Loading...
6 results
Search Results
Now showing 1 - 6 of 6
- Peaches detection using a deep learning technique — A contribution to yield estimation resources management, and circular economy.Publication . Assunção, Eduardo; Gaspar, Pedro Dinis; Mesquita, Ricardo; Simões, M.P.; Ramos, António Santos; Proença, Hugo; Inácio, Pedro R.M.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.
- ICT-Enabled Agri-Food SystemsPublication . Gaspar, Pedro Dinis; Soares, V.N.G.J.; Caldeira, J.M.L.P.Today, despite increased information demand from consumers and food chain players alike, Europe’s food businesses and farmers are slow at adopting digital technologies. This is due in part to the inherent complexities of relevant products and processes, and in part to the dynamically changing open network organization of the food sector with its multitude of SMEs, its cultural diversity, its differences in expectations and in the ability to serve transparency needs. The agri-food sector needs to take more advantage of the potential of digital technologies. Relevant technologies may include Internet of Things, Artificial Intelligence, Big Data technologies, remote and localized sensing. This chapter will engage the agri-food community in supporting the development of solutions to remove the barriers to adoption of digital technologies, taking a multi-actor approach across different supply chains (conventional and organic) from farm to fork.
- Real-time image detection for edge devices: a peach fruit detection applicationPublication . Assunção, Eduardo; Gaspar, Pedro Dinis; Alibabaei, Khadijeh; Simões, M.P.; Proença, Hugo; Soares, V.N.G.J.; Caldeira, J.M.L.P.Within the scope of precision agriculture, many applications have been developed to support decision making and yield enhancement. Fruit detection has attracted considerable attention from researchers, and it can be used offline. In contrast, some applications, such as robot vision in orchards, require computer vision models to run on edge devices while performing inferences at high speed. In this area, most modern applications use an integrated graphics processing unit (GPU). In this work, we propose the use of a tensor processing unit (TPU) accelerator with a Raspberry Pi target device and the state-of-the-art, lightweight, and hardware-aware MobileDet detector model. Our contribution is the extension of the possibilities of using accelerators (the TPU) for edge devices in precision agriculture. The proposed method was evaluated using a novel dataset of peaches with three cultivars, which will be made available for further studies. The model achieved an average precision (AP) of 88.2% and a performance of 19.84 frames per second (FPS) at an image size of 640 × 480. The results obtained show that the TPU accelerator can be an excellent alternative for processing on the edge in precision agriculture.
- Navigation system of autonomous multitask robotic rover for agricultural activities on peach orchards based on computer vision through tree trunk detectionPublication . Simões, J.P.; Gaspar, Pedro Dinis; Assunção, Eduardo; Mesquita, Ricardo; Simões, M.P.Introducing robotics in agriculture can allow a rise in productivity and a reduction in costs and waste. Its capabilities can be enhanced to or above the human level, enabling a robot to function as a human does, but with higher precision, repeatability, and with little to no effort. This paper develops a detection algorithm of peach trunks in orchard rows, as autonomous navigation and anti-bump auxiliary system of a terrestrial robotic rover for agricultural applications. The approach involved computational vision, more specifically, the creation of an object detection model based on Convolutional Neural Networks. The framework of the algorithm is Tensorflow, for implementation in a Raspberry Pi 4. The model’s core is the detection system SSD MobileNet 640×640 with transfer learning from the COCO 2017 database. 89 pictures were captured for the database of the model, of which 90% were used for training and the other 10% for testing. The model was converted for mobile applications with a full integer quantization, from 32floatto uint8, and it was compiled for Edge TPU support. The orientation strategy consists of two conditions: a double detection forms a linear function, represented by an imaginary line, which updates every two simultaneous trunks detected. Through the slope of this function and the horizontal deviation of a single detected bounding box from the created line, the algorithm orders the robot to adjust the orientation or keep moving forward. The arithmetic evaluation of the model shows a precision and recall of 94.4%. After the quantization, the new values of these metrics are 92.3 and 66.7%, respectively. These simulation results prove that, statistically, the model can perform the navigation task.
- Fruit recognition and classification based on SVM method for production prediction of peaches – Preliminary studyPublication . Pereira, Tiago; Gaspar, Pedro Dinis; Simões, M.P.The concept of Precision Agriculture is usually associated with the usage of high-end technology equipment (hardware or software) to evaluate or monitor the conditions of a determined portion of land, adjusting afterwards the production factors, like seeds, fertilizers, pesticides, growing regulators, water, according to differential detected characteristics. This paper describes an algorithm developed to analyze and process images to recognize fruits, particularly peaches, and calculate it dimensions, like volume and weight. The recognition of peaches on their natural conditions on trees depends on several spatial- and time-variable parameters and requires complex segmentation algorithms. The proposed algorithm applies image segmentation for extraction of characteristics such as color and shape. These characteristics were used to train a classification method through a Support Vector Machine (SVM) to improve the recognition rate of fruits. The algorithm is designed to acquire images with a high-resolution camera installed in a drone that will fly between the tree lines. The production prediction of 29.3 tons per hectare was obtained based on volume and relation weight/volume calculated for the recognized peaches. An overall precision of 72% was achieved for the prediction rate of peaches in orchards (808 trees/ha). This is the first study regarding the application of these concepts under orchard trees aiming the production prediction along the fruit maturation. Other useful future applications are foreseen in orchard trees, related not only to production prediction, for this type of algorithm.
- Multitask robotic rover for agricultural activities (R2A2): a robotic platform for peach orchardsPublication . Veiros, André; Mesquita, Ricardo; Gaspar, Pedro Dinis; Simões, M.P.This paper describes the latest innovations in agricultural robotics, specifically for weed control, harvesting and monitoring, taking into account the challenges of introducing robotics in this sector, such as fruit detection, orchard navigation, task planning algorithms, or sensors optimization. One of the trends in precision agriculture is the introduction of swarm robotics, allowing collaboration between robots. Another trend is in aerial imagery acquisition for ground analysis as well as environmental reconstruction, complemented by field-mounted sensors. Although robots are becoming quite important in the evolution of agriculture, it is still unlikely that all tasks will be automated in the near future due to the complexity arisen by the overall variability of cultures. The analysis of the current state of the art allows the proposal of a robotic rover for multipurpose agricultural activities (R2A2), developed to perform particular and controlled spraying, to pick up fallen fruits and to predict fruit production in peach orchards. These tasks are performed in different period of the campaign, allowing to use of the same robotic platform for different activities. The tasks performed by the robotic platform aim to help increasing productivity, by accurate fruit counting, that allows decision making concerning water requirements and the reduction of herbicide and pesticide applications.The design and construction of this platform aims to be an additional contribution for the rising of agricultural robotics.