B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion
With the increasing maturity of underwater agents-related technologies, underwater object recognition algorithms based on underwater robots have become a current hotspot for academic and applied research. However, the existing underwater imaging conditions are poor, the images are blurry, and the un...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/10/11/1764 |
_version_ | 1797464934377848832 |
---|---|
author | Jun Wang Shuman Qi Chao Wang Jin Luo Xin Wen Rui Cao |
author_facet | Jun Wang Shuman Qi Chao Wang Jin Luo Xin Wen Rui Cao |
author_sort | Jun Wang |
collection | DOAJ |
description | With the increasing maturity of underwater agents-related technologies, underwater object recognition algorithms based on underwater robots have become a current hotspot for academic and applied research. However, the existing underwater imaging conditions are poor, the images are blurry, and the underwater robot visual jitter and other factors lead to lower recognition precision and inaccurate positioning in underwater target detection. A YOLOX-based underwater object detection model, B-YOLOX-S, is proposed to detect marine organisms such as echinus, holothurians, starfish, and scallops. First, Poisson fusion is used for data amplification at the input to balance the number of detected targets. Then, wavelet transform is used to perform Style Transfer on the enhanced images to achieve image restoration. The clarity of the images and detection targets is further increased and the generalization of the model is enhanced. Second, a combination of BIFPN-S and FPN is proposed to fuse the effective feature layer obtained by the Backbone layer to enhance the detection precision and accelerate model detection. Finally, the localization loss function of the prediction layer in the network is replaced by EIoU_Loss to heighten the localization precision in detection. Experimental results comparing the B-YOLOX-S algorithm model with mainstream algorithms such as FasterRCNN, YOLOV3, YOLOV4, YOLOV5, and YOLOX on the URPC2020 dataset show that the detection precision and detection speed of the algorithm model have obvious advantages over other algorithm networks. The average detection accuracy mAP value is 82.69%, which is 5.05% higher than the benchmark model (YOLOX-s), and the recall rate is 8.03% higher. Thus, the validity of the algorithmic model proposed in this paper is demonstrated. |
first_indexed | 2024-03-09T18:14:16Z |
format | Article |
id | doaj.art-ee4e4f74aab8452da867c355d601ece9 |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-09T18:14:16Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-ee4e4f74aab8452da867c355d601ece92023-11-24T08:52:31ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-11-011011176410.3390/jmse10111764B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature FusionJun Wang0Shuman Qi1Chao Wang2Jin Luo3Xin Wen4Rui Cao5College of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaWith the increasing maturity of underwater agents-related technologies, underwater object recognition algorithms based on underwater robots have become a current hotspot for academic and applied research. However, the existing underwater imaging conditions are poor, the images are blurry, and the underwater robot visual jitter and other factors lead to lower recognition precision and inaccurate positioning in underwater target detection. A YOLOX-based underwater object detection model, B-YOLOX-S, is proposed to detect marine organisms such as echinus, holothurians, starfish, and scallops. First, Poisson fusion is used for data amplification at the input to balance the number of detected targets. Then, wavelet transform is used to perform Style Transfer on the enhanced images to achieve image restoration. The clarity of the images and detection targets is further increased and the generalization of the model is enhanced. Second, a combination of BIFPN-S and FPN is proposed to fuse the effective feature layer obtained by the Backbone layer to enhance the detection precision and accelerate model detection. Finally, the localization loss function of the prediction layer in the network is replaced by EIoU_Loss to heighten the localization precision in detection. Experimental results comparing the B-YOLOX-S algorithm model with mainstream algorithms such as FasterRCNN, YOLOV3, YOLOV4, YOLOV5, and YOLOX on the URPC2020 dataset show that the detection precision and detection speed of the algorithm model have obvious advantages over other algorithm networks. The average detection accuracy mAP value is 82.69%, which is 5.05% higher than the benchmark model (YOLOX-s), and the recall rate is 8.03% higher. Thus, the validity of the algorithmic model proposed in this paper is demonstrated.https://www.mdpi.com/2077-1312/10/11/1764object detectionYOLOXdata augmentationURPC |
spellingShingle | Jun Wang Shuman Qi Chao Wang Jin Luo Xin Wen Rui Cao B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion Journal of Marine Science and Engineering object detection YOLOX data augmentation URPC |
title | B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion |
title_full | B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion |
title_fullStr | B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion |
title_full_unstemmed | B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion |
title_short | B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion |
title_sort | b yolox s a lightweight method for underwater object detection based on data augmentation and multiscale feature fusion |
topic | object detection YOLOX data augmentation URPC |
url | https://www.mdpi.com/2077-1312/10/11/1764 |
work_keys_str_mv | AT junwang byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion AT shumanqi byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion AT chaowang byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion AT jinluo byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion AT xinwen byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion AT ruicao byoloxsalightweightmethodforunderwaterobjectdetectionbasedondataaugmentationandmultiscalefeaturefusion |