Considering the population growth rate of recent years, a doubling of the current worldwide crop productivity is expected to be needed by 2050. Pests and diseases are a major obstacle to achieving this productivity outcome. Therefore, it is very important to develop efficient methods for the automatic detection, identification, and prediction of pests and diseases in agricultural crops. To perform such automation, Machine Learning (ML) techniques can be used to derive knowledge and relationships from the data that is being worked on. This paper presents a literature review on ML techniques used in the agricultural sector, focusing on the tasks of classification, detection, and prediction of diseases and pests, with an emphasis on tomato crops. This survey aims to contribute to the development of smart farming and precision agriculture by promoting the development of techniques that will allow farmers to decrease the use of pesticides and chemicals while preserving and improving their crop quality and production.

This paper proposes a no-reference quality assessment metric for digital video subject to H.264/advanced video coding encoding. The proposed metric comprises two main steps: coding error estimation and perceptual weighting of this error. Error estimates are computed in the transform domain, assuming that discrete cosine transform (DCT) coefficients are corrupted by quantization noise. The DCT coefficient distributions are modeled using Cauchy or Laplace probability density functions, whose parameterization is performed using the quantized coefficient data and quantization steps. Parameter estimation is based on a maximum-likelihood estimation method combined with linear prediction. The linear prediction scheme takes advantage of the correlation between parameter values at neighbor DCT spatial frequencies. As for the perceptual weighting module, it is based on a spatiotemporal contrast sensitivity function applied to the DCT domain that compensates image plane movement by considering the movements of the human eye, namely smooth pursuit, natural drift, and saccadic movements. The video related inputs for the perceptual model are the motion vectors and the frame rate, which are also extracted from the encoded video. Subjective video quality assessment tests have been carried out in order to validate the results of the metric. A set of 11 video sequences, spanning a wide range of content, have been encoded at different bitrates and the outcome was subject to quality evaluation. Results show that the quality scores computed by the proposed algorithm are well correlated with the mean opinion scores associated to the subjective assessment.

As climate change, biodiversity loss, and biological invaders are all on the rise, the significance of conservation and pest management initiatives cannot be stressed. Insect traps are frequently used in projects to discover and monitor insect populations, assign management and conservation strategies, and assess the effectiveness of treatment. This paper assesses the application of YOLOv5 for detecting insects in yellow sticky traps using images collected from insect traps in Portuguese tomato plantations, acquired under open field conditions. Furthermore, a sliding window approach was used to minimize insect detection duplicates in a non-complex way. This article also contributes to event forecasting in agriculture fields, such as diseases and pests outbreak, by obtaining insect-related metrics that can be further analyzed and combined with other data extracted from the crop fields, contributing to smart farming and precision agriculture. The proposed method achieved good results when compared to related works, reaching 94.4% for mAP_0.5, with a precision and recall of 88% and 91%, respectively, using YOLOv5x.

In recent years, Portugal has seen wide variability in wildfire damage associated to high unpredictability of climatic events such as severe heatwaves and drier summers. Therefore, timely and accurate detection of forest and rural fires is of great importance for successful fire containment and suppression efforts, as wildfires exponentially increase the spread rate from the moment of ignition. In the field of early smoke detection, the CICLOPE project currently trailblazes in the employment of a network of Remote Acquisition Towers for wildfire prevention and observation, along with a rule-based automatic smoke detection system, covering over 2, 700, 000 hectares of wildland and rural area in continental Portugal. However, the inherent challenges of automatic smoke detection raise issues of high false alarm rates that affect the system’s prediction quality and overwhelm the Management and Control Centers with numerous false alarms. The researchwork presented in this paper evaluates the potential improvement in wildfire smoke detection accuracy and specificity using deep learning-based architectures. It proposes a solution based on a Dual-Channel CNN that can be deployed as a secondary prediction confirmation layer to further refine the CICLOPE automatic smoke detection system. The proposed solution takes advantage of the high true alarm coverage of the current detection system by taking only the predicted alarm images and respective bounding box coordinates as inputs. The Dual-Channel network combines state-of-the-art DenseNet architecture with a novel detail selective network with spatial and channel attention modules trained separately with image data obtained from CICLOPE, fusing the extracted features from both networks in a concatenation layer. The results demonstrate that the proposed Dual-Channel CNN outperforms both single-channel networks achieving an accuracy of 99.7% and a low false alarm rate of 0.20% when re-examining the alarms produced by the CICLOPE surveillance system.

Air pollution is known to be one of the main causes of injuries to the respiratory system and even premature death. Gases, particles, and biological compounds affect not only the air we breathe outdoors, but also indoors. Children are highly affected by the poor quality of the air they breathe because their organs and immune systems are still in the developmental stages. To contribute to raising children’s awareness to these concerns, this article presents the design, implementation, and experimental validation of an serious augmented reality game for children to playfully learn about air quality by interacting with physical sensor nodes. The game presents visual representations of the pollutants measured by the sensor node, rendering tangible the invisible. Causal knowledge is elicited by stimulating the children to expose real-life objects (e.g., candles) to the sensor node. The playful experience is amplified by letting children play in pairs. The game was evaluated using the Wizard of Oz method in a sample of 27 children aged between 7 and 11 years. The results show that the proposed game, in addition to improving children’s knowledge about indoor air pollution, is also perceived by them as easy to use and a useful learning tool that they would like to continue using, even in other educational contexts.