Skripsi
OBJEK TRACKING PENGUNJUNG PERPUSTAKAAN MENGGUNAKAN METODE HISTOGRAM OF ORIENTED GRADIENT BERBASIS VIDEO CCTV
Surveillance in the library is significantly aided by the presence of CCTV surveillance cameras installed in specific pathways frequented by library visitors. Given the substantial number of visitors, it becomes essential to record the visitor count to gauge the extent of library utilization. Detection and tracking of human objects pose unique challenges in developing software on computers to recognize human entities within video footage. A video is composed of a series of frames, encompassing human objects that need to be extracted. Not all frames are processed to save time; hence, keyframe selection is employed. This extraction process can be carried out using various methods, one of which is the Histogram of Oriented Gradient (HOG) method. Support Vector Machine (SVM) is employed to distinguish between the extracted human objects and non-human elements. The software developed in this research demonstrates effectiveness in tracking individuals and quantifying their numbers, achieving an accuracy rate of 61.8%
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307003775 | T127125 | T1271252023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available