ACADSTAFF UGM
| Title | : | Object Searching on Real Time Video Using Oriented FAST and Rotated BRIEF Algorithm |
| Author | : |
FAISAL DHARMA A (1) Prof. Drs. Agus Harjoko, M.Sc., Ph.D. (2) Wahyono, Ph.D. (3) |
| Date | : | 31 2021 |
| Keyword | : | Object searching,real time video,keyframe selection,mutual information entropy,ORB Object searching,real time video,keyframe selection,mutual information entropy,ORB |
| Abstract | : | The main stages in object searching on video are pre-processing and feature extraction. Processing video in all frames is inefficient. Frames that have the same information should be only once processed to the next stage. Then, the feature extraction algorithm that is often used to process video frames is SIFT and SURF. The SIFT algorithm is very accurate but slow. On the other hand, the SURF algorithm is fast but less accurate. Therefore, the requirement for keyframe selection and feature extraction methods is fast and accurate in object searching on real time video. Video is pre-processed by extracting video into frames. Then, frames are selected into keyframes using mutual information entropy method. Then, keyframes are extracted using the ORB algorithm. The multiple object detection in video is done by clustering on features. The results of feature extraction on each cluster are matched with the results of feature from query image. Matching results from keyframe on video that match with the query image are used as retrieval of frame information on video. The experiment shows that keyframe selection is very helpful in real time processing because the keyframe selection speed is faster than feature extraction on each frame. Then, feature extraction using ORB algorithm is resulting 2 times faster speed results than SIFT and SURF algorithms with F_1 value not too different from SIFT algorithm. |
| Group of Knowledge | : | Ilmu Komputer |
| Original Language | : | English |
| Level | : | Internasional |
| Status | : |
Published
|
| No | Title | Action |
|---|---|---|
| 1 |
12043-38212-1-PB (1).pdf
Document Type : [PAK] Full Dokumen
|
View |