| Summary: | 碩士 === 國立臺灣科技大學 === 電子工程系 === 101 === Perceptual organization is the process of establishing the meaningful relational visual structures which are grouped together by our proposed methods. In this work, we automatically count the number of moving vehicles in dynamic scene. The image sequences used in our experiments were taken from a camera mounted on a moving vehicle. We make use of the characteristics of the visual organization laws which were developed based on Gestalt psychology, such as: Law of Proximity, Law of Similarity, Law of Closure, Law of Common Fate, Law of Past Experience, and the brightness perception, to generate our target features. The probabilistic framework based on Hough transform is designed to iteratively estimate the maximum a posteriori (MAP) of Hough space. Taking advantage of this process, one can detect the occluded vehicles and then estimates the statistics of vehicles. Experimental results using real images demonstrate the feasibility of the proposed method.
|
|---|
