Précédent|Prochain

Remote sensing monitoring method of livestock in grassland based on multi-scale features and multi-models fusion

  • role： First author第一作者
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

  • Email：AlexanderShaw_84@163.com
  • Introduction：肖如林，研究方向为生态遥感监测评估、信息化等的研究与应用。E-mail： AlexanderShaw_84@163.com
XIAO Rulin1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

  • Email：gjx@nies.org
  • Introduction：高吉喜，研究方向为区域生态保护、生态资产评估、区域生态学等。E-mail： gjx@nies.org
GAO Jixi1*,  
  • Affiliation：

    Inner Mongolia Autonomous Region Grassland Remote Sensing and Emergency Technical Reserve Key Laboratory, Hohhot 010020, China

LIU Aijun2,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

HOU Peng1,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

ZHANG Wenguo1,  
  • Affiliation：

    Inner Mongolia Autonomous Region Grassland Remote Sensing and Emergency Technical Reserve Key Laboratory, Hohhot 010020, China

YANG Yong2,  
  • Affiliation：

    Information Center of Ecology and Environment of Mianyang, Mianyang 621050, China

LI Yunbao3,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

FU Zhuo1,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

JIN Chuanping1,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

YANG Xu1,  
  • Affiliation：

    Inner Mongolia Autonomous Region Grassland Remote Sensing and Emergency Technical Reserve Key Laboratory, Hohhot 010020, China

ZHENG Shuhua2,  
  • Affiliation：

    Satellite Application Center for Ecology and Environment of MEE, Beijing 100094, China

YIN Shoujing1

résumé

China is a large country of grassland and animal husbandry. Overloading and overgrazing is one of the main causes of grassland degradation in China. To protect the grassland, it is necessary to precisely monitoring livestock carrying capacity, which is the key to evaluation and control grass-livestock balance. However, traditional method of livestock carrying capacity such as hierarchical statistics, sampling field survey and online camera monitoring is whether time-consuming, labor-intensive, costly or poor quality. So it is very urgent to find a kind of efficient and precise monitoring method of livestock carrying capacity in grassland.To achieve this goal, this research proposes an efficient and precise monitoring method of the livestock in grassland by using of sub-meter resolution satellite image. The method not only fuses multi-scale features of livestock in sub-meter resolution satellite image such as “blob feature”、“flock feature”、“moving feature” , but also integrates deep learning technology and object oriented recognition technology. Firstly, considering that the livestock in satellite image is a kind of small (tiny) target, it uses kinds of image enhancement method such as bi-lateral filtering and Laplace of Gaussian (LoG) operator to enhance the weak livestock signal successfully. Secondly, in consideration of “flock feature” of livestock flock, it use a kind of “livestock flock detection model” based on deep learning technology to get the rough distribution area of livestock flocks. Thirdly, in consideration of “blob feature” and “moving feature” of livestock, it use a kind of “livestock blob detection method” based on LoG Gradient Difference and object oriented recognition technology to get the possible livestock blobs. Finally, by integrating the detecting result of both livestock flocks and livestock blobs, it uses the livestock blobs result to enhance and verify the livestock flocks result, and the enhanced and verified livestock flocks and the livestock blobs within them is finally get by using some simple manually revising work.Through an experiment in Xilingol grassland, it is found that the approach has good effect on livestock flock detection: with positive detection rate about 0.802 and false detection rate about 0.244, especially as to big livestock flock, the positive detection rate is up to 0.937, the false detection rate is low to 0.072.It is very helpful for the monitoring and supervision of livestock flock in grassland, and can also provide reference for remote sensing monitoring of other “small (tiny) targets”. It is of great significance both in terms of technological innovation and business application. It makes a litter effort in promoting the livestock satellite remote sensing monitoring into an intuitive and fine monitoring era-“Number-Counting Era”.

