基于GBPC-ResNeXt50的攻击状态下群养猪身份识别

doi:10.15933/j.cnki.1004-3268.2026.04.015

摘要/Abstract

摘要： 目前猪攻击识别还处于群体级/成对级研究阶段，识别猪个体身份已成为进一步实现个体级攻击识别的必要条件。为解决猪攻击状态下因身体形变、遮挡、重叠等因素引起的身份难以识别的问题，提出一种改进ResNeXt50（Residual networks with next‑50）的深度学习算法以识别攻击状态下猪身份。从标记的600段1 s 攻击视频片段中产生18 000帧作为数据集。首先，在主干网络ResNeXt50中嵌入GECA（Ghost‑based efficient channel‑coordinate attention）模块提升特征判别力。然后，引入双向特征金字塔网络（Bidirectional feature pyramid network，BiFPN）以提高多尺度特征的融合能力。接着，在BiFPN后级联位置注意力机制（Position attention module，PAM）以增强由猪体形变产生的全局空间特征的区分度，采用通道注意力机制（Channel attention mechanism，CAM）通过通道自适应优化特征利用率。最后，采用Fovea Head 识别攻击状态下猪身份。结果表明，提出的GBPC-ResNeXt50（GECA-BiFPN-PAMCAM-ResNeXt50）算法能够以95.6%的平均精度均值（mAP）识别猪身份，较基准网络ResNeXt50提升3.8百分点。表明该方法能够识别攻击状态下个体猪身份，为推动猪攻击识别从群体级/成对级到个体级的转变提供基础，同时也为其他家畜的攻击状态下身份识别提供参考。

关键词: 群养猪, 身份识别, ResNeXt50, 深度学习, 双向特征金字塔网络, 双重注意力机制

Abstract: Presently pig aggression recognition is still in the research stage of group level/pairwise level，and the identification of individual pig has become a necessary condition for further realizing individual level aggression recognition. In order to solve the problem of difficult identification caused by body deformation，occlusion，overlapping and other factors under pig aggression situation，an improved deep learning algorithm based on ResNeXt50（Residual networks with next‑50）was proposed to recognize pig identity in aggression situation. 18 000 frames were generated from the labelled 600 1‑second aggressive video episodes as the dataset.Firstly，the GECA（Ghost‑based efficient channel‑coordinate attention）module was embedded in the backbone network ResNeXt50 to enhance feature discriminative ability.Secondly，bidirectional feature pyramid network（BiFPN）was introduced to enhance the fusion capability of multi‑scale features.Then，position attention mechanism（PAM）was cascaded after BiFPN to improve the discrimination of global spatial features generated by pig body deformation，and channel attention mechanism（CAM） was used to optimize feature utilization through channel adaption.Finally，Fovea Head was used to recognize the identity of pigs under aggression situation.The identity of pigs could be recognized by using the proposed algorithm GBPC‑ResNeXt50（GECA‑BiFPN‑PAM‑CAM‑ResNeXt50）with a mean average precision（mAP）of 95.6%，which was 3.8 percentage points higher than that of the benchmark network ResNeXt50.The result indicates that this method can be used to recognize the identity of individual pig under aggression situation.This provides a foundation for promoting the conversion of pig aggression recognition from group/pairwise level to individual level，and also provides a reference for identification of other livestock under aggression situation.

Key words: Group?housed pigs, Identification, ResNeXt50, Deep learning, Bidirectional feature pyramid network, Double attention mechanisms

中图分类号:

S126

陈晨, 钱锦华, 朱伟兴, 刘睿, 蒋毅. 基于GBPC-ResNeXt50的攻击状态下群养猪身份识别[J]. 河南农业科学, 2026, 55(4): 150-159.

CHEN Chen, QIAN Jinhua, ZHU Weixing, LIU Rui, JIANG Yi. Identification of Group‑Housed Pigs under the Aggression Situation Based on GBPC‑ResNeXt50[J]. Journal of Henan Agricultural Sciences, 2026, 55(4): 150-159.

图/表 12

参考文献

［1］STUKENBORG A，TRAULSEN I，PUPPE B，et al.Agonistic behaviour after mixing in pigs under commercial farm conditions［J］.Applied Animal Behaviour Science，2011，129（1）：28‑35.

