Sheep delivery scene detection based on faster-RCNN

Shiwen Sun; Junping Qin; Hongcheng Xue

doi:10.1117/12.2538904

27 November 2019 Sheep delivery scene detection based on faster-RCNN

Shiwen Sun, Junping Qin, Hongcheng Xue

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113211C (2019) https://doi.org/10.1117/12.2538904
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

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.

Citation Download Citation

Shiwen Sun, Junping Qin, and Hongcheng Xue "Sheep delivery scene detection based on faster-RCNN", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211C (27 November 2019); https://doi.org/10.1117/12.2538904

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available