Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce PointSyn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability.1

We describe a multi-modal sensing system for reliable recognition of animal behaviour that can operate in varying environmental conditions. We present the system architecture including the utilised sensors, visualise some intermediate processes, and provide a quantitative performance evaluation in one of the target use cases.

A study is presented comparing the effectiveness of unsupervised feature representations with handcrafted features for cattle behaviour classification. Precision management of cattle requires the interaction of individual animals to be continuously monitored on the farm. Consequently, classifiers are trained to infer the behaviour of the animals using the observations from the sensors that are fitted upon them. Historically, domain knowledge drives the generation of features for cattle behaviour classifiers. When new behaviours are introduced into the system, however, it is often necessary to modify the feature set; this requires additional design and more data. Autoencoders, on the other hand, can skip this design step by learning a common, unsupervised feature representation for training. Whilst stacked autoencoders successfully represent structured data including speech, language and images, deep networks have not been used to model cattle motion. Hence, we investigate using a stacked autoencoder to learn a feature representation for cattle behaviour classification. Experimental results demonstrate that the autoencoder features perform reasonably well in comparison to the statistical features that are selected using prior knowledge of behaviour motion.

International audience

We present the design and deployment results for PosNet - a large-scale, long-duration sensor network that gathers summary position and status information from mobile nodes. The mobile nodes have a fixed-sized memory buffer to which position data is added at a constant rate, and from which data is downloaded at a non-constant rate. We have developed a novel algorithm that performs online summarization of position data within the buffer, where the algorithm naturally accommodates data input and output rate mismatch, and also provides a delay-tolerant approach to data transport. The algorithm has been extensively tested in a large-scale long-duration cattle monitoring and control application.

This short-paper presents the design and experimental validation of model-based, mobile routing protocol for a delay tolerant network (DTN), where herds of animals are utilised as message ferries. We develop a novel routing protocol that utilises knowledge of the predicted behaviour of each ferry in order to choose optimal ferries for carrying messages from source to sink nodes, as well as minimise routing overhead of the network via adaptive beaconing based on current behaviour.

Agriculture accounts for a significant portion of the GDP in most developed countries. However, managing farms, particularly large-scale extensive farming systems, is hindered by lack of data and increasing shortage of labour. We have deployed a large heterogeneous sensor network on a working farm to explore sensor network applications that can address some of the issues identified above. Our network is solar powered and has been running for over 6 months. The current deployment consists of over 40 moisture sensors that provide soil moisture profiles at varying depths, weight sensors to compute the amount of food and water consumed by animals, electronic tag readers, up to 40 sensors that can be used to track animal movement (consisting of GPS, compass and accelerometers), and 20 sensor/actuators that can be used to apply different stimuli (audio, vibration and mild electric shock) to the animal. The static part of the network is designed for 24/7 operation and is linked to the Internet via a dedicated high-gain radio link, also solar powered. The initial goals of the deployment are to provide a testbed for sensor network research in programmability and data handling while also being a vital tool for scientists to study animal behavior. Our longer term aim is to create a management system that completely transforms the way farms are managed.

This paper presents research that is being conducted by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) with the aim of investigating the use of wireless sensor networks for automated livestock monitoring and control. It is difficult to achieve practical and reliable cattle monitoring with current conventional technologies due to challenges such as large grazing areas of cattle, long time periods of data sampling, and constantly varying physical environments. Wireless sensor networks bring a new level of possibilities into this area with the potential for greatly increased spatial and temporal resolution of measurement data. CSIRO has created a wireless sensor platform for animal behaviour monitoring where we are able to observe and collect information of animals without significantly interfering with them. Based on such monitoring information, we can identify each animal's behaviour and activities successfully