Difference between revisions of "Assessing Damage"
m |
m |
||
| Line 14: | Line 14: | ||
** [[Risk, Compliance and Regulation]] | ** [[Risk, Compliance and Regulation]] | ||
* [[Explainable Artificial Intelligence (XAI)]] | * [[Explainable Artificial Intelligence (XAI)]] | ||
| − | |||
| − | |||
{|<!-- T --> | {|<!-- T --> | ||
| + | | valign="top" | | ||
| + | {| class="wikitable" style="width: 550px;" | ||
| + | || | ||
| + | <youtube>uoBmao2x_YI</youtube> | ||
| + | <b>LogiMove AI Damage Detector | ||
| + | </b><br>LogiMove CheckMobile Global Our AI solution to detect mechanical damages on your equipment. | ||
| + | |} | ||
| + | |<!-- M --> | ||
| valign="top" | | | valign="top" | | ||
{| class="wikitable" style="width: 550px;" | {| class="wikitable" style="width: 550px;" | ||
| Line 23: | Line 29: | ||
<youtube>m24GfyFzSX0</youtube> | <youtube>m24GfyFzSX0</youtube> | ||
<b>Assessing Property Damage with AI | <b>Assessing Property Damage with AI | ||
| − | </b><br>The critical task of damage claim processing is typically labor-intensive and requires a significant amount of time. The deep learning tools within Esri ArcGIS sped up the process to provide aid to those affected by the Woolsey fire. This demo shows the workflow used; from training the deep learning model to inferring which automated the detection of damaged homes. For this demo, we used a client-server architecture which gives a clean separation of the roles of a Geographic Information System (GIS) Analyst and a Data Scientist. The GIS Analyst uses NVIDIA Quadro Virtual Data Center Workstation (Quadro vDWS) software to create, edit and explore spatial data. The Data Scientist uses [[NVIDIA]] Virtual Compute Server (vComputeServer) software to train/build a model which will then be used by the GIS Analyst to execute object detection inferencing. "To learn more about virtualization in the data center, and to try building and running this demo yourself using free trails of both virtual GPUs and ArcGIS (including the imagery used in this study from [http://www.nvidia.com/en-us/data-center/virtualization/resources/ OpenAerialMap]) | + | </b><br>The critical task of damage claim processing is typically labor-intensive and requires a significant amount of time. The deep learning tools within Esri ArcGIS sped up the process to provide aid to those affected by the Woolsey fire. This demo shows the workflow used; from training the deep learning model to inferring which automated the detection of damaged homes. For this demo, we used a client-server architecture which gives a clean separation of the roles of a Geographic Information System (GIS) Analyst and a Data Scientist. The GIS Analyst uses NVIDIA Quadro Virtual Data Center Workstation (Quadro vDWS) software to create, edit and explore spatial data. The Data Scientist uses [[NVIDIA]] Virtual Compute Server (vComputeServer) software to train/build a model which will then be used by the GIS Analyst to execute object detection inferencing. "To learn more about virtualization in the data center, and to try building and running this demo yourself using free trails of both virtual GPUs and ArcGIS (including the imagery used in this study from [http://www.nvidia.com/en-us/data-center/virtualization/resources/ OpenAerialMap]) |
|} | |} | ||
|}<!-- B --> | |}<!-- B --> | ||
| + | |||
| + | |||
= <span id="Earthquake"></span>Earthquake = | = <span id="Earthquake"></span>Earthquake = | ||
Revision as of 08:54, 11 September 2020
Youtube search... ...Google search
|
|
Earthquake
|
Vehicle
|
|
|
|