Our approach is to collect images, GPS and other data with smartphones, use computer vision algorithms to analyze the images, and save the results in the database of the maintenance department where it can be displayed to the user or further analyzed.
 
To use our approach, you need a smart camera that can be mounted on the windshield and powered through the cigarette lighter. You may need a database system to store the output inventory and assessment data. You may also want computer software like Google Earth, QGIS, or ArcGIS, to visualize the output images on a map.
 
While the car is driving the smartphone collects images of the outside and tags them with GPS and all the other information. The data is transmitted to a central computer via Wifi where it is analyzed. You could either train our algorithms to analyze your images, or skip this step. In the latter case, you could use our trained algorithms (ready-to-use classifier) to directly get the output. The output inventory/assessment information can be managed in your database. The images/information can be viewed with Google Earth, QGIS, ArcGIS, etc, locally and remotely. The user can zoom in to the location of interest in the city and click on a small icons which brings up an image of the location.

Note: Currently, only the instructions for camera setup, data collection and pre-processing are posted. Documentation regarding data assessment etc. will be published in the near future.