［2］BOYLE L A，EDWARDS S A，BOLHUIS J E，et al. The evidence for a causal link between disease and damaging behavior in pigs［J］. Frontiers in Veterinary Science，2022，8：771682.

［3］CHEN C，ZHU W X，STEIBEL J，et al. Recognition of aggressive episodes of pigs based on convolutional neural network and long short‑term memory［J］.Computers and Electronics in Agriculture，2020，169：105166.

［4］GAO Y，YAN K，DAI B S，et al. Recognition of aggressive behavior of group‑housed pigs based on CNN‑GRU hybrid model with spatio‑temporal attention mechanism［J］.Computers and Electronics in Agriculture，2023，205：107606.

［5］ YAN K，DAI B S，LIU H G，et al. Deep neural network with adaptive dual‑modality fusion for temporal aggressive behavior detection of group‑housed pigs［J］.Computers and Electronics in Agriculture，2024，224：109243.

［6］CHEN C，ZHU W X，NORTON T. Behaviour recognition of pigs and cattle：Journey from computer vision to deep learning［J］. Computers and Electronics in Agriculture，2021，187：106255.

［7］刘峰，吴文杰，刘小磊，等. 计算机视觉与深度学习在猪只识别中的研究进展［J］. 华中农业大学学报，2023，42（3）：47‑56.

LIU F，WU W J，LIU X L，et al. Progress of computer vision and deep learning methods for pig’s identity and behavior recognition［J］. Journal of Huazhong Agricultural University，2023，42（3）：47‑56.

［8］MASELYNE J，SAEYS W，DE KETELAERE B，et al.Validation of a High Frequency Radio Frequency Identification（HF RFID）system for registering feeding patterns of growing‑finishing pigs［J］. Computers and Electronics in Agriculture，2014，102：10‑18.

［9］赵伟. 基于Gabor方向直方图和支持向量机的猪个体身份识别［D］. 镇江：江苏大学，2017.

ZHAO W. Recognition of individual pigs based on Gabor directional histogram and support vector machine［D］.Zhenjiang：Jiangsu University，2017.

［10］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 Y Z，ZHU W X，MA C H，et al. Top‑view recognition of individual group‑housed pig based on Isomap and SVM［J］. Transactions of the Chinese Society of Agricultural Engineering，2016，32（3）：182‑187.

［11］秦兴，宋各方. 基于双线性卷积神经网络的猪脸识别算法［J］. 杭州电子科技大学学报，2019，39（2）：12‑17.

QIN X，SONG G F. Pig face recognition algorithm based on bilinear convolution neural network［J］.Journal of Hangzhou Dianzi University，2019，39（2）：12‑17.

［12］HANSEN M F，SMITH M L，SMITH L N，et al.Towards on‑farm pig face recognition using convolutional neural networks［J］. Computers in Industry，2018，98：145‑152.

［13］WADA N，SHINYA M，SHIRAISHI M.［Short paper］pig face recognition using eigenspace method［J］.ITE Transactions on Media Technology and Applications，2013，1（4）：328‑332.

［14］XIE S N，GIRSHICK R，DOLLAR P，et al. Aggregated residual transformations for deep neural networks［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Honolulu，HI：IEEE，2017：5987‑5995.

［15］HOU Q B，ZHOU D Q，FENG J S. Coordinate attention for efficient mobile network design［C］//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. Nashville，TN，USA：IEEE，2021：13708‑13717.

［16］张志刚，余鹏飞，李海燕，等. 基于多尺度特征引导的细粒度野生菌图像识别［J］. 激光与光电子学进展，2022，59（12）：1210016.

ZHANG Z G，YU P F，LI H Y，et al. Fine‑grained image recognition of wild mushroom based on multiscale feature guide［J］.Laser & Optoelectronics Progress，2022，59（12）：1210016.

［17］吴秋兰，陈雪飞，陈超，等. 基于改进YOLOv5s的香菇菌棒污染识别方法［J］. 中国农机化学报，2025，46（2）：217‑223.

WU Q L，CHEN X F，CHEN C，et al. Identification method of Lentinus edodes logs contamination based on improved YOLOv5s ［J］. Journal of Chinese Agricultural Mechanization，2025，46（2）：217‑223.

