While Graph Cuts are used for image segmentation, there exist two problems: how to get better initial information of
foreground and background and how to improve the executing efficiency of Graph Cuts algorithm. To solve the first
problem, path morphology and line segment matching algorithm are performed to get initial background information at
the same time as getting initial foreground information, so non-road pixels similar with road pixels in gray value or
texture are avoided being segmented as road points. To cope with the second problem, push-relabel strategy is chosen
and its parallelized version based on NVIDIA CUDA platform is performed in this paper. Our strategy is performed on
dense built-up area and suburban district and proved to be effective in both accuracy and efficiency.
In this paper, a new method for automatic detection of roads from Light Detection and Ranging (LIDAR) data is
presented. A morphological filter and an elevation difference threshold are first combined to classify the original data. In
the following step, a height fitting difference algorithm is introduced and performed to calculate height fitting difference
with a multi-direction template for each pixel. The algorithm acquires two pieces of information about roads: the least
squares fitting difference and the corresponding orientation. Then, the Otsu's method is applied to obtain a road map with
the fitting difference feature. After performing the Euclidean distance transform on the segmented road map, road
centerlines are searched in the distance map. Next, the centerlines are connected and optimized so that long and smooth
road centerlines are obtained. Finally, road boundaries are found by setting a proper width value for each road centerline.
The proposed method has been tested on various complicated urban images. Experimental results demonstrate that our
new method works efficiently and correctly.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.