elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Improving YOLOv8 with Scattering Transform and Attention for Maritime Awareness

Carrillo Perez, Borja Jesus and Bueno Rodriguez, Angel and Barnes, Sarah and Stephan, Maurice (2023) Improving YOLOv8 with Scattering Transform and Attention for Maritime Awareness. In: Proceedings of 13th International Symposium on Image and Signal Processing and Analysis (ISPA 2023). IEEEXplore. IEEE 2023 International Symposium on Image and Signal Processing and Analysis (ISPA), 17-18 Sep 2023, Rome, Italy. doi: 10.1109/ISPA58351.2023.10279352.

[img] PDF
5MB

Official URL: https://ieeexplore.ieee.org/document/10279352

Abstract

Ship recognition and georeferencing using monitoring cameras are crucial to many applications in maritime situational awareness. Although deep learning algorithms are available for ship recognition tasks, there is a need for innovative approaches that attain higher precision rates irrespective of ship sizes, types, or physical hardware limitations. Furthermore, their deployment in maritime environments requires embedded systems capable of image processing, with balanced accuracy, reduced latency and low energy consumption. To achieve that, we build upon the foundations of the standard YOLOv8 and present a novel architecture that improves the segmentation and georeferencing of ships in the context of maritime awareness using a real-world dataset (ShipSG). Our architecture synergizes global and local features in the image for improved ship segmentation and georeferencing. The 2D scattering-transform enhances the YOLOv8 backbone by extracting global structural features from the image. The addition of convolutional block attention module (CBAM) in the head allows focusing on relevant spatial and channel-wise regions. We achieve mAP of 75.46%, comparable to larger YOLOv8 models at a much faster inference speed, 59.3 milliseconds per image, when deployed on the NVIDIA Jetson Xavier AGX as target embedded system. We applied the modified network to georeference the segmented ship masks, with a georeferencing distance error of 18 meters, which implies comparable georeferencing performance to non-embedded approaches.

Item URL in elib:https://elib.dlr.de/198489/
Document Type:Conference or Workshop Item (Speech)
Title:Improving YOLOv8 with Scattering Transform and Attention for Maritime Awareness
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Carrillo Perez, Borja JesusUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Bueno Rodriguez, AngelUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Barnes, SarahUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Stephan, MauriceUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:September 2023
Journal or Publication Title:Proceedings of 13th International Symposium on Image and Signal Processing and Analysis (ISPA 2023)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI:10.1109/ISPA58351.2023.10279352
Publisher:IEEEXplore
Status:Published
Keywords:Real-time instance segmentation, YOLOv8, scattering transform, attention, georeferencing, maritime awareness
Event Title:IEEE 2023 International Symposium on Image and Signal Processing and Analysis (ISPA)
Event Location:Rome, Italy
Event Type:international Conference
Event Dates:17-18 Sep 2023
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:no assignment
DLR - Program:no assignment
DLR - Research theme (Project):no assignment
Location: Bremerhaven
Institutes and Institutions:Institute for the Protection of Maritime Infrastructures
Deposited By: Carrillo Perez, Borja Jesus
Deposited On:10 Nov 2023 13:58
Last Modified:10 Nov 2023 13:58

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.