Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.

Three classes of impervious surfaces--buildings, roads, and other impervious--were mapped for New Jersey through a semi-automated process developed using eCognition software. The automated feature extraction workflow used a Geographic Object-Oriented Image Analysis (GEOBIA) framework to extract the three impervious classes from the source datasets which include digital imagery, LiDAR point clouds and several vector data sets including Land use/land cover, road centerlines and hydrographic features, using a rule-based expert system.