Loading [MathJax]/extensions/MathMenu.js
Modeling of Optimal Deep Learning Enabled Object Detection and Classification on Drone Imagery | IEEE Conference Publication | IEEE Xplore

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


Abstract:

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 ...Show More

Abstract:

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.
Date of Conference: 24-26 November 2022
Date Added to IEEE Xplore: 16 January 2023
ISBN Information:
Conference Location: Trichy, India

I. Introduction

Nowadays, the drone, otherwise called UAV, is becoming popular equipment for its trade-off among stability and mobility in several applications like agricultural production, security surveillance, express delivery, and aerial photography, where drone image-related object detection becomes an important problem Various computer vision (CV) tasks like image segmentation and object detection have obtained popularity during the previous few decades [1], [2]. Object detection (OD) was difficult and valuable to detect the several graphic substances of a detailed period (like topographies, cars, creatures, pedestrians, and so on.) in the images. OD contracts with the expansion of computing techniques and approaches and one important snag of computer vision (CV) [3]. Furthermore, it is a base of further errands like object tracking, segmentation, and, image captioning, and so on. So, OD discovers its tradition in numerous fields like remote satellite detection, face detection, and pedestrian detection, etc [4]. One conceivable way to overwhelmed difficulties with analyzing imageries from drones is to mechanize approaches for the enumeration, detection, and localization of targeted animals [5].

References

References is not available for this document.