Thesis Details
Sledování pohybů osob v záznamu ze stacionární kamery
This bachelor thesis focuses on pedestrians tracking from camera. In this work, I have introduced several methods of computer vision suitable for detection and classification of people. I proposed an algorithm for detecting and tracking pedestrians based on detection of movement. The application uses a Histogram of Oriented Gradients and SVM classifier together with color histograms for identification of pedestrians. Pedestrian's trajectories are then rendered to the output. Last part of the thesis deals with testing and evaluation of the results of the algorithm.
Histogram of Oriented Gradients, SVM, Feature extraction, Gaussian mixture model, People detection, Pedestrian tracking, OpenCV, Detection of movement in video, Trajectory capture
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Kunovský Jiří, doc. Ing., CSc. (DITS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
@bachelorsthesis{FITBT18854, author = "Milan Trnkal", type = "Bachelor's thesis", title = "Sledov\'{a}n\'{i} pohyb\r{u} osob v z\'{a}znamu ze stacion\'{a}rn\'{i} kamery", school = "Brno University of Technology, Faculty of Information Technology", year = 2016, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/18854/" }