|
|
Speed Measurement of Vehicles from Surveillance Camera
Jaklovský, Samuel ; Juránek, Roman (referee) ; Sochor, Jakub (advisor)
This master's thesis is focused on fully automatic calibration of traffic surveillance camera, which is used for speed measurement of passing vehicles. Thesis contains and describes theoretical information and algorithms related to this issue. Based on this information and algorithms, a comprehensive system design for automatic calibration and speed measurement was built. The proposed system has been successfully implemented. The implemented system is optimized to process the smallest portion of the video input for the automatic calibration of the camera. Calibration parameters are obtained after processing only two and half minutes of input video. The accuracy of the implemented system was evaluated on the dataset BrnoCompSpeed. The speed measurement error using the automatic calibration system is 8.15 km/h. The error is mainly caused by inaccurate scale acquisition, and when it is replaced by manually obtained scale, the error is reduced to 2.45 km/h. The speed measuring system itself has an error of only 1.62 km/h (evaluated using manual calibration parameters).
|
|
|
Calibration of Surveillance Camera
Pištělák, Radek ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This work aims the issue of calibration of cameras, more precisely surveillance cameras, that monitor Ćat areas such as car parks. The calculation is based on several measurements of the same distance over the entire Ąeld of camera view. From the obtained set of measurements, the properties of the camera are calculated so that it is able to measure distances. With this approach, an error of 1.6 % was achieved, which was calculated by substituting back into annotated and unannotated images in the main experiment. The result of the work is a way to calibrate the camera with a view of large spaces, for which other methods of calibration could be difficult.
|
|
|
Calibration of Surveillance Camera
Pištělák, Radek ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This work aims the issue of calibration of cameras, more precisely surveillance cameras, that monitor Ćat areas such as car parks. The calculation is based on several measurements of the same distance over the entire Ąeld of camera view. From the obtained set of measurements, the properties of the camera are calculated so that it is able to measure distances. With this approach, an error of 1.6 % was achieved, which was calculated by substituting back into annotated and unannotated images in the main experiment. The result of the work is a way to calibrate the camera with a view of large spaces, for which other methods of calibration could be difficult.
|
|
|
Speed Measurement of Vehicles from Surveillance Camera
Jaklovský, Samuel ; Juránek, Roman (referee) ; Sochor, Jakub (advisor)
This master's thesis is focused on fully automatic calibration of traffic surveillance camera, which is used for speed measurement of passing vehicles. Thesis contains and describes theoretical information and algorithms related to this issue. Based on this information and algorithms, a comprehensive system design for automatic calibration and speed measurement was built. The proposed system has been successfully implemented. The implemented system is optimized to process the smallest portion of the video input for the automatic calibration of the camera. Calibration parameters are obtained after processing only two and half minutes of input video. The accuracy of the implemented system was evaluated on the dataset BrnoCompSpeed. The speed measurement error using the automatic calibration system is 8.15 km/h. The error is mainly caused by inaccurate scale acquisition, and when it is replaced by manually obtained scale, the error is reduced to 2.45 km/h. The speed measuring system itself has an error of only 1.62 km/h (evaluated using manual calibration parameters).
|
guest ::
