Budi Setiyono

A new algorithm for small object tracking based on super-resolution technique

Object tracking in a video is a problem of estimating the trajectory of an object in the image plane as it moves around a scene. In general, object tracking is a quite complicated problem. Difficulties in object tracking occur due to some constraints or conditions such as object motion, changing appearance patterns, non-rigid object structures, occlusions, and camera motion. Level of problems would be higher if the object tracking has relatively small. If it happens, an object will be difficult to identify and tracking becomes less precision because small object has little information. In order to overcome these problem, the tracking will be integrated with super-resolution where a high-resolution image will be built from several low-resolution image. In this research, tracking of moving object using adaptive particle filter which adaptive motion model is applied to get better proposal distribution approach. The simulation shows that tracking integration with super-resolution significantly increase the ac...

Vehicle speed detection based on gaussian mixture model using sequential of images

Intelligent Transportation System is one of the important components in the development of smart cities. Detection of vehicle speed on the highway is supporting the management of traffic engineering. The purpose of this study is to detect the speed of the moving vehicles using digital image processing. Our approach is as follows: The inputs are a sequence of frames, frame rate (fps) and ROI. The steps are following: First we separate foreground and background using Gaussian Mixture Model (GMM) in each frames. Then in each frame, we calculate the location of object and its centroid. Next we determine the speed by computing the movement of centroid in sequence of frames. In the calculation of speed, we only consider frames when the centroid is inside the predefined region of interest (ROI). Finally we transform the pixel displacement into a time unit of km/hour. Validation of the system is done by comparing the speed calculated manually and obtained by the system. The results of software testing can detect the speed of vehicles with the highest accuracy is 97.52% and the lowest accuracy is 77.41%. And the detection results of testing by using real video footage on the road is included with real speed of the vehicle.