Use your Computer Vision skills to tackle homelessness.

The Data Library is currently running a data project to convert 5 years of monthly homelessness person locations from scanned paper maps to a geographic dataset. The bulk of the work involves volunteers manually digitizing 350 scanned paper maps in two jobs, but we have enough data to build a computer vision solution.

If you have skills, or motivated interest, in programming OpenCV in Python, you can put your talents to service for humanity, by working on the computer vision portion of this project.

Over the past few months, the Data Library has been involved in several projects to study homelessness in San Diego. The main projects have been:

• Digitizing 5 years of monthly homelessness counts for Downtown San Diego.
• Building a collection of data about homeless issues for San Diego and Los Angeles.

Last Spring, we got the first portion of the Downtown homelessness data converted with the help of Kearney High students, and this fall, we’ll be finishing the rest of the data conversion and doing data analysis. If you’d like to participate, you can contact me, or watch for our next project meetup.

Here is an overview of our current projects. If you’d like to join a project, contact Eric Busboom, eric@sandiegodata.org. Homelessness Counts. Digitize and analyze 5 years of monthly counts of the homeless in Downtown San Diego. The San Diego Downtown Partnership counts the homeless downtown every month, and now has about 5 years of paper maps recording the positions of where homeless individuals were sleeping. This project will digitize these maps, extracting the position information, to create a detailed dataset. Then we will analyze the data, by linking homelessness to land use, business location and traffic patterns. The project can be done with manual GIS work, but would be best done with image recognition to geo-reference the maps and extract handwritten marks. Needs:

For its data program for Summer 2018, The San Diego Regional Data Library proposes to build a data repository for water quality data, to make it easier to find water quality data, link it together and to create maps, reports and analyses. The project will be run with a small paid staff and a group of volunteers, and if the project is successful, we will pursue funding for continued maintenance. This project is over, but see theproject website for archived results. Data we expect to collect, process and store will include: