Portable devices play an essential role where edge computing is necessary and mobility is required (e.g., robots in agriculture within remote-sensing applications). With the increasing applications of deep neural networks (DNNs) and accelerators for edge devices, several methods and applications have been proposed for simultaneous crop and weed detection. Although preliminary studies have investigated the performance of inference time for semantic segmentation of crops and weeds in edge devices, performance degradation has not been evaluated in detail when the required optimization is applied to the model for operation in such edge devices. This paper investigates the relationship between model tuning hyperparameters to improve inference time and its effect on segmentation performance. The study was conducted using semantic segmentation model DeeplabV3 with a MobileNet backbone. Different datasets (Cityscapes, PASCAL and ADE20K) were analyzed for a transfer learning strategy. The results show that, when using a model hyperparameter depth multiplier (DM) of 0.5 and the TensorRT framework, segmentation performance mean intersection over union (mIOU) decreased by 14.7% compared to that of a DM of 1.0 and no TensorRT. However, inference time accelerated dramatically by a factor of 14.8. At an image resolution of $1296\times 966$, segmentation performance of 64% mIOU and inference of 5.9 frames per second (FPS) was achieved in Jetson Nano’s device. With an input image resolution of $513\times 513$, and hyperparameters output stride OS = 32 and DM = 0.5, an inference time of 0.04 s was achieved resulting in 25 FPS. The results presented in this paper provide a deeper insight into how the performance of the semantic segmentation model of crops and weeds degrades when optimization is applied to adapt the model to run on edge devices. Lastly, an application is described for the semantic segmentation of weeds embedded in the edge device (Jetson Nano) and integrated with the robotic orchard. The results show good spraying accuracy and feasibility of the method.

Bird damage to fruit crops causes significant monetary losses to farmers annually. The application of traditional bird repelling methods such as bird cannons and tree netting become inefficient in the long run, requiring high maintenance and reducing mobility. Due to their versatility, Unmanned Aerial Vehicles (UAVs) can be beneficial to solve this problem. However, due to their low battery capacity that equals low flight duration, it is necessary to evolve path planning optimization. A novel path planning optimization algorithm of UAVs based on Particle Swarm Optimization (PSO) is presented in this paper. This path planning optimization algorithm aims to manage the drone’s distance and flight time, applying optimization and randomness techniques to overcome the disadvantages of the traditional systems. The proposed algorithm’s performance was tested in three study cases: two of them in simulation to test the variation of each parameter and one in the field to test the influence on battery management and height influence. All cases were tested in the three possible situations: same incidence rate, different rates, and different rates with no bird damage to fruit crops. The field tests were also essential to understand the algorithm’s behavior of the path planning algorithm in the UAV, showing that there is less efficiency with fewer points of interest, but this does not correlate with the flight time. In addition, there is no association between the maximum horizontal speed and the flight time, which means that the function to calculate the total distance for path planning needs to be adjusted. Thus, the proposed algorithm presents promising results with an outstanding reduced average error in the total distance for the path planning obtained and low execution time, being suited for this and other applications.

Fruit detection is crucial for yield estimation and fruit picking system performance. Many state-of-the-art methods for fruit detection use convolutional neural networks (CNNs). This paper presents the results for peach detection by applying a faster R-CNN framework in images captured from an outdoor orchard. Although this method has been used in other studies to detect fruits, there is no research on peaches. Since the fruit colors, sizes, shapes, tree branches, fruit bunches, and distributions in trees are particular, the development of a fruit detection procedure is specific. The results show great potential in using this method to detect this type of fruit. A detection accuracy of 0.90 using the metric average precision (AP) was achieved for fruit detection. Precision agriculture applications, such as deep neural networks (DNNs), as proposed in this paper, can help to mitigate climate change, due to horticultural activities by accurate product prediction, leading to improved resource management (e.g., irrigation water, nutrients, herbicides, pesticides), and helping to reduce food loss and waste via improved agricultural activity scheduling.