https://etalpykla.vilniustech.lt/handle/123456789/159390 2026-04-11T17:56:02Z 2026-04-11T17:56:02Z Tumas, Paulius Jonkus, Artūras Serackis, Artūras https://etalpykla.vilniustech.lt/handle/123456789/159501 2025-12-09T10:51:56Z 2018-01-01T00:00:00Z

Acceleration of HOG based pedestrian detection in FIR camera video stream Tumas, Paulius; Jonkus, Artūras; Serackis, Artūras Pedestrian detection is one the main problem for the automotive applications which is a challenging task to do. In recent years, the number of approaches was developed to speed up the detection rate and accuracy. However, the general problem of detectors remains. The aim of the paper was to evaluate experimentally current and efficient pedestrian detection methods in night vision applications and propose some modifications to accelerate the image analysis workflow. In this paper, for night vision application we used an FIR domain camera. The novelty of the proposed solution lays in the application of HOG based pedestrian detector for FIR domain camera. An acceleration of the algorithm was achieved using subtraction of the thermally active regions before supplying these regions to the pre-trained feature descriptor. An experimental investigation has shown the significant improvement in pedestrian detection speed using solution, proposed in this paper. Our study shows that state of the art detectors can gain nearly triple initial detection rate using the same image data.

2018-01-01T00:00:00Z Semenas, Rokas Bausys, Romualdas https://etalpykla.vilniustech.lt/handle/123456789/159500 2025-12-09T10:33:08Z 2018-01-01T00:00:00Z

Autonomous navigation in the robots" local space by multi criteria decision making Semenas, Rokas; Bausys, Romualdas The field of autonomous robot navigation has become a prominent study subject in the past decades. The main problem of these systems is to assist the robot in leading it through unknown and dangerous environments while also accomplishing the given tasks. In practice, these human uncontrolled devices can be used in search and rescue missions or area mapping requests. The fundamental part of effective autonomous navigation is exploration strategy. Until this day, many different solutions to this problem have been suggested, and multi criteria decision making methods (MCDM) can be considered the state of the art methods that are used to tackle this problem. In this paper, new robot surroundings evaluation criteria are suggested and navigation in local robot space methodology are proposed.

2018-01-01T00:00:00Z Griazev, Kiril Ramanauskaitè, Simona https://etalpykla.vilniustech.lt/handle/123456789/159499 2025-12-09T09:14:14Z 2018-01-01T00:00:00Z

Web mining taxonomy Griazev, Kiril; Ramanauskaitè, Simona The information publication on the Internet increases the information accessibility. However, the amount of data on the Internet increases rapidly and it becomes difficult to find the needed information among multiple possible sources. Therefore, automated tools for web mining gain their popularity and seek to simplify the gathering of the information, published on the internet. The purpose of information gathering as well as web page development technologies, format of published data and other properties might be different therefore different web mining methods exist. However, there is no clear classification or a complete list of web mining techniques therefore it is difficult to fully understand the web mining area. In this paper we present a new web mining taxonomy, designed to clarify the web mining area. The taxonomy will serve as classification methodology and will allow classification of existing web mining technologies or methods according to clearly defined criteria and categories.

2018-01-01T00:00:00Z Skirelis, Julius Navakauskas, Dalius https://etalpykla.vilniustech.lt/handle/123456789/159498 2025-12-09T07:02:37Z 2018-01-01T00:00:00Z

Classification of cell colonies images by ART2 classifier Skirelis, Julius; Navakauskas, Dalius Counting of cell colonies is a high demanded procedure in cytometry. An ability to automatically parameterize biomedical samples highly influences on cytometry and therefore medical research results. The article extends previously by the authors developed cell colonies image parameterization technique with new results based on the use of another - ART2 (Adaptive Resonance Theory 2), classifier. Experimental investigation is carried out in order to check reliability of cell colony count and efficiency of cell colony image classification. Results of the experimental verification confirms that ART2 classifier brings up similar results to Heuristic classifier in terms of F1 score, accuracy and precision, yet DOR value is increased more than two times. Moreover the use of ART2 classifier in terms of true positives manifests better performance than the use of other considered classifiers: Support Vector Machine - by 14%, ART1 - by 4% and Heuristic - by 2%.

2018-01-01T00:00:00Z