| 面向海洋牧场智能化建设的海珍品实时检测方法 |
| |
| 引用本文： | 洪亮,王芳,蔡克卫,陈鹏宇,林远山.面向海洋牧场智能化建设的海珍品实时检测方法[J].农业工程学报,2021,37(9):304-311. |
| |
| 作者姓名： | 洪亮 王芳 蔡克卫 陈鹏宇 林远山 |
| |
| 作者单位： | 大连海洋大学信息工程学院，大连 116023；2. 辽宁省海洋信息技术重点实验室，大连 116023；3. 设施渔业教育部重点实验室，大连海洋大学，大连 116023 |
| |
| 基金项目： | 国家自然科学基金（61603067）；辽宁省自然科学基金项目（20180550674，2020-KF-12-09）；大连市高层次人才创新支持计划（2017RQ053）；辽宁省重点研发计划项目（2020JH2/10100043）；辽宁省教育厅基金项目（QL202016） |
| |
| 摘 要： | 海珍品检测对海洋牧场的智能化建设至关重要,在实时性和准确性方面仍有待提高。该研究提出一种改进的YOLOv3海珍品检测方法。利用深度可分离卷积替代YOLOv3中的标准卷积,得到一个轻量化网络模型DSC-YOLO(Depthwise Separable Convolution-YOLO);在数据预处理方面,采用图像增强方法 UGAN提升海珍品图像清晰度,采用Mosaic数据增广方法丰富数据的多样性。在海珍品数据集上的试验结果显示,相较YOLOv3而言,所提模型大小减少70%,推理时间降低16%,召回率R提高了2.7%,平均准确率提高了2.4%,F1分数提高了0.4%。可见该方法模型小、实时性好,具有部署到移动设备上的潜力。
|
| 关 键 词： | 深度学习 机器视觉 卷积神经网络 YOLOv3网络 深度可分离卷积 海珍品目标检测 |
| 收稿时间： | 2020/12/5 0:00:00 |
| 修稿时间： | 2020/4/10 0:00:00 |
Real-time detection method of seafood for intelligent construction of marine ranch |
| |
| Hong Liang,Wang Fang,Cai Kewei,Chen Pengyu,Lin Yuanshan.Real-time detection method of seafood for intelligent construction of marine ranch[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(9):304-311. |
| |
| Authors: | Hong Liang Wang Fang Cai Kewei Chen Pengyu Lin Yuanshan |
| |
| Institution: | 1. School of Information Engineering, Dalian Ocean University, Dalian 116023, China; 2. Key Laboratory of Marine Information Technology of Liaoning Province, Dalian 116023, China; 3. Key Laboratory of Environment Controlled Aquaculture , Ministry of Education, Dalian Ocean University, Dalian 116023, China |
| |
| Abstract: | Object detection for seafood is a key to intelligence marine ranching, but its real-time and accuracy need to be improved. In this paper we present an YOLOv3-based real-time object detection method for seafood. Firstly, for better real-time performance, we replace the 3×3 standard convolution in YOLOv3 with the depthwise separable convolution technology. This technology resolves standard convolution into depthwise convolution and pointwise convolution. It greatly reduces the amount of parameters and calculations of the model. Thus, we obtain a lightweight network model, named Depthwise Separable Convolution-YOLO (DSC-YOLO); Then, in the data preprocessing stage, we introduce UGAN-based image enhancement methods to relief the color distortion of underwater seafood images. This method uses an unsupervised method to automatically learn the distribution of training data and generate new data. The network consists of generator network and discriminators network. Its main idea is confronting and gaming between networks, on the basis of original data information to generate a new data information. It realizes the mapping process from underwater blurred image to underwater clear image. To be specific, we use CycleGAN to convert images in air to underwater-like images. Thus, lots of image pairs can be obtained and used to train UGAN model. Once UGAN finish training, learned generator of UGAN can transform real underwater images to clear images. Finally, we introduce Mosaic-based data augment methods to enrich image diversity. To be specific, four images are randomly selected from underwater dataset images, and operated with traditional data augmentation (rotation, translation, scaling, roll). Then, the four images are randomly cropped and spliced, obtaining a Mosaic image. The new image has the same dimension as the original images. Combining the three strategies, we obtain a real-time object detection method for seafood. In order to verify the effectiveness of our proposed method, we conduct several experiments. In these experiments, DSC-YOLO, UGAN underwater image enhancement and Mosaic data enhancement were combined to obtain four models: DSC-YOLO, DSC-YOLO+UGAN, DSC-YOLO+Mosaic, DSC-YOLO+UGAN+Mosaic. The four models compare with the YOLOv3 model over the same dataset. The results of experiments show that compared with YOLOv3 model, the model size of the proposed method reduces by 70%, the inference time reduces by 16%, the Recall (R) improves by 2.7%, the mean Average Precision 0.5 (mAP0.5) promotes by 2.4%, and the F1-Score increases by 0.4%. The results indicate that the proposed method has the potential to meet real-time requirements and deploy on mobile devices. |
| |
| Keywords: | deep learning computer vision convolutional neural network YOLOv3 depth separable convolution seafood detection |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
