Henryk Josiński

Real-time multi-view human motion tracking using particle swarm optimization with resampling

In this paper we propose a particle swarm optimization with resampling for marker-less body tracking. The resampling is employed to select a record of the best particles according to the weights of particles making up the swarm. The algorithm better copes with noise and reduces the premature stagnation. Experiments on 4-camera datasets show the robustness and accuracy of our method. It was evaluated on nine sequences using ground truth provided by Vicon. The full body motion tracking was conducted in real-time on two PC nodes, each of them with two multi-core CPUs with hyper-threading, connected by 1 GigE.

3D Gait Recognition Using Spatio-Temporal Motion Descriptors

We present a view independent algorithm for 3D human gait recognition. The identification of the person is achieved using motion data obtained by our markerless 3D motion tracking algorithm. We report its tracking accuracy using ground-truth data obtained by a marker-based motion capture system. The classification is done using SVM built on the proposed spatio-temporal motion descriptors. The identification performance was determined using 230 gait cycles performed by 22 persons. The correctly classified ratio achieved by SVM is equal to 93.5% for rank 1 and 99.6% for rank 3. We show that the recognition performance obtained with the spatio-temporal gait signatures is better in comparison to accuracy obtained with tensorial gait data and reduced by MPCA.

Classification of poses and movement phases

We have focused on the problem of classification of motion frames representing different poses by supervised machine learning and dimensionality reduction techniques. We have extracted motion frames from global database manually, divided them into six different classes and applied classifiers to automatic pose type detection. We have used statistical Bayes, neural network, random forest and Kernel PCA classifiers with wide range of their parameters. We have tried classification on the original data frames and additional reduced their dimensionality by PCA and Kernel PCA methods. We have obtained satisfactory results rated in best case 100 percent of classifiers efficiency.

DTW-Based Gait Recognition from Recovered 3-D Joint Angles and Inter-ankle Distance

We present a view independent approach for 3D human gait recognition. The identification of the person is done on the basis of motion estimated by our marker-less 3D motion tracking algorithm. We show tracking performance using ground-truth data acquired by Vicon motion capture system. The identification is achieved by dynamic time warping using both joint angles and inter-joint distances. We show how to calculate approximate Euclidean distance metric between two sets of Euler angles. We compare the correctly classified ratio obtained by DTW built on unit quaternion distance metric and such an Euler angle distance metric. We then show that combining the rotation distances with inter-ankle distances and other person attributes like height leads to considerably better correctly classified ratio.

View Independent Human Gait Recognition Using Markerless 3D Human Motion Capture

We present an algorithm for view-independent human gait recognition. The human gait recognition is achieved using data obtained by our markerless 3D motion tracking algorithm. The tensorial gait data were reduced by multilinear principal component analysis and subsequently classified. The performance of the motion tracking algorithm was evaluated using ground-truth data from MoCap. The classification accuracy was determined using video sequences with walking performers. Experiments on multiview video sequences show the promising effectiveness of the proposed algorithm.

Detection of tumor tissue based on the multispectral imaging

We have prepared multispectral image database of skin tumor diagnosis. All images have been labeled with two classes - tumor and healthy tissues. We have extracted pixel signatures with their spectral data and class assigning, thus obtained train dataset. Next we have used and evaluated the supervised learning techniques for the purpose of automatic tumor detection. We have tested Naive Bayes, KNN, Multilayer Perceptron, LibSVM, LibLinear, RBFNetwork, ConjuctiveRule, DecisionTable and PART classifiers. We have obtained results on the level of 99% classifier efficiency. We have visualized classification for example images by coloring class regions and verified if they overlap with labeled regions.

The Comparison of an Adapted Evolutionary Algorithm with the Invasive Weed Optimization Algorithm Based on the Problem of Predetermining the Progress of Distributed Data Merging Process

The goal of the project was to adapt the idea of the Invasive Weed Optimization (IWO) algorithm to the problem of predetermining the progress of distributed data merging process and to compare the results of the conducted experiments with analogical outcomes produced by the evolutionary algorithm. The main differences between both compared algorithms constituted by operators used for transformation of individuals and for creation of a new population were taken into consideration during the implementation of the IWO algorithm. The construction of an environment for experimental research made it possible to carry out a set of tests to explore the characteristics of the tested algorithms. The results of the conducted experiments formed the main topic of analysis.

The Expanded Invasive Weed Optimization Metaheuristic for Solving Continuous and Discrete Optimization Problems

This paper introduces an expanded version of the Invasive Weed Optimization algorithm (exIWO) distinguished by the hybrid strategy of the search space exploration proposed by the authors. The algorithm is evaluated by solving three well-known optimization problems: minimization of numerical functions, feature selection, and the Mona Lisa TSP Challenge as one of the instances of the traveling salesman problem. The achieved results are compared with analogous outcomes produced by other optimization methods reported in the literature.

Gait recognition based on marker-less 3D motion capture

We present an algorithm for view-independent gait-based person identification. The identification is achieved using data obtained by our marker-less 3D motion tracking algorithm. The motion tracking was accomplished by a particle swarm optimization algorithm. The accuracy of the motion tracking algorithm was evaluated using ground-truth data from MoCap. It was determined on 88 sequences with 22 walking performers. We obtained 90% identification accuracy (rank 1) on 230 gait cycles.

Feature Selection of Motion Capture Data in Gait Identification Challenge Problem

The method of discovering robust gait signatures containing strong discriminative properties is proposed. It is based on feature extraction and selection of motion capture data. Three different approaches of feature extraction applied to Euler angles and their first and second derivates are considered. The proper supervised classification is preceded by specified selection scenario. On the basis of the obtained precision of person gait identification, analyzed feature sets are assessed. To examine proposed method database containing 353 gaits of 25 different males is used. The results are satisfactory. In the best case the recognition accuracy of 97% is achieved. On the basis of classification which takes into consideration only the data of the specified segments, the ranking is constructed. It corresponds to the evaluation of individual features of the joint movements.