Human action recognition using simple geometric features and a finite state machine

In this paper a human action recognition algorithm, which uses background generation with shadow elimination, silhouette description based on simple geometrical features and a finite state machine for recognizing particular actions is described. The performed tests indicate that this approach obtains a 81 % correct recognition rate allowing real-time image processing of a 360 X 288 video stream.

Automation of selected brazes' dynamic properties in high-temperatures' measurement process

The good quality of several manufactured components frequently depends on solidliquid interactions existing during processing. Nowadays, the research in material engineering focuses also on modern, automatic measurement methods of joining process properties, i.a. wetting force and surface tension, which allows for quantitative determination of above mentioned parameters. In the paper, the brazes’ dynamic properties in high-temperatures’ measurement methodology and the stand for automatic determination of braze’s properties, constructed and implmented within the research grant nr KBN N N519 441 839 - An integrated platform for automatic measurement of wettability and surface tension of solders at high temperatures, are widely described

Comparison of non-linear palette usage for gamma-ray tomography imaging

Gamma-ray tomography is used for non-invasive studying of objects. To enable correct interpretation of such measurements, they need to be presented in analysis-friendly way. One method is to use ILST (Iterative Least Squares Technique) algorithm to visualize 1D detector data on a 2D grid, so that gammaray attenuation is visible with a resemblance to cross-section structure. However algorithm imperfections and thresholding do not always allow inferring shapes of the structure correctly. To remedy this, the analyses of the whole range of reconstructed values are to be used with a non-linear transformation function to visualize and emphasize density gradient.

Application of multidimensional data analysis to chromatography

This work presents analysis of chromatographic signal used to identify substances in samples. First part consists of chromatography overview and description of three classification methods (neural network with backpropagation, probabilistic neural network with Parzen window and support vector machines). Designed algorithm consists of several stages: signal filtering, peak detection and its approximation with sum of two Gaussian functions. The parameters of that two curves are the features vectors describing the peak of the substance. The last step is classification, for which two types of supervised machine learning were compared, based on the whole signal and on features vectors. Both types were tested for different classificators and their parameters. Verification was based on 55 chromatography signals. The best results for both methods of learning were achieved for probabilistic neural networks. The correct classification rate was 82% for the whole signal and 93% for feature vectors.

Detection of tracer particles in tomography images for analysis of gravitational flow in silo

This paper presents a method for the investigations of the gravity flow of granular materials based on the analysis of CT images. The system of X-ray tomography allows to visualize the distribution of bulk material inside the silo model. The images of the distribution of the concentration of the material, both in the form of 3D tomography images and 2D radiographic images, allow to track the behaviour of the material during the silo discharging process. Application of image processing and analysis provides an in-depth tool for investigation of the flow. The proposed, in the paper, methodology of the tracer particles allow to track the particles position changes during the gravitational flow in silo. The determination of tracer particles position is based on the vision information stored in volumetric computed tomography images and two-dimensional radiography.

Preprocessing of GPR data

In this article a set of procedures for data preprocessing of GPR radargrams are presented. Raw data taken from GPR are affected by different noises and instability of equipment. The data in this form, are not suitable for the further analysis. They must undergo a set of transformations in order to obtain indispensable information.

Hardware-software vision system for moving people counting based on 3D information

The article presents a hardware-software system for people counting based on analysis of 3D information. It consists of a 3D video source (3D camera), an FPGA evaluation board and a PC computer. The computationaly demanding disparity map calculation and median filtering are realized in hardware. The software part is responsible for people segmentation, tracking and counting. The data between system nodes is transferred via Ethernet. In the paper the system architecture, proposed algorithms and obtained results are presented.

Efficient implementation of background generation method based on pixel occurrences

The paper presents the implementation of modified background generation algorithm based on analysis of the frequency of occurrences of pixels. The proposed solution allows the use of the algorithm in real-time systems, which was quite difficult in the original method. The results show that the modified algorithm gives practically the same background as the original method but in significantly less time and can be applied in many tasks related to the detection and analysis of moving objects.

Object detection and tracking for low-cost video surveillance system

Automated and intelligent video surveillance systems play important role in the modern world. Since the amount of various video streams that must be analyzed grows, such artificial intelligence systems can assist humans in performing tiresome tasks. As a result, the effectiveness of response to a dangerous situations is increasing (detect unexpected movement or unusual behavior that may pose a threat to people, property and infrastructure). Video surveillance systems have to meet several requirements: must be accurate and not produce too many false alarms, moreover it must be able to process the received video stream in real-time to provide a sufficient response time. The work presented here focuses on the selected challenges of scene analysis in video surveillance systems (object detection/tracking, effectiveness of the whole system). The aim of the research is to design a low-budget surveillance system, that can be used for example in a home security monitoring. Such solution can be use not only to surveillance but also to monitor elderly person at home or provide new ways of interacting in human-computer interaction systems.