PigNet
| Autor: | Shijia Pan, Yiwen Dong, Jesse R Codling, Orathai Sangpetch, Sripong Ariyadech, Kanittha Naruethep, Amelie Bonde, Akkarit Sangpetch, Pei Zhang, Hae Young Noh, Wachirawich Siripaktanakon |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
010401 analytical chemistry Real-time computing 0402 animal and dairy science Wearable computer Motion detection 04 agricultural and veterinary sciences 040201 dairy & animal science 01 natural sciences 0104 chemical sciences Vibration Activity monitoring Animal welfare Structural vibration Animal behavior Noise (video) |
| Zdroj: | IPSN |
| DOI: | 10.1145/3412382.3458902 |
| Popis: | Automated monitoring of livestock behavior can help farmers economically by detecting changes in animal welfare. Prior approaches use video, which requires light and high storage capability, or motion detection, which has difficulty separating subtle activities. Wearable sensors can address these issues but are vulnerable to destruction by the animals. To the best of our knowledge, we present the first system that uses structural vibration to track animal behavior, and the first system to automatically detect piglet nursing. PigNet uses vibration sensors attached to a pig pen to sense the unique vibration patterns and changes in structural response caused by the animals' movement and position within the pen. Combined with our knowledge of pig behavior, we use this physical knowledge of vibration characteristics to detect pig activities and track piglet growth in a real farm environment. Our system is designed to be robust to the harsh environment, which can create unpredictable noise, as well as physically damage or disconnect sensor nodes. When deployed in a real-world farm environment, our system was able to achieve a daily pen-level status profile of up to 90% accuracy, which tracks nursing activity, sow lying activity, and changes in piglet growth over the weeks-long pre-weaning period. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|