20210222 13473400 1.0 TRUE TRUE Rast_impervious_surface_3857 Impervious surfaces for the State of New Jersey. Three classes of impervious surfaces were mapped: 1) Buildings, Roads, and Other Impervious Surfaces. Note that buildings do not exist for some areas due to the lack of LiDAR data. In these instances, buildings are assigned to the Other Impervious class. The overall accuracy of the mapping was 94%. The user's accuracies for Buildings, Roads, and Other Paved were 94%, 87%, and 84% respectively.The 2015 leaf-off New Jersey orthorectified imagery served as the primary data source, but the 1-meter leaf-on imagery acquired through the National Agricultural Imagery Program (NAIP) in the summer of 2015 was also used. Several additional datasets, that although dated and flawed, that still had value were used to supplement the process. This includes LiDAR data, which was collected at varying time periods in New Jersey, road centerlines, and the National Hydrography Dataset (NHD). Initial feature extraction was carried out in the coordinate system of the LiDAR data (most often UTM). LiDAR point clouds were normalized and classified to separate out buildings and trees. Raster surface models and intensity images were generated from the LiDAR point cloud data. Imagery data were mosaicked, and vector datasets were examined for completeness, accuracy, and topology.This project employed a semi-automated approach in which features were automatically extracted then manually reviewed and edited. The automated feature extraction workflow used an OBIA framework to automatically extract aforementioned impervious classes from the source datasets using a rule-based expert system. The expert system made use of segmentation, classification, and morphology algorithms to group pixels into objects, classify the objects based on the properties of the source datasets, and then refined the objects to enhance aesthetics and improve visual realism. The approach to mapping involved both automated feature extraction techniques and manual editing of impervious surfaces. A “bottom-up” approach to mapping was carried out in which impervious surface features that are under tree canopy but visible in the leaf-off imagery was mapped. The key advantage of the object-based approach is that the use of the spectral, textural, geometric, and contextual properties in the imagery reduce confusion