Drone Recognition Using YOLOv7
Drones are widely used to serve various purposes in industry, mapping, and crisis management. However, the use of drones is increasing in important places such as airports, power plants, and important buildings, endangering public safety and causing problems with aircraft. For this reason, it is very important to detect and recognize them accurately and quickly to prevent security problems caused by unauthorized access to critical infrastructures. In this project, a novel and accurate technique based on deep learning networks is presented to detect and recognize 3 types of flying drones in visible images and differentiate them from birds using a set of 26,000 normal visible images.
DESCRIPTION
Three-dimensional modeling of cultural heritage requires the use of powerful tools and fast and cost-effective methods to obtain and accurately record information due to the complexity, scale, and limited access to these works. Drone is one of the new methods used in 3D modeling of cultural heritage with the advancement of technology in recent decades.
Below is an example of Deyre Gachin Caravansary project, created with a real texture and a scale of 1200. The evaluation of the results shows the high performance of UAV photogrammetry as a fast method for three-dimensional modeling with a ground accuracy of better than 2 cm.
Specifications of drones and cameras used in the research
RESULTE
Through the use of drones and depending on the characteristics of the equipment used for data acquisition and the altitude of flight, correct results of the cultural heritage can be obtained. The three-dimensional model is created and contains all the geometrical, spectral and textural information of the model. The fast, inexpensive and non-destructive extraction of data from complex and extensive works with limited access is the greatest strength of this method. Output of 3D model of Deyre Gachin Caravansary with real texture.
(a) East porch view from the central courtyard of Deyre Gachin.
(b) Bird view from the north side 3D model.
No comments