Search

Image segmentation is a critical procedure in object-based identification and classification of remote sensing data. However, optimal scale-parameter selection presents a challenge, given the presence of complex landscapes and uncertain feature changes. This study proposes a local optimal segmentation approach that considers both intersegment heterogeneity and intrasegment homogeneity, uses the standard deviation and local Moran's index to explore each optimal segment across different scale parameters, and combines the optimal segments into a single layer. The optimal segment is measured by using high-spatialresolution images. Results show that our approach outperforms and generates less error than the global optimal segmentation approach. The variety of land cover types or intrasegment homogeneity leads to segment matching with the geo-objects on different scales. Local optimal segmentation demonstrates sensitivity to land cover discrepancy and provides good performance on cross-scale segmentation. [ABSTRACT FROM AUTHOR]

Most commercially available video detection systems are unable to differentiate turning movements at intersections. Therefore, special applications need to be developed. Using the basic time events recorded by a video detection system, a vehicle-tracking algorithm was developed to track vehicles and measure speeds at two-way, stop-controlled intersections. [ABSTRACT FROM AUTHOR]

The article discusses the application of the National Transportation Communications for Intelligent Transport Systems Protocol (NTCIP) standard for Transit Signal Priority (TSP) in California. It was showed how the various TSP elements could be organized in microscopic simulation in a structured and systematic fashion in compliance with the NTCIP. The advantage of the proposed simulation was demonstrated through a sample application on the state's 12 signalized intersections highway.