Stereo-Video UAV (ENGR 415)

The recent commercialization of unoccupied aerial vehicles (UAVs) has facilitated their incorporation into a variety of ecological studies. While UAVs are able to provide accurate visual data from an aerial perspective, these devices remain limited in their ability to accurately measure the size of smaller organisms (i.e.< 2 m). Over the past 3 years, we developed and tested a stereo-video camera (SVC) system that was mounted onto a commercially-available UAV (DJI Matrice 600 Pro). We used the SVC-UAV to conduct remote body-size measurements for two marine species: the green sea turtle (Chelonia mydas) and the nurse shark (Ginglymostoma cirratum). When comparing SVC measurements to those taken by hand, the SVC-UAV had a mean absolute error (MAE) of 4.44 cm (n=6) for green sea turtles and 7.16 cm (n=1) for the nurse shark. 

*NOTE: This project requires you to transfer to the ENGR 415/416 section of Capstone. Project Partner is Joe Piacenza.

Objectives

 

  • This team will focus on lightweighting the current SVC design, and adapting it to work with a DJI Mavic Air 2, so it can be used by biologists in the field.
  • Building off video imaging software tool we created (in MATLAB), covert video post- processing method to Python, with user friendly GUI.
  • Detailed requirements for each team will be defined in meetings with the sponsor and advisor following project assignment.

Motivations

To our knowledge, there is no other stand-alone SVC for UAVs available that offers similar accuracy and utility.

Qualifications

Minimum Qualifications:
None Listed

Preferred Qualifications:
None Listed


Details

Project Partner:

Joseph 0

NDA/IPA:

No Agreement Required

Number Groups:

1

Project Status:

Accepting Applicants

Keywords:
UAV
Card Image Capstone