Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µÅÁö °ø°Ý Çൿ ¸ð´ÏÅ͸µÀ» À§ÇÑ ¿µ»ó ±â¹ÝÀÇ °æ·®È ½Ã½ºÅÛ |
¿µ¹®Á¦¸ñ(English Title) |
Lightweight Video-based Approach for Monitoring Pigs¡¯ Aggressive Behavior |
ÀúÀÚ(Author) |
ÇϽÑ
ÀÌÁ¾¿í
¿À½º¸¸
¹Ú´ëÈñ
Á¤¿ëÈ
Hassan Seif Mluba
Jonguk Lee
Othmane Atif
Daihee Park
Yongwha Chung
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 28 NO. 02 PP. 0704 ~ 0707 (2021. 11) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Pigs¡¯ aggressive behavior represents one of the common issues that occur inside pigpens and which harm pigs¡¯ health and welfare, resulting in a financial burden to farmers. Continuously monitoring several pigs for 24 hours to identify those behaviors manually is a very difficult task for pig caretakers. In this study, we propose a lightweight video-based approach for monitoring pigs¡¯ aggressive behavior that can be implemented even in small-scale farms. The proposed system receives sequences of frames extracted from an RGB video stream containing pigs and uses MnasNet with a DM value of 0.5 to extract image features from pigs¡¯ ROI identified by predefined annotations. These extracted features are then forwarded to a lightweight LSTM to learn temporal features and perform behavior recognition. The experimental results show that our proposed model achieved 0.92 in recall and F1-score with an execution time of 118.16 ms/sequence.
|
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|