Maria João Sousa

Dr. Maria João Sousa

IDMEC, Instituto Superior Técnico, Universidade de Lisboa
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2020 in Expert Systems with Applications
Verified
Journal Article
Closed access
Maria João SousaMaria João Sousa
Maria João Sousa
Alexandra MoutinhoAlexandra Moutinho
Alexandra Moutinho
MAMiguel Almeida
Miguel Almeida

28 November 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Maria João SousaMaria João Sousa
Maria João Sousa
Alexandra MoutinhoAlexandra Moutinho
Alexandra Moutinho
Miguel AlmeidaMiguel Almeida
Miguel Almeida
With the increasing interest in leveraging mobile robotics for fire detection and monitoring arises the need to design recognition technology systems for these extreme environments. This work focuses on evaluating the sensing capabilities and image processing pipeline of thermal imaging sensors for fire detection applications, paving the way for the development of autonomous systems for early warning and monitoring of fire events. The contributions of this work are threefold. First, we overview image processing algorithms used in thermal imaging regarding data compression and image enhancement. Second, we present a method for data-driven thermal imaging analysis designed for fire situation awareness in robotic perception. A study is undertaken to test the behavior of the thermal cameras in controlled fire scenarios, followed by an in-depth analysis of the experimental data, which reveals the inner workings of these sensors. Third, we discuss key takeaways for the integration of thermal cameras in robotic perception pipelines for autonomous unmanned aerial vehicle (UAV)-based fire surveillance.

1 September 2019 in Expert Systems with Applications
Verified
Journal Article
Closed access
Maria João SousaMaria João Sousa
Maria João Sousa
Alexandra MoutinhoAlexandra Moutinho
Alexandra Moutinho
MAMiguel Almeida
Miguel Almeida

1 July 2020
Verified
Conference Paper
Closed access
Maria João SousaMaria João Sousa
Maria João Sousa
Alexandra MoutinhoAlexandra Moutinho
Alexandra Moutinho
Miguel AlmeidaMiguel Almeida
Miguel Almeida
Unmanned aerial vehicles provide a flexible solution for emerging civilian applications such as last-mile delivery, remote environmental monitoring or hazard detection. However, since the demand for this type of applications is sparsely distributed and comprises spatiotemporal uncertainty, prior to the deployment of aerial means, the dimension and configuration of multi-UAV systems has to be addressed. This paper proposes a clustering-based dimensioning strategy for networks of aerial vehicles, that incorporates heterogeneous vehicle characteristics and energy-related autonomy constraints to determine the type and number of vehicles required to meet a given demand. The approach follows a fuzzy data-driven method which enables generating coverage regions with elastic boundaries that allows for cooperation between neighboring regions to manage high and low demand scenarios, providing improved resilience to demand fluctuations and guaranteeing a well-conditioned formulation for the optimal resource allocation problem.

11 July 2021
Verified
Conference Paper
Closed access
PMPedro Messias
Pedro Messias
Maria João SousaMaria João Sousa
Maria João Sousa
AMAlexandra Moutinho
Alexandra Moutinho
Image-based fire detection is a safety-critical task, which requires high-quality datasets to ensure performance guarantees in real scenarios. Automatic fire detection systems are in ever-increasing demand, but the limited number and size of open datasets, and lack of annotations, hinder model development. Solving this issue requires that experts dedicate a significant time to classify and segment fire events in image datasets. Towards building large-scale curated datasets, this paper presents a data annotation method that leverages semantic segmentation based on superpixel aggregation and color features. The approach introduces interpretable linguistic models that generate pixel-wise fire segmentation and annotations, which are explainable through simple fine-tunable rules that can support subsequent annotation validation by fire domain experts. The performance of the proposed algorithm is evaluated for relevant scenarios using a publicly available dataset, namely through the assessment of the segmentation quality and the labeling of fire color categories. The outcomes of this approach pave the way for creating large-scale datasets that can empower future deployments of learning-based architectures in fire detection systems.

28 March 2022
Verified
Conference Paper
Open access
Maria João SousaMaria João Sousa
Maria João Sousa
Alexandra MoutinhoAlexandra Moutinho
Alexandra Moutinho
Miguel AlmeidaMiguel Almeida
Miguel Almeida
The increased frequency, intensity, and severity of wildfire events in several regions across the world has highlighted several disaster response infrastructure hindrances that call for enhanced intelligence gathering pipelines. In this context, the interest in the use of unmanned aerial vehicles for surveillance and active fire monitoring has been growing in recent years. However, several roadblocks challenge the implementation of these solutions due to their high autonomy requirements and energy-constrained nature. For these reasons, the artificial intelligence development focus on large models hampers the development of models suitable for deployment onboard these platforms. In that sense, while artificial intelligence approaches can be an enabling technology that can effectively scale real-time monitoring services and optimize emergency response resources, the design of these systems imposes: (i) data requirements, (ii) computing constraints and (iii) communications limitations. Here, we propose a decentralized approach, reflecting upon these three vectors.Data-driven artificial intelligence is central to both handle multimodal sensor data in real-time and to annotate large amounts of data collected, which are necessary to build robust safety-critical monitoring systems. Nevertheless, these two objectives have distinct implications computation-wise, because the first must happen on-board, whereas the second can leverage higher processing capabilities off-board. While autonomy of robotic platforms drives mission performance, being a key reason for the need for edge computing of onboard sensor data, the communications design is essential to mission endurance as relaying large amounts of data in real-time is unfeasible energy-wise. For these reasons, real-time processing and data annotation must be tackled in a complimentary manner, instead of the general practice of only targeting overall accuracy improvement. To build wildfire intelligence at the edge, we propose developments on two tracks of solutions: (i) data annotation and (ii) on the edge deployment. The need for considerable effort in these two avenues stems from both having very distinct development requirements and performance evaluation metrics. On the one hand, improving data annotation capacity is essential to build high quality databases that can provide better sources for machine learning. On the other hand, for on the edge deployment the development architectures need to compromise on robustness and architectural parsimony in order to be efficient for edge processing. Whereas the first objective is driven foremost by accuracy, the second goal must emphasize timeliness.AcknowledgmentsThis work was supported by FCT – Fundação para a Ciência e a Tecnologia, I.P., through IDMEC, under project Eye in the Sky, PCIF/SSI/0103/2018, and through IDMEC, under LAETA, project UIDB/50022/2020. M. J. Sousa acknowledges the support from FCT, through the Ph.D. Scholarship SFRH/BD/145559/2019, co-funded by the European Social Fund (ESF).