Moving vehicle classification

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2013

Öğrenci: DEMET DUMAN

Danışman: GÖZDE AKAR

Özet:

In recent years intelligent transportation systems have been an active research area in computer vision. The aim of this study is to classify moving vehicles from highway videos taken by stationary uncalibrated cameras. For this study, three types of vehicle classes with different scales are chosen to classify: car, van and truck. The proposed algorithm is composed of foreground/background segmentation, feature extraction and classification steps. In order to classify each vehicle, histogram of oriented gradients (HOG) features which are shape-based descriptors and blob features which are dimension-based descriptors are used in the algorithm. The effects of these features on the classification performance are also evaluated and simulation results are given on different highway videos.