between impervious land cover features and those that are similar in tone, such sand on the banks of streams. Impervious surface buildings roads njdep Impervious surfaces for the State of New Jersey. Three classes of impervious surfaces were mapped: 1) Buildings, Roads, and Other Impervious Surfaces. Note... NJDEP iVBORw0KGgoAAAANSUhEUgAAASwAAADICAYAAABS39xVAAAAAXNSR0IB2cksfwAAAAlwSFlzAAAO xAAADsQBlSsOGwAAGvJJREFUeJztnVlvHOeVht/aq3rhKlqWrFHkBOPkIghylf9/PXMzCAZwDMOO YceLbEnceq118H7Vp1VsURQVUiMW+32QDpvd1ewmrXpwvlPnOydsmqaBEEL0gPBjfwAhhLguEpYQ ojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4Ql hOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBh CSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdI WEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgN EpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6 g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI 3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQ ojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhCSF6g4Ql hOgNEpYQojdIWEKI3iBhCSF6g4QlhOgNEpYQojdIWEKI3iBhiRvTNM365nkefN/XX1V8ECQscWMo Kd6E+NBIWOJGMKoim8KyiEvRlrhNJCxxK8K6TFqKusRtI2GJG9GNoLryEuJDIGGJG/E2Sb1tqSjE TZCwxI347bffEIYhkiRBHMfuviXh67rWX1fcKhKWuBE///wzsizDzs4OxuMxgiBYR1VKuIvbRsLa dpoCdVGu5ZJXNeIkWT3powSwWBQYJiE8VGiKHF4Yoaxq/OvHnzGIPMQBEDQlmrq9wY9RVRWKokCa ph/11xP3Cwlr6/GBIASCwP0l4vB1Er0sS3hc7oUBPNSolgucnx4DfgjPD5yc9vf3EUZxuxyM47X4 GGkpwhK3jYS15TReAFA+3cfsGy9AU5aoiiWaZYl8do7p+ZmT03h3Dw8P913uCp7fyoniWyXcVUwq PgQS1pbj0uIeUNaAV9dOPFzO+V7jEuiL+RJNWaCqclRljij0EUcB0jgC0sy9sIEHj8JaJdqrql1i MsoS4jaRsLYcioqrQObJGRUFPtBUJYq8QBikSLMMqCLks8oJzJLqi8UCieejajxUdeMeD5N2GVjV tRMX76usQdwmEtaWQzHFaQSfwgoa2gooc+STU2ThHhCP3FKPS8cgbHNVy+USs8USee2574uycsIK 4sRFWryvkgbxIZCwthxmr1iEUOQLt/SjvKanr3B+doJh5KPwBogDH7UfIogz+GmMpmywLJeoQyBq Gnc1kAn6KM0QdRLviq7EbSNhbTlJzH8CNRbTCRbTM5ebOj9+ieViBhzstLkpH4iTDF6VuyuEjKjm eYEmiDFK2xIGRlQUF4VFtE1HfAgkrPsO66IaoEKA2q37+GAFH7WrsvIqPtBguTzF8clzhH4Evwkx Hj9EGH/iaq/8xofHBHqQOTGlo118kgycqP755f+4kojdvQPEGANNjbrhhcMAlYvgauTL5bq2i/fd 8jEMV49n7nEuMxmRcYnJaI031XCJTSSse0+zuhLouTwV8Z21mK+q0RQ1fv35OX766Xv4gYenTz7B /tEjwIuB5uKVPkZNlBRlYsvA/QcP3H0e5xL4q2PyIneviQLKcOlExxKIbiU8JcbkPcXkyiNWmLCs PEIIQ8K651SeC3fQrIIrZpe8pkE+m6OYTzA7nWIxn2BvvOMEwuhouVgiySLUrFyv2lyUXfGLosjd 51eKKc58TCYTVHwbysUP4Dtp5cjzHMnOwH0OHkOxcRsPJUWBcSsPrzzactJ+LuWlK4ziMiSsew5X fL7T1IoGKOdLTI9PMTl5iTpfIB0M8PDxfwCDFC9fvsTL0zNkZYWyarC/e/BGlGNRkqu1SkdIEbiI