Share Email Print
cover

Proceedings Paper • new

Sheep delivery scene detection based on faster-RCNN
Author(s): Shiwen Sun; Junping Qin; Hongcheng Xue
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Sheep delivery scene detection is one of the important applications of object detection technology in the field of animal delivery detection. At present, there are reports on the detection of delivery scenarios of pigs and dairy cows at home and abroad, but the research on the behavior of sheep delivery is still in its infancy. This paper aims to apply the Faster- RCNN model for the detection of ewes and newborn lambs in a sheep delivery scenario; Training the Faster-RCNN model based on the ZF, VGG16 feature extraction networks and the Soft-NMS algorithm respectively by using the selfmade sheep delivery scene data set, and the experimental results were compared; The comparison of experimental results show that the Faster-RCNN model based on Soft-NMS algorithm and VGG16 feature extraction network has better effect in sheep delivery scene detection. The method can effectively complete the detection of the ewes and the newborn lambs in the sheep delivery scene, expand the application range of artificial intelligence in the animal husbandry, and has certain popularization and application value for promoting the development of the wisdom animal husbandry.

Paper Details

Date Published: 27 November 2019
PDF: 7 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211C (27 November 2019); doi: 10.1117/12.2538904
Show Author Affiliations
Shiwen Sun, Inner Mongolia Univ. of Technology (China)
Junping Qin, Inner Mongolia Univ. of Technology (China)
Hongcheng Xue, Inner Mongolia Univ. of Technology (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top