基于注意力网络的长时牦牛个体识别研究

doi:10.13733/j.jcam.issn.2095-5553.2024.01.028

摘要/Abstract

摘要： 为推动精准畜牧业的发展及探讨长时间跨度下的动物个体识别，构建间隔6个月和12个月的同一批牦牛个体图像数据集。试验采用引入注意力机制的PCB+SEResNet50识别模型，实现短时和长时牦牛个体识别，从而分析影响长时牦牛个体识别的因素，并在该长时数据集上与ViT和PGCFL模型识别结果进行比较。结果表明:该模型在间隔6个月和12个月的数据集上识别平均精度均值达到60.37%、41.56%。相较于ViT，分别提高1.64%、5.82%；相较于PGCFL，分别提高12.40%、11.22%。该研究可为长时牦牛个体识别、养殖信息化及牲畜精准管理等提供理论依据和方法指导。

关键词: 精准畜牧业, 牦牛, 个体识别, 注意力机制, 动物生物特征

Abstract: In order to promote the development of precision animal husbandry and discuss the longterm span of animal individual recognition, in this paper, the same batch of yak individual image datasets with an interval of 6 months and 12 months are constructed. In the experiment, the PCB+SEResNet50 recognition model with attention mechanism was used to realize shortterm and longterm yak individual recognition, so as to analyze the factors affecting longterm yak individual recognition. The recognition results of this longterm dataset were compared with those of ViT and PGCFL models. The results showed that the mean average precision of the model reached 60.37% and 41.56% on the data set with an interval of 6 months and 12 months. Compared with ViT, it was 1.64% and 5.82% higher, respectively, and compared with PGCFL, it was 12.40% and 11.22% higher, respectively. This study can provide theoretical basis and method guidance for longterm yak individual identification, breeding information and precision management of livestock.

Key words: precision animal husbandry, yak, individual identification, attention mechanism, animal biometrics

中图分类号:

TP391.4

达措, , 赵启军, , , 高定国, , 索南尖措, 尼玛扎西. 基于注意力网络的长时牦牛个体识别研究[J]. 中国农机化学报, 2024, 45(1): 202-208.

Da Cuo, , Zhao Qijun, , , Gao Dingguo, , Suonan Jiancuo, Nima Zhaxi. Research on longterm yak individual recognition based on attention networks[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(1): 202-208.

参考文献

［1］张丽霞, 卫泽珍, 李金邦, 等. 动物个体识别方法种种［J］. 野生动物学报， 2015, 36（4）: 475-478.
Zhang Lixia, Wei Zezhen, Li Jinbang, et al. Differential method for animal individual identification ［J］. Chinese Journal of Wildlife, 2015, 36（4）: 475-478.
［2］ Azmi N, Kamarudin L M, Zakaria A, et al. Radio frequency identification (RFID) range test for animal activity monitoring ［C］. 2019 IEEE International Conference on Sensors and Nanotechnology. IEEE, 2019: 1-4.
［3］ Li W, Ji Z, Wang L, et al. Automatic individual identification of Holstein dairy cows using tailhead images ［J］. Computers and Electronics in Agriculture, 2017, 142: 622-631.
［4］郭依正, 朱伟兴, 马长华, 等. 基于Isomap和支持向量机算法的俯视群养猪个体识别［J］. 农业工程学报, 2016, 32(3): 182-187.
Guo Yizheng, Zhu Weixing, Ma Changhua, et al. Topview recognition of individual grouphoused pig based on Isomap and SVM ［J］. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2016, 32(3): 182-187.
［5］顾佳音, 刘辉, 姜广顺. 东北虎(Panthera tigris altaica)个体识别技术研究进展［J］. 野生动物, 2013, 34(4): 229-237.
Gu Jiayin, Liu Hui, Jiang Guangshun. A review of potential techniques for identifying individual Amur tigers (Panthera tigris altaica) ［J］. Chinese Journal of Wildlife, 2013, 34(4): 229-237.
［6］金耀, 何秀文, 万世主, 等. 基于YOLO v3的生猪个体识别方法［J］. 中国农机化学报, 2021, 42(2): 178-183.
Jin Yao, He Xiuwen, Wan Shizhu, et al. Individual pig identification method based on YOLO v3 ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(2): 178-183.
［7］温长吉, 张笑然, 吴建双, 等. 基于多注意力机制级联LSTM模型的猪脸表情识别［J］. 农业工程学报, 2021, 37(12): 181-190.
Wen Changji, Zhang Xiaoran, Wu Jianshuang, et al. Pig facial expression recognition using multiattention cascaded LSTM model ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(12): 181-190.
［8］谢秋菊, 吴梦茹, 包军, 等. 融合注意力机制的个体猪脸识别［J］. 农业工程学报, 2022, 38(7): 180-188.
Xie Qiuju, Wu Mengru, Bao Jun, et al. Individual pig face recognition combined with attention mechanism ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(7): 180-188.
［9］董力中, 孟祥宝, 潘明, 等. 基于姿态与时序特征的猪只行为识别方法［J］. 农业工程学报, 2022, 38(5): 148-157.
Dong Lizhong, Meng Xiangbao, Pan Ming, et al. Recognizing pig behavior on posture and temporal features using computer vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(5): 148-157.
［10］ Kumar S, Singh S K. Monitoring of pet animal in smart cities using animal biometrics ［J］. Future Generation Computer Systems, 2018, 83: 553-563.
［11］ Li Z, Ge C, Shen S, et al. Cow individual identification based on convolutional neural network ［C］. Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence, 2018: 1-5.
［12］ Bruslund Haurum J, Karpova A, Pedersen M, et al. Reidentification of zebrafish using metric learning ［C］. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2020: 1-11.
［13］ Cheng X, Zhu J, Zhang N, et al. Detection features as attention (defat): A keypointfree approach to Amur tiger reidentification ［C］. 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 2020: 2231-2235.
［14］ Wang L, Ding R, Zhai Y, et al. Giant panda identification ［J］. IEEE Transactions on Image Processing, 2021, 30: 2837-2849.
［15］于雪莹, 高继勇, 王首程, 等. 基于生成对抗网络和混合注意力机制残差网络的苹果病害识别［J］. 中国农机化学报, 2022, 43(6): 166-174.
Yu Xueying, Gao Jiyong, Wang Shoucheng, et al. Apple disease recognition based on Wasserstein generative adversarial networks and hybrid attention mechanism residual network ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(6): 166-174.
［16］张继成, 李德顺. 基于深度残差学习的成熟草莓识别方法［J］. 中国农机化学报, 2022, 43(2): 136-142.
Zhang Jicheng, Li Deshun. Ripe strawberry recognition method based on deep residual learning ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(2): 136-142.
［17］ Zhang T, Zhao Q, Da C, et al. Yak ReID-103: A benchmark for yak reidentification ［C］. 2021 IEEE International Joint Conference on Biometrics (IJCB). IEEE, 2021: 1-8.
［18］ Sun Y, Zheng L, Yang Y, et al. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline) ［C］. Proceedings of the European Conference on Computer Vision (ECCV), 2018: 480-496.
［19］ He K, Zhang X, Ren S, et al. Deep residual learning for image recognition ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
［20］ Li L, Zhang T, Cuo D, et al. Automatic identification of individual yaks in inthewild images using partbased convolutional networks with selfsupervised learning ［J］. Expert Systems with Applications, 2023, 216: 119431.

