基于改进SSD算法对奶牛的个体识别

doi:10.3778/j.issn.1002-8331.2009-0033

摘要/Abstract

摘要： 为了实现养殖场环境下无接触、高精度的奶牛个体有效识别，针对SSD（single shot multibox detector）算法识别准确率不高的问题，提出一种基于浅层特征模块的改进SSD（shallow feature module SSD，SFM-SSD）算法。将原始SSD算法的主干网络由VGG16替换为MobileNetV2，以降低网络的运算量，改善检测的实时性；针对SSD网络结构的浅层特征图设计浅层特征模块，扩大浅层特征图的感受视野，提高浅层特征图对目标物体的特征提取能力；利用[K]均值聚类算法重构区域候选框，提高算法的检测精度。实验结果表明：在奶牛个体识别任务中，SFM-SSD算法的平均准确率比原始的SSD算法提升3.13个百分点。同时检测的实时性也得到改善。

关键词: 深度学习, 目标检测, 反残差网络, 深度可分离卷积, 特征增强模块

Abstract: To implement the non-contact and high-precision identification of dairy cows in farm environment, an improved SSD（shallow feature module SSD, SFM-SSD） algorithm based on shallow feature module is proposed to solve the problem that SSD（single shot multibox detector） algorithm is not accurate for target recognition. Firstly, the backbone network of the original SSD algorithm is replaced by VGG16 with MobileNetV2. Secondly, the shallow feature module is designed for the shallow feature map of SSD network structure to expand the perception field of shallow feature map and improve the feature extraction ability of shallow feature map for target object. Finally, the [K]-means clustering algorithm is used to reconstruct the region candidate frame to improve the detection accuracy of the algorithm. Experimental results show that the average accuracy of SFM-SSD algorithm is 3.13 percentage points higher than that of traditional SSD algorithm. Meanwhile, the real-time performance of detection is also improved.

Key words: deep learning, target detection, anti residual network, deep separable convolution, feature enhancement module

邢永鑫, 孙游东, 王天一. 基于改进SSD算法对奶牛的个体识别[J]. 计算机工程与应用, 2022, 58(2): 208-214.

XING Yongxin, SUN Youdong, WANG Tianyi. Individual Recognition of Dairy Cow Based on Improved SSD Algorithm[J]. Computer Engineering and Applications, 2022, 58(2): 208-214.

参考文献

[1] SANTONI A M，SENSUSE D I，ARYMUURTHY A M，et al.Cattle race classification using gray level co-occurrence matrix convolutional neural networks[J].Procedia Computer Science，2015，59：493-502.
[2] 何东健，刘冬，赵凯旋.精准畜牧业中动物信息智能感知与行为检测研究进展[J].农业机械学报，2016，47（5）：231-244.
HE Dongjian，LIU Dong，ZHAO Kaixuan.Review of perceiving animal information and behavior in precision livestock farming[J].Transactions of the Chinese Society for Agricultural Machinery，2016，47（5）：231-244.
[3] KUMAR S，PANDEY A，SATWIK K，et al.Deep learning framework for recognition of cattle using muzzle point image pattern[J].Measurement，2018，116：1-17.
[4] 刘忠超，何东健.基于卷积神经网络的奶牛发情行为识别方法[J].农业机械学报，2019，50（7）：186-193.
LIU Zhongchao，HE Dongjian.Recognition method of cow estrus behavior based on convolutional neural network[J].Transactions of the Chinese Society for Agricultural Machinery，2019，50（7）：186-193.
[5] 何东健，刘畅，熊虹婷.奶牛体温植入式传感器与实时监测系统设计与试验[J].农业机械学报，2018，49（12）：195-202.
HE Dongjian，LIU Chang，XIONG Hongting.Design and experiment of implantable sensor and real-time detection system for temperature monitoring of cow[J].Transactions of the Chinese Society for Agricultural Machinery，2018，49（12）：195-202.
[6] XIE S，GIRSHICK R，DOLLAR P，et.al.Aggregated residual transformations for deep neural networks[C]//Conference on Computer Vision and Pattern Recognition.Honolulu：IEEE，2017：1492-1500.
[7] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communication of the ACM，2017，60（6）：84-90.
[8] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Proceedings of Neural Information Processing Systems，Lake Tahoe，2012：1097-1105.
[9] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.
1556，2014.
[10] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago：IEEE，2015：1440-1448.
[11] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[12] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[13] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，2016：21-37.
[14] YU F，KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv：1511.07122，2015.
[15] 董彪，熊风光，韩燮，等.基于改进Yolo v3算法的遥感建筑物检测研究[J].计算机工程与应用，2020，56（18）：209-213.
DONG Biao，XIONG Fengguang，HAN Xie，et al.Research on remote sensing building detection based on improved Yolo v3 algorithm[J].Computer Engineering and Applications，2020，56（18）：209-213.
[16] 王冬丽，廖春江，牟金震，等.基于特征融合的SSD视觉小目标检测[J].计算机工程与应用，2020，56（16）：31-36.
WANG Dongli，LIAO Chunjiang，MOU Jinzhen，et al.SSD visual small target detection based on feature fusion[J].Computer Engineering and Applications，2020，56（16）：31-36.
[17] 李宝奇，贺昱曜，强伟，等.基于并行附加特征提取网络的SSD地面小目标检测模型[J].电子学报，2020，48（1）：84-91.
LI Baoqi，HE Yuyao，QIANG Wei，et al.SSD with parallel additional feature extraction network for ground small target detection[J].Acta Electronica Sinica，2020，48（1）：84-91.
[18] 史文旭，谭代伦，鲍胜利.特征增强SSD算法及其在遥感目标检测中的应用[J].光子学报，2020，49（1）：154-163.
SHI Wenxu，TAN Dailun，BAO Shengli.Feature enhancement SSD algorithm and its application in remote sensing images target detection[J].Acta Photonica Sinica，2020，49（1）：154-163.
[19] 沈新烽，姜平，周根荣.改进SSD算法在零部件检测中的应用研究[J].计算机工程与应用，2021，57（7）：257-262.
SHEN Xinfeng，JIANG Ping，ZHOU Genrong.Application of improved SSD algorithm in parts detection[J].Computer Engineering and Applications，2021，57（7）：257-262.
[20] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，99：2999-3007.