ABSTRACT
Due to the complex content and blurry image of the images obtained in the underwater environment, which affect the detection results, resulting in the problems of false detection of objects and difficulty in feature extraction in conventional object detection models, this paper proposes an improved YOLOv7 model to improve the accuracy and real-time performance of underwater object detection models. Based on the YOLOv7 model, this model integrates the CBAM to enhance the weight of the feature information of the detection object in the spatial dimension and channel dimension, so that the feature information of the model object can be captured more easily and the detection accuracy is improved. The SPPFCSPC module is used to reduce the calculation amount of the model and improve the operation speed of the model while maintaining the receptive field. Through comparative ablation experiments, it is proved that the proposed method has higher detection accuracy in object detection in complex underwater environment than several detection models and YOLOv7 models.
- Vinay A, Reddy D N, Sharma A C, G-CNN and F-CNN: Two CNN based architectures for face recognition [C] // Big Data Analytics and Computational Intelligence (ICBDAC). Beijing: IEEE Press, 2017: 23-28.Google Scholar
- C. -H. Yeh , "Lightweight Deep Neural Network for Joint Learning of Underwater Object Detection and Color Conversion," in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 11, pp. 6129-6143, Nov. 2022, doi: 10.1109/TNNLS. 2021. 3072414.Google ScholarCross Ref
- KLAUSNER N H, AZIMI-SADJADI M R. Performance prediction and estimation for underwater object detection using multichannel sonar [J. IEEE Journal of Oceanic Engineering, 2020, 45 (2): 534-546. DOl: 10.1109/JOE. 2018. 2881527.Google ScholarCross Ref
- D. N. Venkatesh Alla, V. Bala Naga Jyothi, H. Venkataraman and G. A. Ramadass, "Vision-based Deep Learning algorithm for Underwater Object Detection and Tracking," OCEANS 2022 - Chennai, 2022, pp. 1-6, doi: 10.1109/OCEANSChennai45887. 2022. 9775438.Google Scholar
- Y. Wang, J. Liu, S. Yu, K. Wang, Z. Han and Y. Tang, "Underwater Object Detection based on YOLO-v3 network," 2021 IEEE International Conference on Unmanned Systems (ICUS), 2021, pp. 571-575, doi: 10.1109/ICUS52573. 2021. 9641489.Google Scholar
- Underwater acoustic source localization via Kernel Extreme Learning Machine [J] Zhengliang, H; Jinxing, H; Pan, X.; Mingxing, N.; Kang, L.; Guangming, L. Frontiers in Physics, 2021.Google Scholar
- Chien-Yao Wang, Alexey Bochkovskiy, & Hong-Yuan Mark Liao 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.Google Scholar
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, & In So Kweon 2018. CBAM: Convolutional Block Attention Module european conference on computer vision.Google Scholar
- SSD: Single shot multibox detector. Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.; Cberg, A. European Conference on Computer Vision, p 21-37, 2016.Google Scholar
- Wen T K, Yin C C. Crack detection in photovoltaic cells by interferometric analysis of electronic speckle patterns [J]. Solar Energy Materials and Solar Cells, 2012, 98: 216-223.Google ScholarCross Ref
- Chollet F 2017 Xception: Deep learning with depth wise sepa-rable convolutions. Computer Vision and Pattern Recognition 2017: 1800–1807, DOI10.1109/CVPR. 2017. 195.Google Scholar
- Research on Smoke Detection Model Based on Improved YOLOv4.5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022, Pages 1-6, 2022.Google Scholar
- Faster R-CNN: Towards real-Time object detection with region proposal networks. Ren, S.; He, K.; Girshick, R.; Sun, J. Advances in Neural Information Processing Systems, p 91-99, 2015.Google Scholar
- Detecting Plant Leaves Based on Vision Transformer Enhanced YOLOv5.2022 3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022, Pages 32-37, 2022.Google Scholar
- H. Wang , "A YOLOv5 Baseline for Underwater Object Detection," OCEANS 2021: San Diego – Porto, 2021, pp. 1-4, doi: 10.23919/OCEANS44145. 2021. 9705896.Google Scholar
Recommendations
Underwater Object Detection Based on Improved Single Shot MultiBox Detector
ACAI '20: Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial IntelligenceUnderwater optical images are scarce, and there are varying degrees of blur and color distortion, which brings great challenges to the detection of underwater objects. In view of the shortcomings of the original Single Shot MultiBox Detector (SSD), in ...
Robust Underwater Object Detection with Autonomous Underwater Vehicle: A Comprehensive Study
ICCA 2020: Proceedings of the International Conference on Computing AdvancementsUnderwater Object Detection had been one of the most challenging research fields of Computer Vision and Image Processing. Before Computer Vision techniques were used for underwater imaging, all the tasks associated with object detection had to be done ...
A systematic review and analysis of deep learning-based underwater object detection
Highlights- Providing an in-depth and comprehensive review related to underwater object detection.
AbstractUnderwater object detection is one of the most challenging research topics in computer vision technology. The complex underwater environment makes underwater images suffer from high noise, low visibility, blurred edges, low contrast ...
Comments