Real time human detection using UAV and visualization on GIS platform | |
| Author | Bhattarai, Nemi |
| Call Number | AIT Thesis no.RS-18-03 |
| Subject(s) | Drone aircraft Visual perception Geographic Information System |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Remote Sensing and Geographic Information Systems, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | Human detection from UAV is gaining popularity in the field of disaster management, crowd counting, people monitoring, etc. Real time human detection from UAV is a challenging task, because of many constraints involved. Among many, flying height of UAV, computation time, scale of viewing and accuracy of detection were considered important and addressed in this study. An android application to receive and transmit UAV telemetry data to the computer was developed. Then, a binary classifier based on Haar-like features was trained using experimentally collected UAV images for human/not human class. The video frames were parsed and detected humans from image frames were geo-localized and visualized on Google Earth. Furthermore, geolocation error of detected humans was computed. Based on flying height and human size relationship, the study came up with optimal parameters for OpenCV's cv2.cascade Classifier detect Multi Scale function. The results show that the geolocation error is dependent on the accuracy of onboard GPS. Scale factor in conjunction with size of the detector can significantly affect the processing time. For real time application, an optimal tradeoff between detection accuracy and computation time was needed. This research establishes a strong ground for further research relating to real time human detection from UAV. |
| Year | 2018 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Nakamura, Tai |
| Examination Committee(s) | Ochi, Shiro ; Miyazaki, Hiroyuki |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2018 |