［18］LIN T Y，DOLLÁR P，GIRSHICK R，et al. Feature pyramid networks for object detection［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. Honolulu，HI，USA：IEEE，2017：936‑944.

［19］张姝瑾，许兴时，邓洪兴，等. 基于YOLO v8n‑seg‑FCABiFPN的奶牛身体分割方法［J］. 农业机械学报，2024，55（3）：282‑289.
ZHANG S J，XU X S，DENG H X，et al. Segmentation model of cow body parts based on YOLO v8n‑seg‑FCABiFPN［J］. Transactions of the Chinese Society for Agricultural Machinery，2024，55（3）：282‑289.

［20］FU J，LIU J，TIAN H J，et al. Dual attention network for scene segmentation［C］//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. Long Beach，CA，USA：IEEE，2019：3141‑3149．
［21］储佳阳. 融合位置注意力与非对称卷积的遥感影像目标检测方法［J］. 测绘与空间地理信息，2025，48（1）：108‑111.

CHU J Y. Object detection method for remote sensing imagery integrating location attention and asymmetric convolution［J］. Geomatics & Spatial Information Technology，2025，48（1）：108‑111.

［22］涂雪滢，张佳鹏，钱程，等. 融合ViT和通道注意力的水稻病害识别技术研究［J］. 农业与技术，2025，45（7）：69‑74.
TU X Y，ZHANG J P，QIAN C，et al. Research on rice disease identification technology combining ViT and channel attention［J］. Agriculture and Technology，2025，45（7）：69‑74.

［23］TAN M X，LE Q V. EfficientNet：Rethinking model scaling for convolutional neural networks［C］//36th International Conference on Machine Learning（ICML）.Long Beach：ICML，2019：6105‑6114.

［24］MEHTA S，RASTEGARI M. Mobilevit：Light‑weight，general‑purpose，and mobile‑friendly vision transformer ［PP/OL］. ArXiv（2021‑10‑05）［2026‑03‑27］. https：//arxiv. org/abs/2110. 02178.

［25］HE K M，ZHANG X Y，REN S Q，et al. Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Las Vegas，NV，USA：IEEE，2016：770‑778. ［26］ALEXEY D，LUCAS B，ALEXANDER K，et al.An image is worth 16x16 words：Transformers for image recognition at scale［C］//International Conference on Learning Representations，2021：1‑21.

［27］LIU Z，LIN Y T，CAO Y，et al. Swin transformer：Hierarchical vision transformer using shifted windows ［C］//2021 IEEE/CVF International Conference on Computer Vision（ICCV）. Montreal，QC，Canada：IEEE，2021：9992‑10002.

［28］HAN K，WANG Y H，TIAN Q，et al.GhostNet：More features from cheap operations［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）.Seattle，WA，USA：IEEE，2020：1577‑1586. ［29］CLEVERT D A，UNTERTHINER T，HOCHREITER S.Fast and accurate deep network learning by exponential linear units（ELUs）［PP/OL］. ArXiv（2016‑02‑22）［2026‑03‑27］. https：//arxiv.org/abs/1511.07289.

［30］KONG T，SUN F C，LIU H P，et al.FoveaBox：Beyound anchor‑based object detection［J］.IEEE Transactions on Image Processing，2020，29：7389‑7398.

［31］LIN T Y，GOYAL P，GIRSHICK R，et al. Focal loss for dense object detection［C］//2017 IEEE International Conference on Computer Vision（ICCV）. Venice，Italy：IEEE，2017：2999‑3007.

［32］TIAN Z，SHEN C H，CHEN H，et al. FCOS：A simple and strong anchor‑free object detector［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，44（4）：1922‑1933.

［33］ZHANG S F，CHI C，YAO Y Q，et al. Bridging the gap between anchor‑based and anchor‑free detection via adaptive training sample selection［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. Seattle，WA，USA：IEEE，2020：9756‑9765.

［34］VARGHESE R，SAMBATH M. YOLOv8：A novel object detection algorithm with enhanced performance and robustness ［C］//2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems（ADICS）. Chennai，India：IEEE，2024：1‑6.

