Underwater Target Detection Based on Improved YOLOv7 Algorithm With BiFusion Neck Structure and MPDIoU Loss Function
Open Access
- 31 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 105165-105177
Abstract
Underwater target detection has developed greatly in recent years. However, the accuracy of underwater target detection is limited by the complex underwater environment. Based on YOLOv7, we propose an underwater object detection algorithm model to improve precision and confidence (BiFusion Neck module and a MPDIoU loss function). Compared to traditional networks module, the Bifusion Neck module preserves more features from the lower layers by utilizing the output of the P2 feature layer. Moreover, the loss function was improved on the basis of IoU introducing Minimum Point Distance. Finally, the LSKA attention mechanism is introduced to enhance the feature extraction of targets at different scales. The experimental results demonstrate that the BFD-YOLO model proposed in this study achieves an average detection accuracy of 84.8% on a customized dataset, surpassing the performance of the YOLOv7 algorithm by 11.5% and outperforming other tested algorithms. Furthermore, the BFD-YOLO algorithm exhibits strong performance on various datasets and demonstrates superior generalization capabilities.Keywords
This publication has 28 references indexed in Scilit:
- PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditionsInformation Fusion, 2024
- YWnet: A convolutional block attention-based fusion deep learning method for complex underwater small target detectionEcological Informatics, 2023
- MOD-YOLO: Rethinking the YOLO architecture at the level of feature information and applying it to crack detectionExpert Systems with Applications, 2023
- YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors2023
- A systematic review and analysis of deep learning-based underwater object detectionNeurocomputing, 2023
- YOLO-Fish: A robust fish detection model to detect fish in realistic underwater environmentEcological Informatics, 2022
- A recursive attention-enhanced bidirectional feature pyramid network for small object detectionMultimedia Tools and Applications, 2022
- Underwater Optical Imaging: Key Technologies and Applications ReviewIEEE Access, 2021
- Underwater scene prior inspired deep underwater image and video enhancementPattern Recognition, 2020
- SSD: Single Shot MultiBox Detector2016