Alberto F. De Souza

• Ph.D.
• Professor (Associate) at Federal University of Espírito Santo

Multiple choice questions (MCQs) are often used in both employee selection and training, providing objectivity, efficiency, and scalability. However, their creation is resource-intensive, requiring significant expertise and financial investment. This study leverages large language models (LLMs) and prompt engineering techniques to automate the gene...

Motor Imagery (MI)-based Brain–Computer Interface (BCI) systems are a great technological advance for the recovery of lost movements in people with severe motor impairments. Different Artificial Intelligence (AI) techniques with supervised methods have been explored for MI task discrimination, especially static movements from left and right hands....

Stroke is a neurological condition that usually results in the loss of voluntary control of body movements, making it difficult for individuals to perform activities of daily living (ADLs). Brain-computer interfaces (BCIs) integrated into robotic systems, such as motorized mini exercise bikes (MMEBs), have been demonstrated to be suitable for resto...

Stroke is a neurological syndrome that usually causes a loss of voluntary control of lower/upper body movements, making it difficult for affected individuals to perform Activities of Daily Living (ADLs). Brain-Computer Interfaces (BCIs) combined with robotic systems, such as Motorized Mini Exercise Bikes (MMEB), have enabled the rehabilitation of p...

The effects of corticomuscular connectivity during object manipulation tasks with different haptic sensations have not been quantitatively investigated. Connectivity analyses enable the study of cortical effects and muscle responses during movements, revealing communication pathways between the brain and muscles. This study aims to examine the cort...

Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related to the fatigue, substance consumption, concentration, and experience in the use. To reduce the effects of lack of experience in the use of BCI systems (naïve users), this paper...

Agricultural losses due to post-harvest diseases can reach up to 30% of total production. Detecting diseases in fruits at an early stage is crucial to mitigate losses and ensure the quality and health of fruits. However, this task is challenging due to the different formats, sizes, shapes, and colors that the same disease can present. Convolutional...

Kinematic reconstruction of lower-limb movements using electroencephalography (EEG) has been used in several rehabilitation systems. However, the nonlinear relationship between neural activity and limb movement may challenge decoders in real-time Brain-Computer Interface (BCI) applications. This paper proposes a nonlinear neural decoder using an Un...

The advances in machine learning – particularly in deep learning – have enabled automatizing the reconstruction of shredded documents with significant accuracy. However, despite the recent remarkable results, the state-of-the-art on fully automatic reconstruction still has room for improvement, mainly due to imprecision on the evaluation of how the...

Deep learning has become a standard approach to machine vision in recent years. Despite several advances, it requires large amounts of annotated data. Nonetheless, in many applications, large-scale data acquisition and annotation is expensive and data imbalance is an intrinsic problem. To address these challenges, we propose a novel synthetic datab...

Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features proven to be promising, achieving state-of-the-art results. However, these methods are laborious to implement and h...

Companies created for money-laundering or as a means for taxevasion are harmful to the country's economy and society. This problem is usually tackled by governmental agencies by having officials to pore over companies' financial data and to single out those that exhibit fraudulent behavior. Such work tends to be slow-paced and tedious. This paper p...

As changes in external environments are inevitable, a lifelong mapping system is desirable for autonomous robots that aim at long-term operation. Capturing external environment changes into internal representations (for example, maps) is crucial for proper behavior and safety, especially in the case of autonomous vehicles. In this work, we propose...

The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for eac...

In recent years, approaches based on machine learning, more specifically Deep Neural Networks (DNN), have gained prominence as a solution to computer vision problems in the most diverse areas. However, this type of approach requires a large number of samples of the problem to be treated, which often makes this type of approach difficult. In compute...

The analysis of Magnetic Resonance Imaging (MRI) sequences enables clinical professionals to monitor the progression of a brain tumor. As the interest for automatizing brain volume MRI analysis increases, it becomes convenient to have each sequence well identified. However, the unstandardized naming of MRI sequences makes their identification diffi...

Deep neural networks come as an effective solution to many problems associated with autonomous driving. By providing real image samples with traffic context to the network, the model learns to detect and classify elements of interest, such as pedestrians, traffic signs, and traffic lights. However, acquiring and annotating real data can be extremel...

