A Non-Invasive Millimetre-Wave Radar Sensor for Automated Behavioural Tracking in Precision Farming—Application to Sheep Husbandry

Abstract

The automated quantification of the behaviour of freely moving animals is increasingly needed in applied ethology. State-of-the-art approaches often require tags to identify animals, high computational power for data collection and processing, and are sensitive to environmental conditions, which limits their large-scale utilization, for instance in genetic selection programs of animal breeding. Here we introduce a new automated tracking system based on millimetre-wave radars for real time robust and high precision monitoring of untagged animals. In contrast to conventional video tracking systems, radar tracking requires low processing power, is independent on light variations and has more accurate estimations of animal positions due to a lower misdetection rate. To validate our approach, we monitored the movements of 58 sheep in a standard indoor behavioural test used for assessing social motivation. We derived new estimators from the radar data that can be used to improve the behavioural phenotyping of the sheep. We then showed how radars can be used for movement tracking at larger spatial scales, in the field, by adjusting operating frequency and radiated electromagnetic power. Millimetre-wave radars thus hold considerable promises precision farming through high-throughput recording of the behaviour of untagged animals in different types of environments.

Automated detection of sow posture changes with millimeter-wave radars and deep learning

“…All these improvements are easily reachable, which strongly suggests that automated fine recording with radars will help to analyse the relationship between sow postural changes and risk of piglet crushing. Importantly, radar tracking has limited constraints on the size and shape of animals (Henry et al 2018;Dore et al 2020;Dore et al 2021), thus offering ample possibilities for tracking a wide range of animals in various environments in applied and fundamental ethology research. 7 -Graphs of the probability of posture transitions, i.e., the probability of switching between the 5 postures for the 10 sows (A-J) over a 5 hours period.…”

“…bees: Dore et al 2020) and mammals (e.g. sheep: Henry et al 2019; Dore et al 2021). The main advantage of radars is that data collection and processing is fast and requires less memory than computer vision (the memory used for each measure is 1Mb and 5Gb for one image without compression).…”

How do bees move across the landscapes?

“…In Bee-Move, we will develop a new type of tracking system based on millimetre wave radars to automatically monitor the 3D movements of hundreds of bees simultaneously in areas of several square kilometres. Our recent utilisation of such radars to monitor the movements of humans and farm animals such as sheep and pigs (Henry et al, 2019;Dore et al, 2021) gives us good reasons to think we will succeed.…”

Monitoring of sow postural activity from 3D millimeter-wave radar imaging

“…In the livestock welfare context (as described in, e.g., Ahmadi et al (2011)) radar technology may be advantageously applied inside crates or pens or outside. As a proof of concept, a 24GHz Frequency-Modulated Continuous-Wave (FM-CW) radar was recently used for the first time by some of us to record the radar-to-sheep separation distance in a corridor Henry et al (2018), while the displacement of sheep during behavioral tests were derived from the image processing obtained from a 77GHz Multiple-Input Multiple Output (MIMO) radar Dore et al (2021). Doppler frequencies delivered by a 24GHz FM-CW radar were also measured to detect parturition of sows inside farrowing crates Manteuffel (2019) and a remote sensing solution using 122GHz FM-CW radars was investigated to detect the sow postural activity Dore et al (2022).…”