|
|
Traffic assistant system for complicated situations
Podola, David ; Janáková, Ilona (referee) ; Petyovský, Petr (advisor)
T-intersections are one of the most common places where collisions happen. An intelligent traffic mirror is one the possible solutions to reduce the accident rate. The mirror detects the situation around the intersection, process the data and provides the driver with an information, whether the situation is safe and the driver can enter the junction safely. The aim of the thesis is a feasibility study of reliable detection of non-stationary objects based on cameras. The core of the intended product – the detection algorithm – detected the object on short distance from the camera reliably but as the distance was growing, the detection quality degraded. One of the possible solutions to achieve better detection results on longer distances may be achieved by using a camera with greater zoom. Based on the example improvement proposal, the feasibility of the solution based on optical methods was finally confirmed.
|
|
|
Traffic Assistant System For Road Junctions
Podola, David
Road junctions are one of the most common places where collisions happen. This article proposes an algorithm for moving object extraction, which will act as an input for an assistant systém based on cameras, image processing algorithms and a light signal, monitoring the situation at a junction and providing the driver with an information, whether the situation is safe and the driver can enter the junction safely. The algorithm takes decision based on the direction and speed of the moving objects. The results have shown that it is feasible to solve the challenge by the chosen method, however, the most challenging part would be various weather conditions as well as reliable shadow detection.
|
|
|
Traffic assistant system for complicated situations
Podola, David ; Janáková, Ilona (referee) ; Petyovský, Petr (advisor)
T-intersections are one of the most common places where collisions happen. An intelligent traffic mirror is one the possible solutions to reduce the accident rate. The mirror detects the situation around the intersection, process the data and provides the driver with an information, whether the situation is safe and the driver can enter the junction safely. The aim of the thesis is a feasibility study of reliable detection of non-stationary objects based on cameras. The core of the intended product – the detection algorithm – detected the object on short distance from the camera reliably but as the distance was growing, the detection quality degraded. One of the possible solutions to achieve better detection results on longer distances may be achieved by using a camera with greater zoom. Based on the example improvement proposal, the feasibility of the solution based on optical methods was finally confirmed.
|
guest ::