Convolutional neural networks have been successful lately enabling companies to develop neural-based products, which demand an expensive process, involving data acquisition and annotation; and model generation, usually requiring experts. With all these costs, companies are concerned about the security of their models against copies and deliver them...

Convolutional neural networks have been successful lately enabling companies to develop neural-based products, which demand an expensive process, involving data acquisition and annotation; and model generation, usually requiring experts. With all these costs, companies are concerned about the security of their models against copies and deliver them...

Deep neural networks come as an effective solution to many problems associated with autonomous driving. By providing real image samples with traffic context to the network, the model learns to detect and classify elements of interest, such as pedestrians, traffic signs, and traffic lights. However, acquiring and annotating real data can be extremel...

Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for autonomous vehicles. In this work, we propose LaneATT: an anchor-based deep lane detection model, which, akin to other generic deep object detectors, uses the anchors for...

The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for eac...

We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the deci...

Deep learning has been successfully applied to several problems related to autonomous driving, often relying on large databases of real target-domain images for proper training. The acquisition of such real-world data is not always possible in the self-driving context, and sometimes their annotation is not feasible. Moreover, in many tasks, there i...

The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solut...

The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solut...

One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods for this task have to work in real time (+30 FPS), they not only have to be effective (i.e., have high accurac...

In general, proposed solutions for LiDAR-based localization used in autonomous cars require expensive sensors and computationally expensive mapping processes. Moreover, the global localization for autonomous driving is converging to the use of maps. Straightforward strategies to reduce the costs are to produce simpler sensors and use maps already a...

The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly relevant for supporting forensic investigation as documents may contain criminal evidence. As an alternative to the laborious and time-consuming manual process, several r...

Avanços da inteligência artificial têm um papel importante no desenvolvimento de carros autônomos, como auxiliar no reconhecimento de semáforos. No entanto, quando contando com imagens da cena apenas, pouco progresso foi observado na seleção dos semáforos que definem orientação para o carro. Abordagens comuns de detecção dependem de processo adicio...

We propose a bio-inspired foveated technique to detect cars in a long range camera view using a deep convolutional neural network (DCNN) for the IARA self-driving car. The DCNN receives as input (i) an image, which is captured by a camera installed on IARA's roof; and (ii) crops of the image, which are centered in the waypoints computed by IARA's p...

The development of intelligent autonomous cars is of great interest. A particular and challenging problem is to handle pedestrians, for example, crossing or walking along the road. Since pedestrians are one of the most fragile elements in traffic, a reliable pedestrian detection and handling system is mandatory. The current pedestrian handling syst...

Deep learning has been successfully applied to several problems related to autonomous driving. Often, these solutions rely on large networks that require databases of real image samples of the problem (i.e., real world) for proper training. The acquisition of such real-world data sets is not always possible in the autonomous driving context, and so...

Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training dataset which must resemble the images in the target task. The acquisition of a dataset involves annotating images, an arduous and expensive process, gen...

Autonomous terrestrial vehicles must be capable of perceiving traffic lights and recognizing their current states to share the streets with human drivers. Most of the time, human drivers can easily identify the relevant traffic lights. To deal with this issue, a common solution for autonomous cars is to integrate recognition with prior maps. Howeve...

Autonomous robotic vehicles need accurate positioning to navigate. For outdoor autonomous vehicles, the localization problem has been solved using GNSS systems. However, many places suffer from problems in the signal of those systems, known as GNSS-denied environments. To face such a problem, several approaches first map the environment to thereaft...

We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the deci...

In this work, we present a novel strategy for correcting imperfections in occupancy grid maps called map decay. The objective of map decay is to correct invalid occupancy probabilities of map cells that are unobservable by sensors. The strategy was inspired by an analogy between the memory architecture believed to exist in the human brain and the m...

Advanced Driver Assistance Systems (ADAS) have experienced major advances in the past few years. The main objective of ADAS includes keeping the vehicle in the correct road direction, and avoiding collision with other vehicles or obstacles around. In this paper, we address the problem of estimating the heading direction that keeps the vehicle align...

Decreasing costs of vision sensors and advances in embedded hardware boosted lane related research detection, estimation, and tracking in the past two decades. The interest in this topic has increased even more with the demand for advanced driver assistance systems (ADAS) and self-driving cars. Although extensively studied independently, there is s...

