Underwater object detection using Invert Multi-Class Adaboost with deep learning

Long Chen; Zhihua Liu; Lei Tong; Zheheng Jiang; Shengke Wang; Junyu Dong; Huiyu Zhou

doi:10.1109/IJCNN48605.2020.9207506

Underwater object detection using Invert Multi-Class Adaboost with deep learning

Long Chen, Zhihua Liu, Lei Tong, Zheheng Jiang, Shengke Wang, Junyu Dong, Huiyu Zhou

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

91 Citations (Scopus)

Abstract

In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in real applications are usually small and their images are blurry, and (2) images in the underwater datasets and real applications accompany heterogeneous noise. To address these two problems, we first propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection. SWIPENet consists of high resolution and semanticrich Hyper Feature Maps which can significantly improve small object detection accuracy. In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet. Experiments on two underwater robot picking contest datasets URPC2017 and URPC2018 show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.

Original language	English
Title of host publication	2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728169262
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9207506
Publication status	Published - Jul 2020
Externally published	Yes
Event	2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom Duration: 19 Jul 2020 → 24 Jul 2020

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Name	International Joint Conference on Neural Networks (IJCNN): Proceedings
Publisher	IEEE
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	2020 International Joint Conference on Neural Networks, IJCNN 2020
Country/Territory	United Kingdom
City	Virtual, Glasgow
Period	19/07/2020 → 24/07/2020

Bibliographical note

Funding Information:
ACKNOWLEDGMENT Thanks for National Natural Science Foundation of China and Dalian Municipal People’s Government providing the underwater object detection datasets for research purposes. This project of underwater object detection is supported by China Scholarship Council.

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Multi-Class Adaboost
noisy data
sample re-weighting
underwater object detection

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN48605.2020.9207506Licence: Unspecified

Cite this

Chen, L., Liu, Z., Tong, L., Jiang, Z., Wang, S., Dong, J., & Zhou, H. (2020). Underwater object detection using Invert Multi-Class Adaboost with deep learning. In 2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings Article 9207506 (Proceedings of the International Joint Conference on Neural Networks), (International Joint Conference on Neural Networks (IJCNN): Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN48605.2020.9207506

Chen, Long ; Liu, Zhihua ; Tong, Lei et al. / Underwater object detection using Invert Multi-Class Adaboost with deep learning. 2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (Proceedings of the International Joint Conference on Neural Networks). (International Joint Conference on Neural Networks (IJCNN): Proceedings).

@inproceedings{188e32c01c89451396a48f5baa0cd108,

title = "Underwater object detection using Invert Multi-Class Adaboost with deep learning",

abstract = "In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in real applications are usually small and their images are blurry, and (2) images in the underwater datasets and real applications accompany heterogeneous noise. To address these two problems, we first propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection. SWIPENet consists of high resolution and semanticrich Hyper Feature Maps which can significantly improve small object detection accuracy. In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet. Experiments on two underwater robot picking contest datasets URPC2017 and URPC2018 show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.",

keywords = "Multi-Class Adaboost, noisy data, sample re-weighting, underwater object detection",

author = "Long Chen and Zhihua Liu and Lei Tong and Zheheng Jiang and Shengke Wang and Junyu Dong and Huiyu Zhou",

note = "Funding Information: ACKNOWLEDGMENT Thanks for National Natural Science Foundation of China and Dalian Municipal People{\textquoteright}s Government providing the underwater object detection datasets for research purposes. This project of underwater object detection is supported by China Scholarship Council. Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

year = "2020",

month = jul,

doi = "10.1109/IJCNN48605.2020.9207506",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings",

address = "United States",

}

Chen, L, Liu, Z, Tong, L, Jiang, Z, Wang, S, Dong, J & Zhou, H 2020, Underwater object detection using Invert Multi-Class Adaboost with deep learning. in 2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings., 9207506, Proceedings of the International Joint Conference on Neural Networks, International Joint Conference on Neural Networks (IJCNN): Proceedings, Institute of Electrical and Electronics Engineers Inc., 2020 International Joint Conference on Neural Networks, IJCNN 2020, Virtual, Glasgow, United Kingdom, 19/07/2020. https://doi.org/10.1109/IJCNN48605.2020.9207506

Underwater object detection using Invert Multi-Class Adaboost with deep learning. / Chen, Long; Liu, Zhihua; Tong, Lei et al.
2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9207506 (Proceedings of the International Joint Conference on Neural Networks), (International Joint Conference on Neural Networks (IJCNN): Proceedings).

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

TY - GEN

T1 - Underwater object detection using Invert Multi-Class Adaboost with deep learning

AU - Chen, Long

AU - Liu, Zhihua

AU - Tong, Lei

AU - Jiang, Zheheng

AU - Wang, Shengke

AU - Dong, Junyu

AU - Zhou, Huiyu

N1 - Funding Information: ACKNOWLEDGMENT Thanks for National Natural Science Foundation of China and Dalian Municipal People’s Government providing the underwater object detection datasets for research purposes. This project of underwater object detection is supported by China Scholarship Council. Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/7

Y1 - 2020/7

N2 - In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in real applications are usually small and their images are blurry, and (2) images in the underwater datasets and real applications accompany heterogeneous noise. To address these two problems, we first propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection. SWIPENet consists of high resolution and semanticrich Hyper Feature Maps which can significantly improve small object detection accuracy. In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet. Experiments on two underwater robot picking contest datasets URPC2017 and URPC2018 show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.

AB - In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in real applications are usually small and their images are blurry, and (2) images in the underwater datasets and real applications accompany heterogeneous noise. To address these two problems, we first propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection. SWIPENet consists of high resolution and semanticrich Hyper Feature Maps which can significantly improve small object detection accuracy. In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet. Experiments on two underwater robot picking contest datasets URPC2017 and URPC2018 show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.

KW - Multi-Class Adaboost

KW - noisy data

KW - sample re-weighting

KW - underwater object detection

UR - http://www.scopus.com/inward/record.url?scp=85093855296&partnerID=8YFLogxK

U2 - 10.1109/IJCNN48605.2020.9207506

DO - 10.1109/IJCNN48605.2020.9207506

M3 - Conference contribution

AN - SCOPUS:85093855296

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 International Joint Conference on Neural Networks, IJCNN 2020

Y2 - 19 July 2020 through 24 July 2020

ER -

Chen L, Liu Z, Tong L, Jiang Z, Wang S, Dong J et al. Underwater object detection using Invert Multi-Class Adaboost with deep learning. In 2020 International Joint Conference on Neural Networks, IJCNN 2020: Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9207506. (Proceedings of the International Joint Conference on Neural Networks). (International Joint Conference on Neural Networks (IJCNN): Proceedings). doi: 10.1109/IJCNN48605.2020.9207506

Underwater object detection using Invert Multi-Class Adaboost with deep learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this