A noise robust automatic radiolocation animal tracking system

Abstract

Agriculture is becoming increasingly reliant upon accurate data from sensor arrays, with localization an emerging application in the livestock industry. Ground-based time difference of arrival (TDoA) radio location methods have the advantage of being lightweight and exhibit higher energy efficiency than methods reliant upon Global Navigation Satellite Systems (GNSS). Such methods can employ small primary battery cells, rather than rechargeable cells, and still deliver a multi-year deployment. In this paper, we present a novel deep learning algorithm adapted from a one-dimensional implementing a convolutional neural network (CNN) model, originally developed for the task of semantic segmentation. The presented model () both converts TDoA sequences directly to positions and reduces positional errors introduced by sources such as multipathing. We have evaluated the model using simulated animal movements in the form of TDoA position sequences in combination with real-world distributions of TDoA error. These animal tracks were simulated at various step intervals to mimic potential TDoA transmission intervals. We compare to a Kalman filter to evaluate the performance of our algorithm to a more traditional noise reduction approach. On average, for simulated tracks having added noise with a standard deviation of 50 m, the described approach was able to reduce localization error by between 66.3% and 73.6%. The Kalman filter only achieved a reduction of between 8.0% and 22.5%. For a scenario with larger added noise having a standard deviation of 100 m, the described approach was able to reduce average localization error by between 76.2% and 81.9%. The Kalman filter only achieved a reduction of between 31.0% and 39.1%. Results indicate that this novel 1D CNN like encoder/decoder for TDoA location error correction outperforms the Kalman filter. It is able to reduce average localization errors to between 16 and 34 m across all simulated experimental treatments while the uncorrected average TDoA error ranged from 55 to 188 m.

Robust Time-of-Arrival Location Estimation Algorithms for Wildlife Tracking

“…Recently, machine learning and neural networks are beginning to be explored for robust localization [2,26]. In some cases, machine learning is used to classify outliers and in others to also estimate locations from ToA or differences of ToA measurements.…”

“…These approaches require training for a particular geography, which is not necessary in our approach. Some of these approaches (e.g., [2]) also ignore physical and mathematical constraints that our approach exploits, such as the statistical relationship between the signal-to-noise ratios and ToA measurement errors.…”

“…For many species, the only viable high-throughput high-resolution tracking technology is time-of-arrival (ToA) transmitter localization [1]. Similar techniques are now also used to track livestock [2]. In such systems, a network of radio or acoustic sensors (receivers) estimate the times of arrival of a signal emitted by a transmitter attached to an animal to the sensors.…”

“…The system uses these ToA estimates to estimate the location of the transmitter. Radio transmitters are used for ToA tracking of terrestrial species [2][3][4], and ultrasonic audio transmitters are used for ToA tracking of aquatic species [5][6][7][8].…”