the target in next Frame is composed of learned discriminative and pixel based appearance models. A modified parameter learning method seek to maximize the score as well as margin between the examples. The appearance model learned using HOG features gives better tracking performance. The tracking accuracy of all the proposed methods is better than state-of-the-art trackers in a number of challenging video sequences.
-
Online Training of Discriminative Parameter for Object Tracking-by-Detection in a Video
Soft Computing in Data Analytics, 2018Co-Authors: Vijay Kumar Sharma, Bibhudendra Acharya, Kamalakanta MahapatraAbstract:In this chapter, an online training algorithm to update a discriminative parameter vector is proposed. The initial discriminative parameter is obtained by training an SVM in the first video Frame only. The positive example for SVM training is the initial target object, while the negative examples are cropped at some distance away from the target object. In the Successive video Frames, the parameter vector is updated based on the similarity score between the parameter vector and the vector corresponding to tracked object. The similarity score is measured using a Gaussian kernel. The learned parameter is used to construct a likelihood model. Using particle filter Framework, a number of target candidates are cropped. The tracked object in each Successive Frame is the target candidate corresponding to the highest likelihood value.
-
Visual object tracking based on sequential learning of SVM parameter
Digital Signal Processing, 2018Co-Authors: Vijay Kumar Sharma, Kamalakanta MahapatraAbstract:Abstract In this paper, a training algorithm is proposed to online (sequentially) learn the SVM based parameter. The proposed online learning method is used to construct discriminative classifier for visual object tracking application, where new examples are available in each Successive Frame of a video. The iterative method is based on maximizing the magnitude of sum of projection values of a positive example and a negative example which are closest to the hyperplane formed by parameter to be updated. In the proposed training Framework, even if there is non-accurate labeling of the training examples (which are received online), it is possible to learn the parameter that ensures maximum value from the classification function. The learned parameter along with some examples which are nearest to hyperplane are used for the construction of object likelihood model. Using likelihood model, tracking instance most similar to the target is selected, where the target candidates are generated using particle filter Framework. An object representation is also learned based on sparse DCT coefficients. This representation contains the basic structure of the target appearance. The proposed object tracking method performs better than state-of-the-art trackers in a number of challenging video sequences. When high dimension feature vectors are used, instead of simple raw pixels based feature vectors, to represent the training examples, the performance of the object tracking is better in a number of video sequences even without integrating sparse DCT coefficient based object representation as an additional model.
Satoshi Nakamura - One of the best experts on this subject based on the ideXlab platform.
-
modeling Successive Frame dependencies with hybrid hmm bn acoustic model
International Conference on Acoustics Speech and Signal Processing, 2005Co-Authors: Konstantin Markov, Satoshi NakamuraAbstract:Most current state-of-the-art speech recognition systems use the hidden Markov model (HMM) for modeling the acoustical characteristics of a speech signal. In the first-order HMM, speech data are assumed to be independently and identically distributed (iid), meaning that there is no dependency between neighboring feature vectors. Another assumption is that the current vector depends only on the current HMM state. In practice, however, these assumptions are not true. We describe a hybrid HMM/BN (Bayesian network) acoustic model, where the dependency of the current speech vector on the previous vector and on the previous state is also learned and used in speech recognition. This is possible because the state probability distribution is modeled by a BN. Previous instances of the state and speech feature vector are represented by additional variables of the BN and the probabilistic dependencies between them, and their current instances are learned during training. During recognition, the likelihood of the current feature vector is inferred from the BN where the previous state and previous feature vector are treated as hidden. We have evaluated this hybrid HMM/BN model with our LVCSR system by phoneme recognition and by large-vocabulary continuous word recognition tasks. In both cases, we observed improved performance over the conventional Gaussian mixture HMM.
-
ICASSP (1) - Modeling Successive Frame dependencies with hybrid HMM/BN acoustic model
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics Speech and Signal Processing 2005., 1Co-Authors: Konstantin Markov, Satoshi NakamuraAbstract:Most current state-of-the-art speech recognition systems use the hidden Markov model (HMM) for modeling the acoustical characteristics of a speech signal. In the first-order HMM, speech data are assumed to be independently and identically distributed (iid), meaning that there is no dependency between neighboring feature vectors. Another assumption is that the current vector depends only on the current HMM state. In practice, however, these assumptions are not true. We describe a hybrid HMM/BN (Bayesian network) acoustic model, where the dependency of the current speech vector on the previous vector and on the previous state is also learned and used in speech recognition. This is possible because the state probability distribution is modeled by a BN. Previous instances of the state and speech feature vector are represented by additional variables of the BN and the probabilistic dependencies between them, and their current instances are learned during training. During recognition, the likelihood of the current feature vector is inferred from the BN where the previous state and previous feature vector are treated as hidden. We have evaluated this hybrid HMM/BN model with our LVCSR system by phoneme recognition and by large-vocabulary continuous word recognition tasks. In both cases, we observed improved performance over the conventional Gaussian mixture HMM.