mots-clés

livestock;remote sensing;livestock carrying;grassland;small (tiny) target

References

  1. 1.
    Fu G C, Yang W and Song Z H. 2009. Preliminary discussion on current situation of meadows and main reasons of degradation of China. Inner Mongolia Environmental Sciences, 21(4): 32-35
  2. 2.
    Guo X J, Shao Q Q, Yang F, Li Y Z, Wang Y C and Wang D L. 2019. Using UAV remote sensing for a population census of blue sheep (Pseudois nayaur) in Maduo county, source region of the Yellow River. Journal of Natural Resources, 34(5): 1054-1065
  3. 3.
    Institute of Botany, The Chinese Academy of Sciences. 2020. Method and system for recognizing cattle and sheep based on remote sensing image. China, 202010111366.1
  4. 4.
    Li G, Sun W L, Zhang H and Gao C Y. 2014. Balance between actual number of livestock and livestock carrying capacity of grassland after added forage of straw based on remote sensing in Tibetan Plateau. Transactions of the Chinese Society of Agricultural Engineering, 30(17): 200-211
  5. 5.
    Liang H, Wang Q W, Zhang Q and Li C X. 2021. Small object detection technology: a review. Computer Engineering and Applications, 57(1): 17-28
  6. 6.
    Liang T G, Cui X, Feng Q S, Wang Y and Xia W T. 2019. Remotely sensed dynamics monitoring of grassland aboveground biomass and carrying capacity during 2001-2008 in Gannan pastoral area. Acta Prataculturae Sinica, 18(6): 12-22
  7. 7.
    Liu A J and Han J G. 2007. The study of method about monitoring grazing intensity in Xilingol rangeland using RS data. Chinese Journal of Grassland, 29(2): 70-74
  8. 8.
    Liu A J, Xing Q, Gao W, Yang G Q, Su R N, Ha S and An M Z. 2003. Productivity monitoring and livestock capacity calculation of natural grassland in Inner Mongolia in 2003. Inner Mongolia Prataculture, 15(4): 1-3
  9. 9.
    Liu X N, Wang Z P, He Y T and Liu Q. 2019. Research on small target detection based on deep learning. Tactical Missile Technology, (1): 100-107
  10. 10.
    Ma Z L and Ni J Z. 2022. A vehicle detection method for remote sensing image. Beijing Surveying and Mapping, 36(5): 547-551
  11. 11.
    Pearson C, Filippi P and González L A. 2021. The relationship between satellite-derived vegetation indices and live weight changes of beef cattle in extensive grazing conditions. Remote Sensing, 13(20): 4132
  12. 12.
    Peng J B, Wang D L, Liao X H, Shao Q Q, Sun Z G, Yue H Y and Ye H P. 2020. Wild animal survey using UAS Imagery and deep learning: modified faster R-CNN for kiang detection in Tibetan Plateau. ISPRS Journal of Photogrammetry and Remote Sensing, 169: 364-376
  13. 13.
    Sha M M, Li Y and Li A. 2022. Multiscale aircraft detection in optical remote sensing imagery based on advanced Faster R-CNN. National Remote Sensing Bulletin, 26(8): 1624-1635
  14. 14.
    Shao Q Q, Guo X J, Li Y Z, Wang Y C, Wang D L, Liu J Y, Fan J W and Yang F. 2018. Using UAV remote sensing to analyze the population and distribution of large wild herbivores. Journal of Remote Sensing, 22(3): 497-507
  15. 15.
    Tong K, Wu Y Q and Zhou F. 2020. Recent advances in small object detection based on deep learning: a review. Image and Vision Computing, 97: 103910
  16. 16.
    Tong K and Wu Y Q. 2022. Deep learning-based detection from the perspective of small or tiny objects: a survey. Image and Vision Computing, 123: 104471
  17. 17.
    Wang K, Wu P, Xuan C Z, Yu W B and Su H. 2020. Progress in monitoring the grazing information of livestock. Journal of Nanjing Agricultural University, 43(3): 403-413
  18. 18.
    Wang M T and Li D Q. 2017. Analysis of animal husbandry economy development in Northern Tibet Plateau based on the statistical data and investigation of 111 shepherds. Journal of Shanxi Agricultural University (Social Science Edition), 16(12): 18-24
  19. 19.
    Wang Q, Ma L L, Wang N, Wang Y H, Li J M, Teng G E, Ouyang G Z, Zhang Y P, Ao L, Niu Y F, Zheng Q C and Li Z Y. 2021. Automatic grassland livestock quantity accounting method for optical images acquired by tethered balloon. Radio Engineering, 51(12): 1485-1492
  20. 20.
    Wang Q, Sun B P and Zhao T N. 2007. Investigation and research of forage yield and livestock capacity in Yanchi county. Research of Soil and Water Conservation, 14(4): 109-112
  21. 21.
    Yao H G, Wang C, Yu J, Bai X J and Li W. 2020. Recognition of small-target ships in complex satellite images. Journal of Remote Sensing, 24(2): 116-125
  22. 22.
    Zhang X S, Zhang M J, Wang L, Luo H L and Li J. 2019. Research status and development analysis of wearable information monitoring technology in animal husbandry. Transactions of the Chinese Society for Agricultural Machinery, 50(11): 1-14
  23. 23.
    Zhao J B and Du B S. 2023. Development of small target detection technology based on deep learning. Electronics Optics and Control, 30(2): 63-70, 74

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website