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.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1007/978-3-319-60699-6_20
- Category
- Aktywność konferencyjna
- Type
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language
- polski
- Publication year
- 2017
