Search

The ability to automatically monitor agricultural fields is an important capability in precision farming, enabling steps towards more sustainable agriculture. Precise, high-resolution monitoring is a key prerequisite for targeted intervention and the selective application of agro-chemicals. The main goal of this paper is developing a novel crop/weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Although a map can be generated by processing single segmented images incrementally, this requires additional complex information fusion techniques which struggle to handle high fidelity maps due to their computational costs and problems in ensuring global consistency. Moreover, computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB (red, green, and blue) inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics., Remote Sensing, 10 (9), ISSN:2072-4292

This paper discusses the problem of autonomous UAV missions in GNSS-challenging environments. A cooperative navigation approach is proposed where autonomous flight of a ("son") UAV in challenging environments is supported by a cooperating ("father") aircraft flying under good satellite coverage, by means of relative sensing and information broadcast. It is assumed that flight plan for the son UAV does not take navigation issues into account and only depends on mission constraints. Thus, the paper is focused on path planning for the father UAV, and its main purpose is to define a flyable trajectory for the father that allows maximizing the accuracy in son positioning estimation when cooperative measurements are used to overcome the lack of GNSS reliable measurements. The concept of generalized dilution of precision is exploited to this aim. Son and father paths are divided into a discrete number of intervals where relative geometry can be kept constant, and father path is then optimized to provide the requested geometries. Transitions between subsequent intervals are designed taking dynamic constraints into account. Simulation results, obtained integrating Matlab and Robot Operating Systems software environments, demonstrate that proper optimization of father trajectory improves cooperative navigation performance.