［35］DONG Z W，LI G X，LIAO Y，et al. CentripetalNet：Pursuing high‑quality keypoint pairs for object detection［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）.Seattle，WA，USA：IEEE，2020：10516‑10525.

［36］ZHAO Y A，LV W Y，XU S L，et al. DETRs beat YOLOs on real‑time object detection［C］//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. Seattle，WA，USA：IEEE，2024：16965‑16974. ［37］REN S Q，HE K M，GIRSHICK R，et al. Faster R‑CNN：Towards real‑time object detection with region proposal
networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137‑1149.

［38］FENG C J，ZHONG Y J，GAO Y，et al. TOOD：Task‑aligned one‑stage object detection［C］//2021 IEEE/CVF International Conference on Computer Vision（ICCV）. Montreal，QC，Canada：IEEE，2021：3490‑3499.

［39］ZHU X Z，SU W J，LU L W，et al. Deformable DETR：Deformable transformers for end‑to‑end object detection［PP/OL］. ArXiv（2021‑03‑18）［2026‑03‑27］.https：//arxiv.org/abs/2010.04159.

［40］HOU P R，WANG Z L，CHU Q H，et al. SwinDet：A multi‑level RGB‑D fusion framework for on‑orbit space target detection［C］//2025 IEEE 7th International Conference on Communications，Information System and Computer Engineering（CISCE）. Guangzhou，China：IEEE，2025：374‑378.
［41］WANG A，CHEN H，LIU L H，et al.YOLOv10：Real‑time end‑to‑end object detection［PP/OL］.ArXiv（2024‑10‑30）［2026‑03‑27］. https：//arxiv.org/abs/2405.14458.

[1]	沈川, 李夏. 深度学习在作物病害识别方面的研究进展[J]. 河南农业科学, 2026, 55(3): 19-27.
[2]	江明泽, 闫建伟, 邹传筑. 果蔬成熟度检测关键技术研究进展[J]. 河南农业科学, 2026, 55(1): 1-15.
[3]	盛彬. 基于改进YOLOv5 的黄花成熟度检测方法[J]. 河南农业科学, 2024, 53(8): 145-153.
[4]	冯晓, 张辉, 刘正, 张会芳, 陈海燕, 赵威, 郑国清, 马中杰. 基于深度学习的玉米包衣种子品种识别[J]. 河南农业科学, 2024, 53(7): 160-167.
[5]	戴佳兵, 宋春芳, 凌彩金, 李臻锋, 孙崇高. 基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法研究[J]. 河南农业科学, 2024, 53(5): 157-163.
[6]	钟正扬, 云利军, 杨璇玺, 陈载清. 基于改进YOLOX 的自然环境下核桃识别算法研究[J]. 河南农业科学, 2024, 53(1): 152-161.
[7]	于雁南, 莫泳彬, 严继池, 熊春林, 窦世卿, 杨荣峰. 基于改进ShuffleNet V2 的柑橘病害识别研究[J]. 河南农业科学, 2024, 53(1): 142-151.
[8]	陈聪, 于啸, 宫琪. 基于改进残差网络的苹果叶片病害识别研究[J]. 河南农业科学, 2023, 52(4): 152-161.
[9]	臧贺藏, 王从胜, 赵巧丽, 赵晴, 张杰, 李国强, 郑国清. 基于深度学习的小麦倒伏自动分类方法研究[J]. 河南农业科学, 2023, 52(11): 167-173.
[10]	杨文庆, 刘天霞, 唐兴萍, 徐国富, 马喆, 杨贺凯, 吴文斗. 智慧农业背景下的植物表型组学研究进展[J]. 河南农业科学, 2022, 51(7): 1-12.
[11]	刁智华, 闫娇楠, 赵素娜, 贺振东. 基于图像处理的作物行识别算法研究进展[J]. 河南农业科学, 2022, 51(3): 12-19.
[12]	董燕, 李环宇, 李卫杰, 李春雷, 刘洲峰. 基于联合剪枝深度模型压缩的种子分选方法研究[J]. 河南农业科学, 2022, 51(1): 162-170.
[13]	郑二功，田迎芳，陈涛. 基于深度学习的无人机影像玉米倒伏区域提取[J]. 河南农业科学, 2018, 47(8): 155-160.