SlimDeblurGAN-Based Motion Deblurring and Marker Detection for Autonomous Drone Landing

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 14; p. 3918
• Main Authors: Truong, Noi Quang, Lee, Young Won, Owais, Muhammad, Nguyen, Dat Tien, Batchuluun, Ganbayar, Pham, Tuyen Danh, Park, Kang Ryoung
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 14.07.2020; MDPI
• Subjects: Accuracy; Algorithms; autonomous landing; Cameras; Datasets; Deburring; Deep learning; deep-learning-based motion deblurring and marker detection; Drones; Embedded systems; Landing; Light; Markers; Methods; Model accuracy; Motion perception; network slimming; Neural networks; pruning model; Sensors; unmanned aerial vehicle; Unmanned aerial vehicles
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20143918

Deep learning-based marker detection for autonomous drone landing is widely studied, due to its superior detection performance. However, no study was reported to address non-uniform motion-blurred input images, and most of the previous handcrafted and deep learning-based methods failed to operate with these challenging inputs. To solve this problem, we propose a deep learning-based marker detection method for autonomous drone landing, by (1) introducing a two-phase framework of deblurring and object detection, by adopting a slimmed version of deblur generative adversarial network (DeblurGAN) model and a You only look once version 2 (YOLOv2) detector, respectively, and (2) considering the balance between the processing time and accuracy of the system. To this end, we propose a channel-pruning framework for slimming the DeblurGAN model called SlimDeblurGAN, without significant accuracy degradation. The experimental results on the two datasets showed that our proposed method exhibited higher performance and greater robustness than the previous methods, in both deburring and marker detection.