Welcome to Francis Academic Press

Academic Journal of Agriculture & Life Sciences, 2024, 5(1); doi: 10.25236/AJALS.2024.050114.

Target localisation of rotating frame in ear root area of pigs based on improved YOLOv8_OBB

Author(s)

Qi Li, Dong Ren

Corresponding Author:
Dong Ren
Affiliation(s)

School of Electronic Information and Artificial Intelligence, Shaanxi University of Science & Technology, Xi'an, 710021, China

Abstract

In the thermal infrared temperature measurement scenario of pigs, the temperature at the root of the ear is closest to the body temperature. Due to the weak light in the pig house scene, the inconspicuous characteristics of the pig's ear area, and the mutual blockage caused by the pig's posture changing at any time, it is difficult to accurately locate the pig's ear root. Therefore, in order to reduce the impact of low light conditions on the positioning of the pig's ear root, the Retinex algorithm based on bilateral filtering is used to preprocess the input image; an improved rotating target detection method of YOLOv8_OBB is proposed, and the Shuffle Attention mechanism is introduced in the neck, which effectively integrates spatial and channel attention mechanisms to enhance the feature extraction capability of the model; the original feature extraction method is replaced by the Shuffle Attention mechanism, which effectively integrates spatial and channel attention mechanisms to enhance the feature extraction capability of the model. Feature extraction capability; the original backbone network is replaced with MobileNetV3 network structure to reduce the number of parameters and computation of the model. The improved YOLOv8_OBB algorithm improves the accuracy by 7.3%, recall by 7.6%, and average accuracy by 7.1% compared with the baseline algorithm, and is more robust under low light conditions and target occlusion, which provides the basis for intelligent temperature measurement in pigs. Effective positioning out of the ear root is of practical significance for modernised intelligent temperature measurement in pigs.

Keywords

Pig population, YOLOv8_OBB, MobileNetV3, Hybrid attention mechanism

Cite This Paper

Qi Li, Dong Ren. Target localisation of rotating frame in ear root area of pigs based on improved YOLOv8_OBB. Academic Journal of Agriculture & Life Sciences (2024) Vol. 5 Issue 1: 102-112. https://doi.org/10.25236/AJALS.2024.050114.

References

[1] SOERENSEN D D, CLAUSEN S, MERCER J B, et al. Determining the emissivity of pig skin for accurate infrared thermography[J]. Computers and Electronics in Agriculture, 2014, 109: 52-58. 

[2] SYKES D J, COUVILLION J S, CROMIAK A, et al. The use of digital infrared thermal imaging to detect estrus in gilts[J]. Theriogenology, 2012, 78(1):147-152. 

[3] TZANIDAKIS C, SIMITZIS P, ARVANITIS K, et al. An overview of the current trends in precision pig farming technologies[J]. Livestock Science, 2021, 249:104530. 

[4] Jing Huang, Jian Zhang. A study on an individual pig target detection method based on improved SSD network[J]. Software Engineering, 2022, 25(8): 25-29. 

[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. New York:ACM, 2014:580-587. 

[6] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. 

[7] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). December 07-13, 2015, Santiago, Chile. IEEE, 2016: 1440-1448. 

[8] 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.  

[9] YANG S, PEI Z, ZHOU F, et al. Rotated faster R-CNN for oriented object detection in aerial image[C]// ZOU J X, Proceedings of the 2020 3rd International Conference on Robot Systems and Applications. Chengdu:Association for Computing Machinery, 2020:35-39. DOI: 10. 1145/3402597. 3402605. 

[10] XU YC, FUMT, WANG Q M , et al. Gliding vertex on the horizontal bounding box for muli-oriented object detection[J]. IEEE. Transacions on Pattem Analysis andMachine Intelligence, 2021, 43(4): 1452-1459. DOI; 10. 1109/TPAMI. 2020. 2974745

[11] YANG X, YAN JC, FENG Z M, et al. R3Det ; refined single-stage detector with feature refinement for rotating object[J]. Proceedings of the AAAl Conference on Artificial Intelligence, 2021, 35(4); 3163-3171. DOI:10. 1609/aai. v35i4. 16426. 

[12] WANG J, CHEN L Q, HUANG L L, et al. Lane recognition method in weak light condition based on retinex [J]. Computer & Digital Engineering, 2019, 47(2): 451-456. (in Chinese with English abstract) 

[13] Hulin Li, Hanbing Wei, Zheng Liu et al.  Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles [J]. Computer Vision and Pattern Recognition (CVPR), 2022. 

[14] D. Ouyang et al., "Efficient Multi-Scale Attention Module with Cross-Spatial Learning, " ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5. 

[15] Xie Qiuju, Wu Mengru, Bao Jun et al. Individual pig face recognition by fusing attention mechanisms[J]. Journal of Agricultural Engineering, 2022, 38(07):180- 188. 

[16] Dongsheng Ruan, Daiyin Wang, Yuan Zheng, Nenggan Zheng, Min Zheng. Gaussian Context Transformer [J]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. 

[17] Zhao L, Liu S-P. Global and local image feature adaptive fusion of global and local image features [J]. Control and Decision, 2023, 38(04):935-943. 

[18] Lu Jingyu, Zhang Haiyan, Wang Wenxin et al. Global sampling space attention mechanism and its application in image classification and small target detection and recognition[J]. Laser and Optoelectronics Advances in Laser and Optoelectronics, 2023(3):1-23. 

[19] Cheng Changxin, Qiao Qingyuan, Luo Xiaoling et al. Target detection in UAV aerial images based on improved YOLOv8 Target Detection Algorithm for UAV Aerial Images[J]. Radio Engineering, 2024(3): 1-10.  

[20] Ma Zhigang, Nan Xinyuan, Gao Bingpeng, et al. A pedestrian detection algorithm based on Pedestrian Detection Algorithm Based on Mobilenetv3 [J]. Modern Electronic Technology, 2023, 46(16): 149-154.