摘要
受水下强光衰减或散射的影响,水下图像存在颜色失真、模糊和细节丢失等问题,严重影响水下目标识别的精度。针对上述问题,提出一种面向浑浊水域的图像增强方法和YOLOv4算法相结合的方案。首先使用改进的带颜色恢复的多尺度Retinex算法增强水下图像,然后采用全卷积生成式对抗网络实现图像颜色校正和细节恢复,最后通过YOLOv4算法对增强后的图像进行鱼目标识别。结果表明,所提出的图像增强方法与YOLOv4算法相结合方案的平均准确率(mAP)可达到89.59%,与原始图像经训练得到的平均准确率相比提高了7.46%,检测速度达到了90 frame/s。
Affected by strong underwater light attenuation or scattering,underwater images have problems such as color distortion,blur,and loss of detail,which seriously affect the accuracy of underwater target recognition.To address the above problems,this paper proposes a scheme that combines image enhancement for turbid waters and the YOLOv4 algorithm.First,the improved multi-scale Retinex with color restoration is used to enhance the underwater image,and then the fully convolutional generative adversarial network is used to achieve image color correction and detail restoration.Finally,the enhanced image is used for fish target recognition through YOLOv4 algorithm.The results show that the mAP(mean Average Precision)of the proposed method combining the image enhancement method with the YOLOv4 algorithm can reach 89.59%,which is 7.46%higher than that of original image after training,and the detection speed reaches 90 frame·s^(-1).
作者
杨文静
陈明
冯国富
Yang Wenjing;Chen Ming;Feng Guofu(College of Information Technology,Key Laboratory of Fisheries In formation,Ministry of Agriculture and Rural Affairs,Shanghai Ocean University,Shanghai 201306,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第22期286-295,共10页
Laser & Optoelectronics Progress
基金
上海市科技兴农重点攻关项目(2017-02-08-00-03-F00072)
畜禽水产品品质管控与溯源系统开发(2018YFD0701003)。
关键词
成像系统
水下视频
图像增强
全卷积生成式对抗网络
YOLOv4
目标识别
imaging systems
underwater video
image enhancement
full convolution generative adversarial network
YOLOv4
target recognition
