In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Hidden Markov Models (HMM). We build our models on Principal Com...
Faisal I. Bashir, Wei Qu, Ashfaq A. Khokhar, Dan S...
Shadow detection is critical for robust and reliable vision-based systems for traffic vision analysis. Shadow points are often misclassified as object points causing errors in loc...
- In this paper, we proposed a new solution to the reconstruction of image in order to solve the oversegmentation problem of watershed transformation which is widely used as an ima...
Hyun Sil Sin, Hyun Woo Park, Hwang Kyu Yang, Tae S...
We consider the `group motion segmentation' problem and provide a solution for it. The group motion segmentation problem aims at analyzing motion trajectories of multiple obj...