基于机器视觉的水下河蟹识别方法  

Detection of Underwater Crabs Based on Machine Vision

作　　者：赵德安[1] 刘晓洋[1] 孙月平[1] 吴任迪 洪剑青[1] 阮承治[1] ZHAO Dean;LIU Xiaoyang;SUN Yueping;WU Rendi;HONG Jianqing;RUAN Chengzhi(School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,China)

机构地区：[1]江苏大学电气信息工程学院,镇江212013

出　　处：《农业机械学报》2019年第3期151-158,共8页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金项目(31571571);2017年省级重点研发专项(BE2017331);江苏省渔业科技类项目(Y2017-36);镇江市2017年度科技创新资金项目(重点研发计划-现代农业)(NY2017013);江苏省高校优势学科建设项目(PAPD);江苏省自然科学基金项目(BK20170536)

摘　　要：为了探测河蟹在池塘中的数量及分布情况,为自动投饵船提供可靠的数据反馈,提出了基于机器视觉的水下河蟹识别方法。该方法通过在投饵船下方安装摄像头进行河蟹图像实时采集,针对水下光线衰减大、视野模糊等特点,采用优化的Retinex算法提高图像对比度,增强图像细节,修改基于深度卷积神经网络YOLO V3的输入输出,并采用自建的数据集对其进行训练,实现了对水下河蟹的高精度识别。实验所训练的YOLO V3模型在测试集上的平均精度均值达86. 42%,对水下河蟹识别的准确率为96. 65%,召回率为91. 30%。实验对比了多种目标检测算法,仅有YOLO V3在识别准确率和识别速率上均达到较高水平。在同一硬件平台上YOLO V3的识别速率为10. 67 f/s,优于其他算法,具有较高的实时性和应用价值。In order to detect underwater crabs,a detection method based on machine vision was proposed,which can produce necessary feedback data on the number and distribution of crabs to automatic bait casting boat in real time so that the boat can cast baits precisely.An underwater camera with LED light installed at the bottom of the boat was used to capture images of crabs.These images taken under water were enhanced by optimized retinex filter firstly,which can make images clearer and enhance the details in images.Then,a dataset included original images captured underwater,captured from a laboratory and downloaded from webs was built.There were totally 3500 labelled original images in the dataset.The dataset was augmented and divided into training and test datasets.Finally,a deep convolution neural network,YOLO V3 was trained to detect the crabs by training dataset.The mean average precision of trained network reached 86.42%on test dataset,the detection precision for underwater crabs was 96.65%and the recall ratio was 91.30%.Compared with crabs with big size,the crabs with small size were more difficult to be detected.Compared with other methods for object detection,YOLO V3 can reach a high level of both recognition precision and speed.The recognition speed of the proposed method was 10.67 f/s,which was higher than that of other methods on the same hardware platform.Therefore,the proposed method was real time and had application values.

关 键 词：河蟹识别 机器视觉 水下图像 图像增强 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]