KAij9fNZ2ibfGSVRSLPZbB1lUWSMuobDIcIwcjLjnkS+7rPPPltvpLbSCCEMCWvLYMDlczWYl1hM ptjfy1DWRZtPGo5wePAQte+jbGq8OD5xEZBB+dhyjTdGWHu7I0QsZ4gS+J1jGSnxtbPpuYueLDFv ouNz/qr8gTI7Pz93r9vb23PCsuWnhCW6SFj3He6zoaVWsuK60I9jJxRGNFEaoFqWThijIEYy3oEf ROC1vr3x6I0f161g5/268YEwWf9Dqrg2RLUWE5eABiVluS/KaHJ+jtm8zW+x24PlrPi8LQ+F6CJh 3XNYC8pFFavRnbaYefd9+GHgEvGMrpJBiqbxMV/k8MMCfu2j8RsM0syJpZvDclf4Ool4d0VwtWJs Ov2v2mVk7aIoJtUt58Xl33w+d/dPT09R1VhHVLZhupuYF6KLhHXPCagrnvxcYtU1Ai90VweLusKy LuFFEaIkwnzRIGgaRNkQ3J9T5nMgvCinzZFeLiJiwz570vPd1p7O0e7/GVUxuqKkuPzj9xTSdDpF XrRCZE7L+mqZrJTDEptIWHccy/u8LeJgApvicMunpu1BlSSr4s0iRx5Frg1MGAaIXKxVIy8KNHGC vUdPMUgqFLMce0GMcr5A/fw5/KMj+Kyg8pzuLnDVZ3nzYb/tiZUN8cMPP7gbc1RsSUNxhVGCf3z1 vy7Bzijr+PjY3R+NRloSikuRsO44lnTejGxsrx5P8AsUBRNJrpiTx4VsH+MBdVW6ZnxRELbFmaur defzKWq+pgaqskFdFhhUFZrAW9Vr3QzLQ1k+i6UMh4eHePDggfsd+PzXX3/txEaZMRJ78eKFO5bH CdFFwrrj2BaX7lCHbp6HNU38aoWXdnUt8Dz39fjFby6H5MRWN/DqBmEUYTAcOlksZw2KZY44TLGY LlCG7L5QYtFQJgFi/2YtYtxnCQK31OP7UVhWzU4+/fRT/Pjjj+53ePLkiSt14GuY5xJiEwmrZ2wu ySgqi7aKPMerV68wOz9z0dNsOkHeeHj27BkeP37skuKWQ3KJ8CxFlBygyisEUQQvnruq+CCNETC/ dQs1UFaaQBHxPfnZ+dl4o7Qosj/84Q8uouJSkFKj0Pi8yU4IQ8K645ic+HVzOUh4nwlrrDouMDKx rTB8zd5wjHE2cPlvjxXvTbtVZh2V+ZFb/rGFTDjI2iVoGCCGj/a64s2WhVbHZVN0+N6UkBWH8nGK isfxs1OoFFubi0uc6IQwJKweJd0vS3izNIAnOiXATqC7u7t4+OAQg8HAVTAU8xJ+FAJF6bbnZHGC erX1hVlyr2Guy8VVrpSh5pITwPTsHGVVYX//Znkkq6mikGwpyN+BYmKuip/37OxsXWjK57/99lsX KX7++ef405/+dMO/oLhPSFh3nG51OLEIiye2PUcoLCcpysFt6QtcAj1KUyxnM+TcFjPIECSx64Hl YNRWscrBu5gvK0qcnxxjOpncWFiWU7N5hfyM/NycZ/j3v/8df/vb35zIbA8hIys+9/333+Phw4c3 ++OJe4eEdcexJRVPcuZ1mGRn/RKjKvue8jo4OMBw0BZooq4wn81cDmsn23G5LSbaWeHOeqzJdOKU xaXYct6+3uWK2J0h4lf+w/BYbXrjz28SsiS7XTCwzqW2p5BfKSoe++uvv7oSB3uNEIaEdeepUbLw MoqQpjHOTo/x3T+/cWL6/e9/j3/893/h4OgBnh7twW9qd/vt9BiD4RiDBw8QVAWiJHU1VfNVNXnK 7Teo4aFB6k8xKeeYnZ5jON4HkKGogOTgEQ53P33np+s26usuV9thFO3VPibWWeFu+Sg+9sknn+CP f/yjky9vrM3iFUQKmBcJKDr+jtZ+hsfw9VaEqkr47UTCuuPwyh4ls1xFUjyJnz59ul5ePflde382 XWBZT7Cz29Yy8ST3V1twEjdV0Joh89IdNy/nTDAhjiM2aXBbdygxVsGzVmuUJq5lzLvoXgyw74kt YfkZiSXYCT8foynmsU5OTtZJdquA5xVDdm3gkpD5LT5vVwvVI2u7kbDuOFwqcXINT1RGKTx5GbFw OcgT/PGTz3B+NkXJrTbLHExHDbIRAlc/xRE4beGoq3FnlwZ2WljOsJyeo1xM4flMggdu+o3nTxFl IwyGOwhiNo15PzZlwvuUE6MjJtEZLR0dHbnHnz9/7n6X7777ziXerfUMoyjKjhcTvvrqKxeJ8TXd pbGhsoftQ8K649iJSmm5hnirCnW7+oY4gp+wqV6A0PWPCltxwEdeFgiaAH7AjcurIYQ84XnFcDlH OZ9iVuaIXTQWuoJRRlVRFCPgUFS+ZjUc9X2WhNaGhkIhLAylgHhjpMWKdoqYERSPtXIGipgRGY+j 