Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection

Lin Xu; Hurriyatul Fitriyah; Craig Styan; Ivan Lee

doi:10.1145/3626641.3627016

Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection

Lin Xu
, Hurriyatul Fitriyah
, Craig Styan
, Ivan Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

The field of underwater object detection has gained significant attention recently, yet it remains challenged by issues like turbid water conditions and limited lighting, despite the rapid development in deep learning algorithms. In this paper, we try to provide a novel hybrid underwater object detection framework, named Efficient-YOLOv8, designed to address confusion-scale, low-resolution and small targets. In particular, our focus lies on the detection of cuttlefish, an underwater mollusc species known for its irregular postures. In our self-collected dataset, our proposed approach demonstrates remarkable results, achieving a precision of 94.18%, recall of 97.40%, and mAP of 98.18%.

Original language	English
Title of host publication	SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology
Publisher	Association for Computing Machinery
Pages	119-128
Number of pages	10
ISBN (Electronic)	9798400708503
DOIs	https://doi.org/10.1145/3626641.3627016
Publication status	Published - 24 Oct 2023
Externally published	Yes
Event	8th International Conference on Sustainable Information Engineering and Technology, SIET 2023 - Bali, Indonesia Duration: 24 Oct 2023 → 25 Oct 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	8th International Conference on Sustainable Information Engineering and Technology, SIET 2023
Country/Territory	Indonesia
City	Bali
Period	24/10/23 → 25/10/23

Keywords

EfficientDet
object detection
underwater
YOLOv8

Access to Document

10.1145/3626641.3627016

Cite this

Xu, L., Fitriyah, H., Styan, C., & Lee, I. (2023). Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection. In SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology (pp. 119-128). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3626641.3627016

@inproceedings{94647eb2acfd4ae89b9a21693a85bbdb,

title = "Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection",

abstract = "The field of underwater object detection has gained significant attention recently, yet it remains challenged by issues like turbid water conditions and limited lighting, despite the rapid development in deep learning algorithms. In this paper, we try to provide a novel hybrid underwater object detection framework, named Efficient-YOLOv8, designed to address confusion-scale, low-resolution and small targets. In particular, our focus lies on the detection of cuttlefish, an underwater mollusc species known for its irregular postures. In our self-collected dataset, our proposed approach demonstrates remarkable results, achieving a precision of 94.18\%, recall of 97.40\%, and mAP of 98.18\%.",

keywords = "EfficientDet, object detection, underwater, YOLOv8",

author = "Lin Xu and Hurriyatul Fitriyah and Craig Styan and Ivan Lee",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 8th International Conference on Sustainable Information Engineering and Technology, SIET 2023 ; Conference date: 24-10-2023 Through 25-10-2023",

year = "2023",

month = oct,

day = "24",

doi = "10.1145/3626641.3627016",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "119--128",

booktitle = "SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology",

}

Xu, L, Fitriyah, H, Styan, C & Lee, I 2023, Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection. in SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 119-128, 8th International Conference on Sustainable Information Engineering and Technology, SIET 2023, Bali, Indonesia, 24/10/23. https://doi.org/10.1145/3626641.3627016

Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection. / Xu, Lin; Fitriyah, Hurriyatul; Styan, Craig et al.
SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology. Association for Computing Machinery, 2023. p. 119-128 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Efficient-YOLOv8

T2 - 8th International Conference on Sustainable Information Engineering and Technology, SIET 2023

AU - Xu, Lin

AU - Fitriyah, Hurriyatul

AU - Styan, Craig

AU - Lee, Ivan

PY - 2023/10/24

Y1 - 2023/10/24

N2 - The field of underwater object detection has gained significant attention recently, yet it remains challenged by issues like turbid water conditions and limited lighting, despite the rapid development in deep learning algorithms. In this paper, we try to provide a novel hybrid underwater object detection framework, named Efficient-YOLOv8, designed to address confusion-scale, low-resolution and small targets. In particular, our focus lies on the detection of cuttlefish, an underwater mollusc species known for its irregular postures. In our self-collected dataset, our proposed approach demonstrates remarkable results, achieving a precision of 94.18%, recall of 97.40%, and mAP of 98.18%.

AB - The field of underwater object detection has gained significant attention recently, yet it remains challenged by issues like turbid water conditions and limited lighting, despite the rapid development in deep learning algorithms. In this paper, we try to provide a novel hybrid underwater object detection framework, named Efficient-YOLOv8, designed to address confusion-scale, low-resolution and small targets. In particular, our focus lies on the detection of cuttlefish, an underwater mollusc species known for its irregular postures. In our self-collected dataset, our proposed approach demonstrates remarkable results, achieving a precision of 94.18%, recall of 97.40%, and mAP of 98.18%.

KW - EfficientDet

KW - object detection

KW - underwater

KW - YOLOv8

UR - https://www.scopus.com/pages/publications/85182391561

U2 - 10.1145/3626641.3627016

DO - 10.1145/3626641.3627016

M3 - Conference contribution

AN - SCOPUS:85182391561

T3 - ACM International Conference Proceeding Series

SP - 119

EP - 128

BT - SIET 2023 - Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology

PB - Association for Computing Machinery

Y2 - 24 October 2023 through 25 October 2023

ER -

Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this