Emotion recognition has attracted major attention in numerous fields because of its relevant applications in the contemporary world: marketing, psychology, surveillance, and entertainment are some examples. It is possible to recognize an emotion through several ways; however, this paper focuses on facial expressions, presenting a systematic review on the matter. In addition, 112 papers published in ACM, IEEE, BASE and Springer between January 2006 and April 2019 regarding this topic were extensively reviewed. Their most used methods and algorithms will be firstly introduced and summarized for a better understanding, such as face detection, smoothing, Principal Component Analysis (PCA), Local Binary Patterns (LBP), Optical Flow (OF), Gabor filters, among others. This review identified a clear difficulty in translating the high facial expression recognition (FER) accuracy in controlled environments to uncontrolled and pose-variant environments. The future efforts in the FER field should be put into multimodal systems that are robust enough to face the adversities of real world scenarios. A thorough analysis on the research done on FER in Computer Vision based on the selected papers is presented. This review aims to not only become a reference for future research on emotion recognition, but also to provide an overview of the work done in this topic for potential readers.

Monitoring classrooms using cameras is a non-invasive approach of digitizing students’ behaviour. Understanding students’ attention span and what type of behaviours may indicate a lack of attention is fundamental for understanding and consequently improving the dynamics of a lecture. Recent studies show useful information regarding classrooms and their students’ behaviour throughout the lecture. In this paper we start by presenting an overview about the state of the art on this topic, presenting what we consider to be the most robust and efficient Computer Vision techniques for monitoring classrooms. After the analysis of relevant state of the art, we propose an agent that is theoretically capable of tracking the students’ attention and output that data. The main goal of this paper is to contribute to the development of an autonomous agent able to provide information to both teachers and students and we present preliminary results on this topic. We believe this autonomous agent features the best solution for monitoring classrooms since it uses the most suited state of the art approaches for each individual role.

Floor-cleaning robots are becoming increasingly more sophisticated over time and with the addition of digital cameras supported by a robust vision system they become more autonomous, both in terms of their navigation skills but also in their capabilities of analyzing the surrounding environment. This document proposes a vision system based on the YOLOv5 framework for detecting dirty spots on the floor. The purpose of such a vision system is to save energy and resources, since the cleaning system of the robot will be activated only when a dirty spot is detected and the quantity of resources will vary according to the dirty area. In this context, false positives are highly undesirable. On the other hand, false negatives will lead to a poor cleaning performance of the robot. For this reason, a synthetic data generator found in the literature was improved and adapted for this work to tackle the lack of real data in this area. This synthetic data generator allows for large datasets with numerous samples of floors and dirty spots. A novel approach in selecting floor images for the training dataset is proposed. In this approach, the floor is segmented from other objects in the image such that dirty spots are only generated on the floor and do not overlap those objects. This helps the models to distinguish between dirty spots and objects in the image, which reduces the number of false positives. Furthermore, a relevant dataset of the Automation and Control Institute (ACIN) was found to be partially labelled. Consequently, this dataset was annotated from scratch, tripling the number of labelled images and correcting some poor annotations from the original labels. Finally, this document shows the process of generating synthetic data which is used for training YOLOv5 models. These models were tested on a real dataset (ACIN) and the best model attained a mean average precision (mAP) of 0.874 for detecting solid dirt. These results further prove that our proposal is able to use synthetic data for the training step and effectively detect dirt on real data. According to our knowledge, there are no previous works reporting the use of YOLOv5 models in this application.

The increasing relevance of remote sensing and artificial intelligence (AI) for archaeological research and cultural heritage management is undeniable. However, there is a critical gap in this field. Many studies conclude with identifying hundreds or even thousands of potential sites, but very few follow through with crucial fieldwork validation to confirm their existence. This research addresses this gap by proposing and implementing a fieldwork validation pipeline. In northern Portugal’s Alto Minho region, we employed this pipeline to verify 237 potential burial mounds identified by an AI-powered algorithm. Fieldwork provided valuable information on the optimal conditions for burial mounds and the specific factors that led the algorithm to err. Based on these insights, we implemented two key improvements to the algorithm. First, we incorporated a slope map derived from LiDAR-generated terrain models to eliminate potential burial mound inferences in areas with high slopes. Second, we trained a Vision Transformer model using digital orthophotos of both confirmed burial mounds and previously identified False Positives. This further refines the algorithm’s ability to distinguish genuine sites. The improved algorithm was then tested in two areas: the original Alto Minho validation region and the Barbanza region in Spain, where the location of burial mounds was well established through prior field work.

Mapping potential archaeological sites using remote sensing and artificial intelligence can be an efficient tool to assist archaeologists during project planning and fieldwork. This paper explores the use of airborne LiDAR data and data-centric artificial intelligence for identifying potential burial mounds. The challenge of exploring the landscape and mapping new archaeological sites, coupled with the difficulty of identifying them through visual analysis of remote sensing data, results in the recurring issue of insufficient annotations. Additionally, the top-down nature of LiDAR data hinders artificial intelligence in its search, as the morphology of archaeological sites blends with the morphology of natural and artificial shapes, leading to a frequent occurrence of false positives. To address this problem, a novel data-centric artificial intelligence approach is proposed, exploring the available data and tools. The LiDAR data is pre-processed into a dataset of 2D digital elevation images, and the known burial mounds are annotated. This dataset is augmented with a copy-paste object embedding based on Location-Based Ranking. This technique uses the Land-Use and Occupation Charter to segment the regions of interest, where burial mounds can be pasted. YOLOv5 is trained on the resulting dataset to propose new burial mounds. These proposals go through a post-processing step, using directly the 3D data acquired by the LiDAR to verify if its 3D shape is similar to the annotated sites. This approach drastically reduced false positives, attaining a 72.53% positive rate, relevant for the ground-truthing phase where archaeologists visit the coordinates of proposed burial mounds to confirm their existence.

Recent advancements in remote sensing and artificial intelligence can potentially revolutionize the automated detection of archaeological sites. However, the challenging task of interpreting remote sensing imagery combined with the intricate shapes of archaeological sites can hinder the performance of computer vision systems. This work presents a computer vision system trained for efficient hillfort detection in remote sensing imagery. Equipped with an adapted multimodal semantic segmentation model, the system integrates LiDAR‐derived LRM images and aerial orthoimages for feature fusion, generating a binary mask pinpointing detected hillforts. Post‐processing includes margin and area filters to remove edge inferences and smaller anomalies. The resulting inferences are subjected to hard positive and negative mining, where expert archaeologists classify them to populate the training data with new samples for retraining the segmentation model. As the computer vision system is far more likely to encounter background images during its search, the training data are intentionally biased towards negative examples. This approach aims to reduce the number of false positives, typically seen when applying machine learning solutions to remote sensing imagery. Northwest Iberia experiments witnessed a drastic reduction in false positives, from 5678 to 40 after a single hard positive and negative mining iteration, yielding a 99.3% reduction, with a resulting F₁ score of 66%. In England experiments, the system achieved a 59% F₁ score when fine‐tuned and deployed countrywide. Its scalability to diverse archaeological sites is demonstrated by successfully detecting hillforts and other types of enclosures despite their typical complex and varied shapes. Future work will explore archaeological predictive modelling to identify regions with higher archaeological potential to focus the search, addressing processing time challenges.