Research on Contactless Detection of Sow Backfat Thickness Based on Segmented Images with Feature Visualization

被引:1
|
作者
Cao, Tingjin [1 ,2 ]
Li, Xuan [1 ,2 ,3 ,4 ]
Liu, Xiaolei [5 ]
Liang, Hao [1 ,2 ]
Wang, Haiyan [2 ,6 ]
Xu, Dihong [1 ,2 ]
机构
[1] Huazhong Agr Univ, Coll Engn & Technol, Wuhan 430070, Peoples R China
[2] Huazhong Agr Univ, Shenzhen Inst Nutr & Hlth, Shenzhen 518000, Peoples R China
[3] Chinese Acad Agr Sci, Agr Genom Inst Shenzhen, Shenzhen 518000, Peoples R China
[4] Guangdong Lab Lingnan Modern Agr, Shenzhen Branch, Shenzhen 518000, Peoples R China
[5] Hubei Hongshan Lab, Wuhan 430070, Peoples R China
[6] Minist Agr & Rural Affairs, Key Lab Smart Farming Agr Anim, Wuhan 430070, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 02期
关键词
backfat thickness; non-contact detection; feature visualization; residual network; TRACKING; PIGS;
D O I
10.3390/app14020752
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Aiming to address the problem that the existing methods for detecting sow backfat thickness are stressful, costly, and cannot detect in real time, this paper proposes a non-contact detection method for sow backfat with a residual network based on image segmentation using the feature visualization of neural networks. In this paper, removing the irrelevant information of the image to improve the accuracy of the sow backfat thickness detection model is proposed. The irrelevant features in the corresponding image of the feature map are found to have the same high brightness as the relevant feature regions using feature visualization. An image segmentation algorithm is then used to separate the relevant feature image regions, and the model performance before and after image segmentation is compared to verify the feasibility of this method. In order to verify the generalization ability of the model, five datasets were randomly divided, and the test results show that the coefficients of determination (R2) of the five groups were above 0.89, with a mean value of 0.91, and the mean absolute error (MAE) values were below 0.66 mm, with a mean value of 0.54 mm, indicating that the model has high detection accuracy and strong robustness. In order to explain the high accuracy of the backfat thickness detection model and to increase the credibility of the application of the detection model, using feature visualization, the irrelevant features and related features of the sow back images extracted by the residual network were statistically analyzed, which were the characteristics of the hip edge, the area near the body height point, the area near the backfat thickness measurement point (P2), and the lateral contour edge. The first three points align with the previous research on sow backfat, thus explaining the phenomenon of the high accuracy of the detection model. At the same time, the side contour edge features were found to be effective for predicting the thickness of the back. In order to explore the influence of irrelevant features on the accuracy of the model, UNet was used to segment the image area corresponding to the irrelevant features and obtain the sow contour image, which was used to construct a dorsal fat thickness detection model. The R2 results of the model were above 0.91, with a mean value of 0.94, and the MAE was below 0.65 mm, with a mean value of 0.44 mm. Compared to the test results of the model before segmentation, the average R2 of the model after segmentation increased by 3.3%, and the average MAE decreased by 18.5%, indicating that irrelevant features will reduce the detection accuracy of the model, which can provide a reference for farmers to dynamically monitor the backfat of sows and accurately manage their farms.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Harbor Detection in Remote Sensing Images Based on Feature Fusion
    Zhao, Huibin
    Li, Weihai
    Yu, Nenghai
    Ao, Huanhuan
    2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), 2012, : 1053 - 1057
  • [32] Feature point detection in HDR images based on coefficient of variation
    Artur Santos Nascimento
    Welerson Augusto Lino de Jesus Melo
    Daniel Oliveira Dantas
    Beatriz Trinchão Andrade
    Multimedia Tools and Applications, 2024, 83 : 19981 - 20002
  • [33] Linear sparse feature based face detection in gray images
    Lu, XF
    Zheng, NN
    Zheng, SF
    2003 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL 3, PROCEEDINGS, 2003, : 889 - 892
  • [34] Feature extraction for oil spill detection based on SAR images
    Brekke, C
    Solberg, AHS
    IMAGE ANALYSIS, PROCEEDINGS, 2005, 3540 : 75 - 84
  • [35] Character Detection and String Identification on a Signboard in Scene Image Based on Criterions of Segmented Images
    Kawano, Hideaki
    Orii, Hideaki
    Maeda, Hiroshi
    ADVANCES IN PRECISION INSTRUMENTATION AND MEASUREMENT, 2012, 103 : 658 - 666
  • [36] Research on vehicle detection based on the regional feature fusion
    Cai, Bixin
    Wang, Qidong
    Chen, Wuwei
    Zhao, Linfeng
    Wang, Huiran
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING, 2022, 236 (08) : 1795 - 1808
  • [37] Motion object detection research based on texture feature
    Peng, Shanshan
    Sensors and Transducers, 2014, 175 (07): : 279 - 283
  • [38] Research and improvement of feature detection algorithm based on FAST
    Li, Yulin
    Zheng, Wenfeng
    Liu, Xiangjun
    Mou, Yuanyuan
    Yin, Lirong
    Yang, Bo
    RENDICONTI LINCEI-SCIENZE FISICHE E NATURALI, 2021, 32 (04) : 775 - 789
  • [39] Research on Face Detection based on fast Haar feature
    Wang, Shuang
    Wen, Guanyu
    Cai, Hua
    2017 10TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI), 2017,
  • [40] Research and improvement of feature detection algorithm based on FAST
    Yulin Li
    Wenfeng Zheng
    Xiangjun Liu
    Yuanyuan Mou
    Lirong Yin
    Bo Yang
    Rendiconti Lincei. Scienze Fisiche e Naturali, 2021, 32 : 775 - 789