Cristiano Premebida

Cristiano Premebida
University of Coimbra | UC · Department of Electrical & Computer Engineering

PhD

About

63
Publications
47,777
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,774
Citations
Introduction
Cristiano Premebida is a Lecturer in the Dept of Electrical and Computer Engineering (DEEC) at the University of Coimbra, Portugal. His main research interests are robotic perception, mobile robotics, machine learning, autonomous vehicles, ADAS, CAV, and sensor fusion. He is part of the Institute of Systems and Robotics (ISR-UC), and also collaborates with the ARVIS Lab (Aston Univ) and LUCAS Lab (Lboro Univ, UK).

Publications

Publications (63)
Preprint
Full-text available
In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs. Such layers often produce overconfident predictions rather than proper probabilistic scores, which can thus harm the decision-making of `critical' perception systems applied in autonomous driving and robotics....
Article
In state-of-the-art deep learning for object recognition, Softmax and Sigmoid layers are most commonly employed as the predictor outputs. Such layers often produce overconfidence predictions rather than proper probabilistic scores, which can thus harm the decision-making of ‘critical’ perception systems applied in autonomous driving and robotics. G...
Preprint
Full-text available
Object detection in autonomous driving applications implies that the detection and tracking of semantic objects are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art deep-learning based object detection is false positive which occurrences with overconfident scores. This is hi...
Preprint
Full-text available
Autonomous Vehicles (AV) are becoming more capable of navigating in complex environments with dynamic and changing conditions. A key component that enables these intelligent vehicles to overcome such conditions and become more autonomous is the sophistication of the perception and localization systems. As part of the localization system, place reco...
Preprint
Full-text available
Deep networks have been progressively adapted to new sensor modalities, namely to 3D LiDAR, which led to unprecedented achievements in autonomous vehicle-related applications such as place recognition. One of the main challenges of deep models in place recognition is to extract efficient and descriptive feature representations that relate places ba...
Conference Paper
Deep learning on 3D point clouds has drawn much attention, due to its large variety of applications in intelligent perception for automated and robotic systems. Unlike structured 2D images, it is challenging to extract features and implement convolutional networks over these unordered points. Although a number of previous works achieved high accura...
Article
Full-text available
In this work we present a three-stage Machine Learning strategy to country-level risk classification based on countries that are reporting COVID-19 information. A K% binning discretisation (K = 25) is used to create four risk groups of countries based on the risk of transmission (coronavirus cases per million population), risk of mortality (coronav...
Conference Paper
Full-text available
The novelty of this study consists in a multi-modality approach to scene classification, where image and audio complement each other in a process of deep late fusion. The approach is demonstrated on a difficult classification problem, consisting of two synchronised and balanced datasets of 16,000 data objects, encompassing 4.4 hours of video of 8 e...
Preprint
Full-text available
The novelty of this study consists in a multi-modality approach to scene classification, where image and audio complement each other in a process of deep late fusion. The approach is demonstrated on a difficult classification problem, consisting of two synchronised and balanced datasets of 16,000 data objects, encompassing 4.4 hours of video of 8 e...
Preprint
Full-text available
In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects and consider their MFCC attributes. Using character level LSTMs (supervised learning) and OpenAI's attention-b...
Preprint
Full-text available
Deep networks are currently the state-of-the-art for sensory perception in autonomous driving and robotics. However, deep models often generate overconfident predictions precluding proper probabilistic interpretation which we argue is due to the nature of the SoftMax layer. To reduce the overconfidence without compromising the classification perfor...
Conference Paper
Full-text available
Autonomous speaker identification suffers issues of data scarcity due to it being unrealistic to gather hours of speaker audio to form a dataset, which inevitably leads to class imbalance in comparison to the large data availability from non-speakers since large-scale speech datasets are available online. In this study, we explore the possibility o...
Conference Paper
Full-text available
Object detection and recognition is a key component of autonomous robotic vehicles, as evidenced by the continuous efforts made by the robotic community on areas related to object detection and sensory perception systems. This paper presents a study on multisensor (camera and LIDAR) late fusion strategies for object recognition. In this work, LIDAR...
Chapter
The aim of this paper is to contribute with an object-based learning and selection methods to improve localization and mapping techniques. The methods use 3D-LiDAR data which is suitable for autonomous driving systems operating in urban environments. The objects of interest to be served as landmarks are pole-like objects which are naturally present...
Chapter
Full-text available
Autonomous driving systems (ADS) comprise, essentially, sensory perception (including AI-ML-based techniques), localization, decision-making, and control. The cornerstone of an ADS is the sensory perception part, which is involved in most of the essential and necessary tasks for safe driving such as sensor-fusion, environment representation, scene...
Chapter
Full-text available
Robotic perception is related to many applications in robotics where sensory data and artificial intelligence/machine learning (AI/ML) techniques are involved. Examples of such applications are object detection, environment representation, scene understanding, human/pedestrian detection, activity recognition, semantic place classification, object m...
Conference Paper
Full-text available