[1]	黎远江, 李云伍, , 赵颖, , 台少瑜, 王克超. 基于改进Deeplabv3+模型的果树语义分割研究[J]. 中国农机化学报, 2024, 45(1): 209-216.
[2]	叶荣, 马自飞, 高泉, 李彤, 邵郭奇, 王白娟. 基于改进YOLOv5sECAASFF算法的茶叶病害目标检测[J]. 中国农机化学报, 2024, 45(1): 244-251.
[3]	王瑞彬, 杨世忠, 高升. 融合残差网络与注意力机制的草莓检测[J]. 中国农机化学报, 2024, 45(1): 266-273.
[4]	吴潇, 杨颖, 刘刚, 张倩, 宁远霖. 基于迁移学习和改进ResNet34的猪个体识别方法[J]. 中国农机化学报, 2023, 44(9): 214-221.
[5]	余胜, 谢莉. 基于迁移学习和卷积视觉转换器的农作物病害识别研究[J]. 中国农机化学报, 2023, 44(8): 191-197.
[6]	段宇飞, 董庚, 孙记委, 王焱清, . 基于SE-ResNet网络的油茶果果壳与茶籽分选模型[J]. 中国农机化学报, 2023, 44(4): 89-95.
[7]	李宇航, 庄继晖, 陈振斌. 数据驱动下农用车辆柴油机NOX排放预测模型[J]. 中国农机化学报, 2023, 44(4): 128-136.
[8]	王宇博, 马廷淮, 陈光明. 基于改进YOLOv5算法的农田杂草检测[J]. 中国农机化学报, 2023, 44(4): 167-173.
[9]	惠巧娟, 马伟, 边超. 融合强化注意力机制的农田杂草识别方法[J]. 中国农机化学报, 2023, 44(4): 195-201.
[10]	陈欢欢, 姜戌雅, 刘建彪, 蔡红珍, , 高锋. 牦牛粪生物质燃烧特性及动力学研究[J]. 中国农机化学报, 2023, 44(12): 162-167.
[11]	钟丹, 李宗南, 王思, 黄平, 邱霞, 蒋怡. 基于深度学习分类模型的4种果树物候期识别[J]. 中国农机化学报, 2023, 44(11): 148-154.
[12]	肖克辉, , 杨宏, , 苏章顺, , 杨小丹, . 基于改进YOLOv5的蝴蝶兰花朵识别与计数[J]. 中国农机化学报, 2023, 44(11): 155-161.
[13]	项新建, 周焜, 费正顺, 郑永平, 姚佳娜. 基于改进YOLOX算法的杨梅成熟度检测方法[J]. 中国农机化学报, 2023, 44(10): 201-208.
[14]	胡奕帆, 赵贤林, 李佩娟, 赵辰雨, 陈光明. 基于改进YOLOv5的自然环境下番茄果实检测[J]. 中国农机化学报, 2023, 44(10): 231-237.
[15]	汪颖, 王峰, 李玮, 王艳艳, 王应彪, 罗鑫. 用于复杂环境下果蔬检测的改进YOLOv5算法研究[J]. 中国农机化学报, 2023, 44(1): 185-191.