Repozytorium publikacji - Politechnika Gdańska

Several problems may arise when multiple trains are to be tracked using two IP camera streams. In this work, real-life conditions are simulated using a railway track model based on the Pomeranian Metropolitan Railway (PKM). Application of automatic clustering of optical flow is investigated. A complete tracking solution is developed using background subtraction, blob analysis, Kalman filtering, and a Hungarian algorithm. In total, six morphological, convolutional and non-linear filtering methods are compared in sixty-three combinations. Accuracy and performance of the system are evaluated, and the obtained results are analyzed and commented on.

Autorzy

• prof. dr hab. inż. Zdzisław Kowalczuk link otwiera się w nowej karcie ,
• Sylwester Frączek link otwiera się w nowej karcie