4JjHsnII+zt0309947cPCeuOw9xVVZbuJHb1S6uqdet/zuERblR8lmJelE4EiyWT3O2m49Fg6IRF 3CqNswVZf1WkaMolkv09ZOkAfhih4EZktAlxNs1i+2TvmsLqllxQVLbEo1wpJIueeKOUXJO/LMMX X3yxzlPxRnEx+rKOpFwSdt+rK0WxfUhYdxxe7eNeO+Z6Hj161PY/T1OMxhz4wN4xw7blix8hCKco SpY8tINM295SbBnTLs140Y/tkX2WNlRDBGUBPxvDTxKEYYwwY1cHrh9XxZ7R9SvdN5Pgltfi56Wk +BkpMi4PTW78jH/5y1+cpHgsBcbflSUNjB4pOavbsp9puSw199tOJKw7DqMTNtezUgCe8K65XRy3 VeHDNqndxhvtSU75MI/Fcgbfm8P3Qpd0L1b5n8QPULOANB5gWQJLLgtjIMtasbgfds0i924b5G7C 3RoE8jOz5ILPMeJiHo4S4uOUDvNTjLgYGfIx3rcWM4yurEeW0RVWtxuq2A70X/yOwxOYV8zY3YBR Fbt0uquFq/12ZdudD0EQuZzVaLSDJKEwPCzmFQbD2PW34jYb17RvlcrilGY/zZGGAyeSmsMj2OGh /XGoS+aNfM6UeCcWLVn/Kt6siwTFwqWdbXzm1UHXRWLVH4u/AyXGfBWT7yxv+Otf/+pe/80337zx XiYvTZbeTiSsj4wtnexE5AnMk9s6MfDEfvb55+45FzGtjlvM5+6kDoPEbanhsXEYIc8XbSFmvsQi n2K8e+SOZ+xzoRGNF2I82ncRWxq2UQxzZa6w0/cQJq/F0I1w3taf622blN34r7J072NXAq17qS0F Xa5tNHJy5mdnhEWZ/fnPf16/zkTo/g6r6TuMyrrjwcT9R8L6yFgi2ZLIlJAtsVwnhqpYH9s9ae2Y bqTRnRvYXaJdRXcCzmXHb/bjMmyoxLv6rpuQ7Eax8vditMWrhVaDxffmYzaUgjdL2PM+BbUpSvV8 3z4krDuA5XesbslObIs0nEw6cwFNTOvnVo9bJGLfW9HmdYR1lbSsar07gKIr2auw5Z+bkuO3HUjt CqEtJTeXeoycmL/iyDHmv942p1AtlLcPCesjYyeq1SzxxOYJyzIGntQ2ZNSSzyYKO1n51Z7rtnIx SbyL7mveVq6wuQHbHn+j2+kl2HF8LaOpzfez33szOrT7lK6S68KQsO443QiIWKcGO9G5bOpuW7Fj unmxq3jXstGm5th78L3tPa+TP9qcL2gRoo27p5QpJevPZceZgPla6+/F7y2/RySy7UPC+shYpNQd bcUTl1fM2hzNKpm9iqpsajJpo6j2BO5KxZZft8Hmz6FomFfie/D93iUNvt4Gr1oJhL3WBGu5OcvJ 8fe235/fMzKzpoPa9LzdSFh3ADuJDWtm1ybkXx9j0QZvPMb1kEoHb2w8vk26S0LSzUddV4p2bPdm v2c3Wux2JOUyktGX/V0uW35qI/T2IWF9ZCwntVnWwO+ZeI/C11fpLNFuyyNWvNvP2ITHbYrwMq5z 0tsS0yIqlh5s5rTeRvfz2me1TctcElp+y6Ivax9jQuYVQjcsYyWy7pVBRVvbh4T1kdlc5nQjCS6F unCOH2f8XYf3Gd7wrqt9m9J7n9yRTYq26LCb++qOACP8O2z2cLcrnd2/hXJX24uEJT4ottyz5P1m kz9NxRHvg4QlPii23LVE+21dDBDbiYS15XzoPFD36md36Wl5MSHeBwlLfHA25WSJfi0HxfsiYYn/ t6ug3er2t20DEuIqJCzxwdnMW7F0wUoutIFZvA8SlvigWD2Y1Vqxtowbm1lvxu8fP36s/wLi2khY 95zZ8x9Q1jXiNEO6e+D6YHF6Dpv0sRMyqw7yxRKDJIQfsEUyizcrBGxzw27JG21lyGVX+ixP9cb2 GdZhNYBXVuCEi2Y6ww/ffo1fX73EeG8XURLj6PABimLp3tv2D7KXfdvJoV06bibuu9t6xPYgYd1z FnmOpvHgB7WbR8ghFO3J7q1Hf/lNiaqo4Dftfr4ojN08xNmiwGiYXJg9aBX3xuaewM28lHuPukIx n7v35/FPHj1uR5eFPn78/p8YphHiIESYZu41Hk25mvqTxuEbUZqhvu7bh4R1zwmiuN0LyDbJLgJi JMQIxTVKxuz8BGW+wKIqXLNARjh7Bw/gxSlCr/63hqgSa4HDeYmhz7mHNUr2bU9C1+fLjwL3XD6Z IF4NcEVZsJy//Zms+o+S9c+x7Tzdqni1Sd4+JKx7znhnD2XDivIQ3nq2X+X8UBRAEgWI/BjVssL5 dI55VbntMNwilGbJGyUJm3sILxu9Zb3abeKNF3OzNKfwrK4Ssr9XDSQhR381KBcL5OxaEScY7eyv