Modeling of Optimal Deep Learning Enabled Object Detection and Classification on Drone Imagery

Object detection in unmanned aerial vehicle (UAV) images becomes a persistent problem in the domain of computer vision. Particularly, object detection in drone images is a difficult process because of the object of different scales namely, hills, buildings, and water bodies. The study presents an execution of ensemble transfer learning to improve the efficiency of the fundamental model for multi-scale object recognition in drone imagery. This study develops an Optimal Deep Learning Enabled Object Detection and Classification on Drone Imagery (ODL-ODCDI) technique. The presented ODL-ODCDI technique can recognize and classify the objects present in the images collected by the drones. It follows a two stage process. In the first level, the ODL-ODCDI technique employed YOLO-v5 as object detector with Nadam optimizer. Next, in the latter level, the ODL-ODCDI technique makes use of random forest (RF) classifier to identify objects in the drone images. To establish the enhanced performance of the ODL-ODCDI approach, a series of experiments were performed. The experimental values depicted the improved outcomes of the ODL-ODCDI method over other DL models.