Crop segmentation is an important task in Precision Agriculture, where the use of aerial robots with an on-board camera has contributed to the development of new solution alternatives. We address the problem of fig plant segmentation in top-view RGB (Red-Green-Blue) images of a crop grown under open-field difficult circumstances of complex lighting conditions and non-ideal crop maintenance practices defined by local farmers. We present a Convolutional Neural Network (CNN) with an encoder-decoder architecture that classifies each pixel as crop or non-crop using only raw colour images as input. Our approach achieves a mean accuracy of 93.85% despite the complexity of the background and a highly variable visual appearance of the leaves. We make available our CNN code to the research community, as well as the aerial image data set and a hand-made ground truth segmentation with pixel precision to facilitate the comparison among different algorithms.

The automatic classification of plants with nutrient deficiencies or excesses is essential in precision agriculture. In particular, being able to perform early detection of nutrient concentrations would increase the production of crop yields and make appropriate use of fertilizers. RGB cameras represent a low-cost alternative sensor for plant monitoring, but this task is complicated when it is purely visual and has limited samples. In this paper, we analyze the Curriculum by Smoothing technique with a small dataset of RGB images (144 images per class) to classify nitrogen concentrations in greenhouse basil plants. Our Deep Learning method changes the texture information found in the images during training by convolving each feature map (the output of a convolutional layer) with a Gaussian kernel whose width increases as training progresses. We observed that controlled information extraction allows a state-of-the-art deep neural network to perform well using little training data containing a high variance between items of the same class. As a result, the Curriculum by Smoothing provides an average accuracy 7% higher than the traditional transfer learning method for the classification of the nitrogen concentration level of greenhouse basil ‘Nufar’ plants with little data.

Currently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Autonomous navigation at low altitudes is an important area of research, as it would allow monitoring parts of the crop that are occluded by their foliage or by other plants. This task is difficult due to the large number of obstacles that might be encountered in the drone’s path. The generation of high-quality depth maps is an alternative for providing real-time obstacle detection and collision avoidance for autonomous UAVs. In this paper, we present a comparative analysis of four supervised learning deep neural networks and a combination of two for monocular depth map estimation considering images captured at low altitudes in simulated natural environments. Our results show that the Boosting Monocular network is the best performing in terms of depth map accuracy because of its capability to process the same image at different scales to avoid loss of fine details.

Municipal solid waste (MSW) accumulation is a critical global challenge for society and governments, impacting environmental and social sustainability. Efficient separation of MSW is essential for resource recovery and advancing sustainable urban management practices. However, manual classification remains a slow and inefficient practice. In response, advances in artificial intelligence, particularly in machine learning, offer more precise and efficient alternative solutions to optimize this process. This research presents the development of a light deep neural network called R3sNet (three “Rs” for Reduce, Reuse, and Recycle) with residual modules trained end-to-end for the binary classification of MSW, with the capability for faster inference. The results indicate that the combination of processing techniques, optimized architecture, and training strategies contributes to an accuracy of 87% for organic waste and 94% for inorganic waste. R3sNet outperforms the pre-trained ResNet50 model by up to 6% in the classification of both organic and inorganic MSW, while also reducing the number of hyperparameters by 98.60% and GFLOPS by 65.17% compared to ResNet50. R3sNet contributes to sustainability by improving the waste separation processes, facilitating higher recycling rates, reducing landfill dependency, and promoting a circular economy. The model’s optimized computational requirements also translate into lower energy consumption during inference, making it well-suited for deployment in resource-constrained devices in smart urban environments. These advancements support the following Sustainable Development Goals (SDGs): SDG 11: Sustainable Cities and Communities, SDG 12: Responsible Consumption and Production, and SDG 13: Climate Action.