Nn4D9GXFz3rJUrM7QUdsDxLWPcfPMsTu7Kdt7ARvIycu+1K3d4/RTQqmsDgMgknx3Shxexdr73Xb F2L1U5ft59tcOrYDXWtMJguXoxplA9eBIZ/OUMxnrnf8ZDLF2eQcVRBgsLOL0e6ei7YWZ+eoixr+ sG36x5ttnLbloYS1fUhY9xwqw8U9zlmvB154Xnv/5PgU+WKGLAoQc+JzFOP0bIJZ0SAdjHDw4HDd cI83YuUIm0s0+2pN9lx+q85xfj5zk3HiMMBwZ4x4Z4R6PkeVL7G/f4SXkzOX55rO50hPjpH4ISYv XmIQJ8AwvbSXvZLt24mEdc/h6HmbWujVq69+A5+CqYHZssS/vv8X4tDH754+QTIcY7KssMhL+Mnr qMlaFneldJU01pXsje86MJRlgflyifFihrDm1cgKTV4i/uxTHA2GKLwKr06PcXLyCl6+QHk2wdGn n6FYRVaGRLXdSFj3HS6dXNfSGnVTw+NVQROABzx8dISffvoJ09k5/CByCfG88rAsG2TDkTusu8Sz jczMcXVzV93ku0VkLlHe1Njd20OURHj54lf88ssvGDBiyisEVY1yskAThMjGQxzGAU5++wWzkxny ySlQPlgvPS2P1e1Oaol4sT1IWPeccD2+2UfgMfPdedLVWVX44j9/55Zs8yKHN59hd3/H9a6az0+R J74TA6Mkm+hj5QuUkuWW3ihnWDXkm0yXWJzO3RXAvXTsZicmWYqak4I4rHUQuGKwcj5l/2Xs7hzi 8OBhWwHf2Ti9iSKt7UTC2nJsqo0NgOBXi54oHA4ytejGespbC2feusn4za+8DQYZ3MDpKsNycobl fOFKHAbjMZJBykuG7RVBP0AYtSJ0MnKXFVUUKi4iYYk3ygYuLr9eS836zHcT4EZ3OdiNftYrttVS rjv9x9+cytO+mf6LiLciYW051nO9K6vuNhvLIVlfq26rYuvJbq/rTrF+LabVKrRsi1LHe3tA4KOu KkzPzpAMMjckVrIS10HC2nJsQo1FVN1yhXYZiFU+a+5k1S0c7dZivW0EFx/y+TCPZaEX9cX/rZaS F+q5Lmvop4BLdJCwxIXx8926Kt6nzGyIhE1ltseuYn3lkAs/5ykPKEosZ3O3qTpMknbAxKqY1aK6 7vLU3fTfR3SQsLaczXKE7uj4NqH+WlLWHsa23PBYu2p4Wb9293PNOE2D5WLhojU/DBAxWltvxG65 ICrlssQlSFhbjkVSlnsi3c3MX375JcbjMR49erS+gmiJctKdF9gdI2+v54U+eo/dGvhzWR4RDLI2 Z9VJuqsDqbgOEtbWQ1mxBKpYdwK1vYJRFOLZs2fryMnGzdvVQpeIzyc4nc7d8/sHh8jGO67mi/22 uA+RKfmqLlEy1IpS+K5Cvp1HeJ1Br0J00b8WcaGCvXulj4KypeDmkm99FdAa7PkXizyDwHP19Xbs 5tVGIf4dJKwtpzvglEu6blmD6/wZhlcOjNjd3UWctKUO0aoBn3V3cK9b1V+ZqLrJeolLvC8SlnB0 E922V++q5Pd6b2EYIRtFF6vSm8p1hrA9iyaqzZ/VrdcS4jpIWFtOd5nX7eBpm4wvG4J64criWjx1 WwDK17ouDfxZF5P4XSyS0+Zl8T5IWFvOZcMdNruKXvW6VnLMeQG+VczXVVsE2tRo3EbCy99HiPdF whJrrlsDdaE/lRWd8v+aysmKnUzLIndXHQe7bV7L6IpKHRfE+yJhbTmXDZDoPndZfVb3+IrR2KpJ oHvMJdo9RF4MjwJ7CyoOFf8OEtaWc1U0dVnLmMv+AbUzbtoCUZsjCI7tGr7eKG0oqhI3QcISQvQG CUsI0RskLCFEb5CwhBC9QcISQvQGCUsI0RskLCFEb5CwxJWwwmqxyF1Pd8Imfu1IsFXhaDV3O3Ha 7gztCPv1tp2KlfD6A4vbQ8ISVzKbTl2bmflsgtlshizLcHh46MTEdsl5MYPvtTMKKSwhPiT6Fyau JPJqpEkIlDGaYoFBHCBL246hdT5HURaIo2DdpfT1zEL9YcXtI2GJKynyJUruJ6wrDLLU3diFIZ/P MTk/w+hgH3GUruYV+ustOm7fIcfjCHGLSFji6n8gYeiWflwWcixXytFcq46iHCjBx8KgHab6uldW e/8dHWqEeG8kLHElyXCEoqxQN9zPHLVZ9KZBOhwhHY3ReN0xYW1rZUZaTMorvhK3jYQlrmSZV6j9 CLUPTJclorod68XIizePcwvXHUgvdildNXEQQsIS/z+EUYI4Sdz9srTx8u1aryhrRGG3B3y3pTJQ lXy9/kuJ20MRlriSoJOHilaiuvj9qo/7RsKK3pKsxG0jYQkheoOEJYToDRKWEKI3SFhCiN4gYQkh eoOEJYToDRKWEAJ94f8AgLU6M7/iYEMAAAAASUVORK5CYII=