基于深度学习的水面漂浮物智能检测方法  

Intelligent Detection of Floating Objects on Water Surface Based on Deep Learning

作　　者：陈任飞 彭勇[1,2] 吴剑 欧阳文宇[1] 李昱 岳廷秀[2] CHEN Renfei;PENG Yong;WU Jian;OUYANG Wenyu;LI Yu;YUE Tingxiu(Faculty of Infrastructure Eng.,Dalian Univ.of Technol.,Dalian 116024,China;Aartificial Intelligence Inst.,Dalian Univ.of Technol.,Dalian 116000,China)

机构地区：[1]大连理工大学水利工程学院,辽宁大连116024 [2]大连理工大学人工智能大连研究院,辽宁大连116000

出　　处：《工程科学与技术》2023年第3期165-174,共10页Advanced Engineering Sciences

基　　金：大连理工大学人工智能研究院项目(05090001)。

摘　　要：漂浮物作为河道表观污染的重要源头,加强漂浮物检测是改善水环境生态质量的重要途径,也是积极落实“河长制”政策的技术手段。由于水面漂浮物具有场景复杂度高、形状不规则及多尺度形态变化等特点,采用传统的图像识别方法快速有效地检测目标具有较大的挑战性。因此,本文提出了一种基于深度学习的实时且稳健的水面漂浮物智能检测方法。首先,基于稀疏分解思想对低质量漂浮物图像进行降噪和增强处理,初步降低复杂水面环境对漂浮物图像质量的影响。其次,以轻量化MobileNetV2网络取代(single shot multibox detector,SSD)算法中的VGG16网络作为骨干网络,在预测层中将深度可分离卷积取代标准卷积,并采用动态特征金字塔网络提高多尺度漂浮物的检测精度,弥补SSD网络中强制不同层学习相同特征的不足。然后,将统一量化卷积神经网络(Quantized-CNN)框架应用于量化SSD检测器的检测误差,进一步加速卷积层计算和压缩全连接层的参数,降低SSD算法的计算复杂度和内存成本。本文在构建的水面漂浮物数据集上进行的实验结果表明:与现有的图像识别算法相比,改进后的SSD检测算法的平均精度(AP)和综合评价指数(F_(1))分别达到95.86%和94.74%,在硬件GPU下的检测速度达到64.23 FPS,检测算法的参数计算量减少到0.75×10^(9),模型内存成本压缩到6.27 MB。改进SSD算法实现了水面漂浮物检测的高精度和高效率。Floating objects are important sources of apparent pollution in a river.Strengthening the detection of floating objects is an important step to improve the ecological quality of the water environment,and it is also a technical means to actively implement the“river chief system”policy.Because floating objects on the water have the characteristics of high scene complexity,irregular shapes,and multi-scale morphological changes,it is challenging to use traditional image recognition methods to detect targets quickly and effectively.In this paper we propose a realtime and robust intelligent detection method for floating objects on the water surface based on deep learning.First,the low-quality floating objects image is denoised and enhanced based on the sparse decomposition idea,which reduces the impact of the complex water surface environment on the image quality of the floating objects.Secondly,lightweight MobileNetV2 is selected as the backbone of a single shot multi-box detector(SSD),and standard convolution is replaced by depthwise separable convolution in the prediction layers.A dynamic feature pyramid network(DyFPN)is adopted at extra low cost to improve the detection precision of multi-scale objects and to make up for the deficiency of SSD to force different network layers to learn the same features.More significantly,the unified quantized convolutional neural network(Quantized-CNN)framework is applied to quantifying the error correction of the improved detector for further accelerating the computation of convolutional layers and compressing the parameters of fully connected layers to reduce the computational complexity and memory cost of the SSD algorithm.The experimental results conducted in this paper on the constructed water surface floating objects data set show that:Compared with the existing image recognition algorithm,the improved SSD detection algorithm has an average accuracy(AP)and comprehensive evaluation index(F_(1))score of 95.86%and 94.74%.The detection speed under the hardware GPU reaches 64.

关 键 词：漂浮物智能检测 深度学习 SSD算法 动态特征金字塔 模型量化 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]