In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore it is in their best interest to protect them, i.e., to avoid that someone else copies them. Recent studies rev...

Correctly identifying crosswalks is an essential task for the driving activity and mobility autonomy. Many crosswalk classification, detection and localization systems have been proposed in the literature over the years. These systems use different perspectives to tackle the crosswalk classification problem: satellite imagery, cockpit view (from th...

This work describes the development of a nonfatigating Brain–Computer Interface (BCI) based on Steady State Evoked Potentials (SSVEP) and Event-Related Desynchronization (ERD) to control an autonomous car. Through a graphical interface presented to the user in the autonomous car, destination places are shown. The selection of commands is performed...

Currently, self-driving cars rely greatly on the Global Positioning System (GPS) infrastructure, albeit there is an increasing demand for alternative methods for GPS-denied environments. One of them is known as place recognition, which associates images of places with their corresponding positions. We previously proposed systems based on Weightless...

In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore it is in their best interest to protect them, i.e., to avoid that someone else copy them. Recent studies revea...

We propose the use of deep neural networks (DNN) for solving the problem of inferring the position and relevant properties of lanes of urban roads with poor or absent horizontal signalization, in order to allow the operation of autonomous cars in such situations. We take a segmentation approach to the problem and use the Efficient Neural Network (E...

Decreasing costs of vision sensors and advances in embedded hardware boosted lane related research detection, estimation, and tracking in the past two decades. The interest in this topic has increased even more with the demand for advanced driver assistance systems (ADAS) and self-driving cars. Although extensively studied independently, there is s...

Correctly identifying crosswalks is an essential task for the driving activity and mobility autonomy. Many crosswalk classification, detection and localization systems have been proposed in the literature over the years. These systems use different perspectives to tackle the crosswalk classification problem: satellite imagery, cockpit view (from th...

High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing classification problem. In this letter, crowdsourcing systems are exploited in order to enable the automatic...

High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing classification problem. In this letter, crowdsourcing systems are exploited in order to enable the automatic...

We present the Model-Predictive Motion Planner (MPMP) of the Intelligent Autonomous Robotic Automobile (IARA). IARA is a fully autonomous car that uses a path planner to compute a path from its current position to the desired destination. Using this path, the current position, a goal in the path and a map, IARA's MPMP is able to compute smooth traj...

We present a simple yet effective obstacle avoider for the Intelligent and Autonomous Robotic Automobile (IARA). At each or several motion planning cycles, the IARA's obstacle avoider firstly receives as input an updated map of the environment around the car, the current car's state relative to the map, and a trajectory from the current car's state...

We propose a light-weight yet accurate localization system for autonomous cars that operate in large-scale and complex urban environments. It provides appropriate localization accuracy and processing time at high frequency suitable for fast control actions, besides low power consumption desirable for limited energy availability in commercial cars....

This paper studies two end-effector modalities for warehouse picking: (i) a recently developed, underactuated three-finger hand and (ii) a custom built, vacuum-based gripper. The two systems differ on how they pick objects. The first tool provides increased flexibility, while the vacuum alternative is simpler and smaller. The aim is to show how the...

Facial expression recognition has been an active research area in the past ten years, with growing application areas including avatar animation, neuromarketing and sociable robots. The recognition of facial expressions is not an easy problem for machine learning methods, since people can vary significantly in the way they show their expressions. Ev...

We present a biologically inspired long-term object tracking system based on Virtual Generalizing Random Access Memory (VG-RAM) Weightless Neural Networks (WNN). VG-RAM WNN is an effective machine learning technique that offers simple implementation and fast training. Our system models the biological saccadic eye movement, the transformation suffer...

The Virtual Generalizing Random Access Memory Weightless Neural Network (VG-RAM WNN) is a type of WNN that only requires storage capacity proportional to the training set. As such, it is an effective machine learning technique that offers simple implementation and fast training – it can be made in one shot. However, the VG-RAM WNN test time for app...

This work proposes a system for detection and tracking of multiple moving vehicles in the environment around an autonomous vehicle using a Light Detection and Ranging (LIDAR) 3D sensor. The proposed system operates in four steps: pre-processing, segmentation, association and tracking. At each sensor scan, the sensor data is converted into a 3D poin...