ACADSTAFF UGM
| Title | : | Improved Visual Background Extractor for Illegally Parked Vehicle Detection |
| Author | : |
PUTRA YUDHA PRANATA (1) Wahyono, Ph.D. (2) |
| Date | : | 30 2022 |
| Keyword | : | Illegal Parking Detection,False-Positive Error,Background Modeling,Visual Background Extractor Illegal Parking Detection,False-Positive Error,Background Modeling,Visual Background Extractor |
| Abstract | : | Illegal parking is a violation that often occurs in urban areas. Supervision is conducted in places where parking is prohibited to overcome this problem. Manual monitoring requires high staff performance and costs. Therefore, a video-based illegal parking detection is proposed. Previous studies have several weaknesses in video based illegal parking detection, especially those that use background modeling techniques. Examples of drawbacks include changes in illumination and imperfect segmentation caused by noise, leading to false-positive errors. This study aims to overcome the problem of frequently occurring false-positive errors by using the improved visual background extractor (I-ViBe). This method develops the ViBe approach to detect illegal parking by modifying the background model update mechanism with the static region extraction and vehicle verification processes and integrating tracking processes. Experimental results show that the values of precision, recall, and f-measure are 100%,, 60%, and 75% respectively, which means that the proposed system has overcome all false-positive problems. |
| Group of Knowledge | : | Ilmu Komputer |
| Original Language | : | English |
| Level | : | Internasional |
| Status | : |
Published
|
| No | Title | Action |
|---|