Enhancing object detection in aerial imagesopen access
- Authors
- Pandey, Vishal; Anand, Khushboo; Kalra, Anmol; Gupta, Anmol; Roy, Partha Pratim; Kim, Byung-Gyu
- Issue Date
- May-2022
- Publisher
- AMER INST MATHEMATICAL SCIENCES-AIMS
- Keywords
- object detection; aerial images; VisDrone-2019; drones; RetinaNet
- Citation
- MATHEMATICAL BIOSCIENCES AND ENGINEERING, v.19, no.8, pp 7920 - 7932
- Pages
- 13
- Journal Title
- MATHEMATICAL BIOSCIENCES AND ENGINEERING
- Volume
- 19
- Number
- 8
- Start Page
- 7920
- End Page
- 7932
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/152753
- DOI
- 10.3934/mbe.2022370
- ISSN
- 1547-1063
1551-0018
- Abstract
- Unmanned Aerial Vehicles have proven to be helpful in domains like defence and agriculture and will play a vital role in implementing smart cities in the upcoming years. Object detection is an essential feature in any such application. This work addresses the challenges of object detection in aerial images like improving the accuracy of small and dense object detection, handling the class-imbalance problem, and using contextual information to boost the performance. We have used a density map-based approach on the drone dataset VisDrone-2019 accompanied with increased receptive field architecture such that it can detect small objects properly. Further, to address the class imbalance problem, we have picked out the images with classes occurring fewer times and augmented them back into the dataset with rotations. Subsequently, we have used RetinaNet with adjusted anchor parameters instead of other conventional detectors to detect aerial imagery objects accurately and effi- ciently. The performance of the proposed three step pipeline of implementing object detection in aerial images is a significant improvement over the existing methods. Future work may include improvement in the computations of the proposed method, and minimising the effect of perspective distortions and occlusions.
- Files in This Item
-
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.