Pedro Gonçalves

Identifying the plant species comprising a pasture, among other aspects, is crucial for assessing its nutritional value for grazing animals and facilitating its effective management. Traditionally, it requires labor-intensive visual inspection. Artificial Intelligence (AI) offers a solution for automatic classification, yet robust datasets for training such models in natural, uncontrolled environments are scarce. This data descriptor presents a dataset of 741 images collected in pasture lands in the Centre of Portugal using standard cameras at a height of 50 cm. A semi-automated annotation pipeline was employed, utilizing a Faster R-CNN model followed by manual verification and refinement. The dataset contains 1744 annotations across four categories: ‘Shrubs’, ‘Grasses’, ‘Legumes’, and ‘Others’. It includes diverse morphological variations and captures real-world challenges such as occlusion and lighting variability. This dataset serves as a benchmark for training object detection models in agricultural settings, facilitating the development of automated monitoring systems for precision agriculture. Such a mechanism could be incorporated into a mobile application, mounted on a drone, or embedded in an animal-worn device, enabling automated sampling and identification of the plant composition within a pasture.

Early detection of lambing is essential for improving animal welfare and farm management, as it enables timely intervention and reduces complications. Wearable inertial sensors have been applied to sheep monitoring, with frequent transitions between standing and lying identified as key behavioral indicators of lambing. However, unlike in larger livestock, no accelerometry-based system currently provides real-time detection for small ruminants, and existing studies remain limited to preliminary approaches. This study monitored 61 ewes using accelerometers sampling at 20 Hz, while lambing was simultaneously recorded on video to establish precise birth times for 113 events. Video analysis also documented litter size and the need for assistance. Data were organized per ewe, supplemented with information such as birth year, previous lambing records, and ultrasound results. A video of one birth was included to illustrate behavior during the process. The dataset provides a valuable foundation for developing algorithms capable of classifying birth-related behaviors, thereby supporting future automated lambing detection systems.

Effective and sustainable livestock management within Mediterranean ecosystems depends heavily on accurate and timely monitoring of sward composition. Traditionally, this task has relied on human observers who must traverse large and often rugged areas to identify the distribution of grasses, legumes, shrubs, and other plant groups. However, this approach is not only labor-intensive and slow but also susceptible to substantial human error, especially when observations must be repeated frequently or carried out under difficult field conditions. In the present study, an alternative method that integrates wearable cameras with modern computer-vision techniques to automatically recognize pasture plant species through an edge device present in farm premises was investigated. Additionally, the feasibility of achieving reliable classification performance on resource-constrained edge devices was evaluated. To this end, five widely used pre-trained convolutional neural networks were compared against a lightweight custom model developed entirely from scratch. The results demonstrated that ResNet50 delivered the strongest classification accuracy, achieving a Matthews Correlation Coefficient (MCC) of 0.992. Nonetheless, the custom lightweight model proved to be a practical compromise for real-world field use, reaching an MCC of 0.893 while requiring only 6.24 MB of storage. The inference performance on Raspberry Pi 4, Raspberry Pi 5, and Jetson Orin Nano platforms was also evaluated, revealing that the Selective Search stage remains a major computational limitation for achieving real-time operation. The results obtained confirm the possibility of implementing a plant identification system in agricultural facilities without the need to transfer images to a cloud-based application.

Kidding in goats is a highly significant event with major economic implications and strong impacts on the welfare of both the offspring and the mothers. Monitoring the process is extremely demanding, as it is impossible to predict precisely when it will occur. For this reason, the automatic detection of kidding has the potential to generate substantial productivity gains while also improving animal well-being. Artificial intelligence techniques based on accelerometry data have been explored for identifying the event, but these approaches typically rely on data loggers, which cannot trigger real-time alerts or assistance. Embedding detection mechanisms directly into wearable devices enables much faster identification and supports energy-efficient operations. However, this approach also introduces considerable challenges, particularly due to the strict constraints of wearable devices in terms of weight, cost, and battery life. The present work documents the development of a real-time, automatic kidding-detection mechanism in which the detection workload is distributed between the collar and an edge device. System evaluation demonstrated the feasibility of this distributed architecture, confirming that both components can cooperate effectively to achieve reliable detection. The system achieved a Matthews Correlation Coefficient performance of 0.91, highlighting the robustness and practical viability of the proposed solution.

In the last two decades, rural regions have been suffering from profound populational abandonment due to a lack of economic dynamism and motivated by a declining agricultural sector. Conversely, in these regions, the tourism sector has been maintaining economic vigor, even recovering old houses, thus creating a new rural tourism offer. The synergies between the agricultural and the tourism sectors are obvious, despite not being frequently explored, especially by smaller operators. The GAIME project aims to boost agricultural activities in rural regions through cooperation between operators from both sectors. The project strategy is based on a gamification-based process of agritourism experiences, seeking mutual gains between all actors.

The birth process in animals, much like in humans, can encounter complications that pose significant risks to both offspring and mothers. Monitoring these events can provide essential nursing support, but human monitoring is expensive. Although there are commercial monitoring systems for large ruminants, there are no effective solutions for small ruminants, despite various attempts documented in the literature. Inertial sensors are very convenient given their low cost, low impact on animal life, and their flexibility for monitoring animal behavior. This study offers a systematic review of the literature on detecting parturition in small ruminants using inertial sensors. The review analyzed the specifics of published research, including data management and monitoring processes, behaviors indicative of parturition, processing techniques, detection algorithms, and the main results achieved in each study. The results indicated that some methods for detecting birth concentrate on classifying unique animal behaviors, employing diverse processing techniques, and developing detection algorithms. Furthermore, this study emphasized that employing techniques that include analyzing animal activity peaks, specifically recurrent lying down and getting up occurrences, could result in improved detection precision. Although none of the studies provided a completely valid detection algorithm, most results were promising, showing significant behavioral changes in the hours preceding delivery.

Indirect methods of measuring the energy expenditure of grazing animals using heartbeat variation or accelerometers are very convenient due to their low cost and low intrusiveness, allowing animals to maintain their usual routine. In the case of accelerometers, it is possible to use them to measure activity, as well as to classify animal behavior, allowing their usage in other scenarios. Despite the obvious convenience of use, it is important to evaluate the measurement error and understand the validity of the measurement through a simplistic method. In this paper, data from accelerometers were used to classify behavior and measure animal activity, and an algorithm was developed to calculate the energy expended by sheep. The results of the energy expenditure calculations were subsequently compared with the values reported in the literature, and it was verified that the values obtained were within the reference ranges. Although it cannot be used as a real metering of energy expended, the method is promising, as it can be integrated with other complementary sources of information, such as the evolution of the animal’s weight and ingestion time, thus providing assistance in animals’ dietary management.