Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as ...
Aerial video provides strong cues for automatic road extraction that are not available in static aerial images. Using stabilized (or geo-referenced) video data, capturing the dist...
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic "t...
Many image processing and computer vision applications have difficulty dealing with a nonstatic background such as water waves, but this particular dynamic scene actually contains...
We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...