This paper presents a study on pedestrian classification based on deep learning using data from a monocular camera and a 3D LIDAR sensor, separately and in combination. Early and late multi-modal sensor fusion approaches are revisited and compared in terms of classification performance. The problem of pedestrian classification finds applications in...
Article
The technological advances of autonomous and connected road vehicles have been shown an accelerating pace in the recent years. On the other hand, the regulations for autonomous, or driverless, road vehicles across Europe still deserve much attention and discussion. In this paper, we introduce the AUTOCITS project which has the main goals of conduct...
Chapter
Full-text available
This paper addresses the problem of vehicle detection using a little explored LIDAR’s modality: the reflection intensity. LIDAR reflection measures the ratio of the received beam sent to a surface, which depends upon the distance, material, and the angle between surface normal and the ray. Considering a 3D-LIDAR mounted on board a robotic vehicle,...
Conference Paper
Full-text available
ARMADA 2017 Workshop Proceedings: 1-BEAT-o-matic: a baseline for learning behavior expressions from utterances (Matthias Gallé, Ankuj Arora); 2-Tactile Recognition based on Two-layered Hidden Markov Models (Nutnaree Kleawsirikul, Hironori Mitake, Shoichi Hasegawa); 3-Semantic Edge Detection (Anastasia Bolotnikova); 4-Towards Multimodal Affecti...
Article
Full-text available
Most of the current successful object detection approaches are based on a class of deep learning models called Convolutional Neural Networks (ConvNets). While most existing object detection researches are focused on using ConvNets with color image data, emerging fields of application such as Autonomous Vehicles (AVs) which integrates a diverse set...
Conference Paper
Full-text available
This paper addresses the problem of vehicle detection using Deep Convolutional Neural Network (ConvNet) and 3D-LIDAR data with application in advanced driver assistance systems and autonomous driving. A vehicle detection system based on the Hypothesis Generation (HG) and Verification (HV) paradigms is proposed. The data inputted to the system is a...
Conference Paper
Full-text available
This paper addresses the problem of vehicle detection using a little explored LIDAR's modality: the reflection intensity. LIDAR reflection measures the ratio of the received beam sent to a surface, which depends upon the distance, material, and the angle between surface normal and the ray. Considering a 3D-LIDAR mounted on board a robotic vehicle,...
Article
Full-text available
In this paper, the problem of semantic place cate-gorization in mobile robotics is addressed by considering a time-based probabilistic approach called Dynamic Bayesian Mixture Model (DBMM), which is an improved variation of the Dynamic Bayesian Network (DBN). More specifically , multi-class semantic classification is performed by a DBMM composed of...
Conference Paper
Robotic walkers are assistive robotic devices that provide mobility assistance to frail or elderly users, also providing a significant potential for lower limb rehabilitation. This paper presents the ISR-AIWALKER robotic walker, an instrumented robotic platform that has been developed to conduct research on rehabilitation and assistive robotics. Th...
Conference Paper
Full-text available
High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the low-resolution of a LIDAR. This paper, on the other hand, introduc...
Article
Full-text available
In this paper, the problem of semantic place categorization in mobile robotics is addressed by considering a time-based probabilistic approach called Dynamic Bayesian Mixture Model (DBMM), which is an improved variation of the Dynamic Bayesian Network (DBN). More specifically, multi-class semantic classification is performed by a DBMM composed of a...
Article
Full-text available
High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the low-resolution of a LIDAR. This paper, on the other hand, introduc...
Article
Full-text available
Artificial perception, in the context of autonomous driving, is the process by which an intelligent system translates sensory data into an effective model of the environment surrounding a vehicle. In this paper, and considering data from a 3D-LIDAR mounted onboard an intelligent vehicle, a 3D perception system based on voxels and planes is proposed...
Conference Paper
Full-text available
In this paper a spatial interpolation approach, based on polar-grid representation and Kriging predictor, is proposed for 3D point cloud sampling. Discrete grid representation is a widely used technique because of its simplicity and capacity of providing an efficient and compact representation, allowing subsequent applications such as artificial pe...
Conference Paper
Full-text available
In this work, we present a human-centered robot application in the scope of daily activity recognition towards robot-assisted living. Our approach consists of a probabilistic ensemble of classifiers as a dynamic mixture model considering the Bayesian probability, where each base classifier contributes to the inference in proportion to its posterior...
Article
Full-text available
This paper proposes a road detection approach based solely on dense 3D-LIDAR data. The approach is built up of four stages: (1) 3D-LIDAR points are projected to a 2D reference plane; then, (2) dense height maps are computed using an upsampling method; (3) applying a sliding-window technique in the upsampled maps, probability distributions of neighb...
Conference Paper
Full-text available
Why is pedestrian detection still very challenging in realistic scenes? How much would a successful solution to monocular depth inference aid pedestrian detection? In order to answer these questions we trained a state-of-the-art deformable parts detector using different configurations of optical images and their associated 3D point clouds, in conju...
Conference Paper
Full-text available
In this work, we propose an approach that relies on cues from depth perception from RGB-D images, where features related to human body motion (3D skeleton features) are used on multiple learning classifiers in order to recognize human activities on a benchmark dataset. A Dynamic Bayesian Mixture Model (DBMM) is designed to combine multiple classifi...
Conference Paper
Full-text available
Advances in autonomous navigation, safety, and natural-landmark based localization, are among the key objectives in the development of the next generation of autonomous vehicles, to be deployed in manufacturing and semi-structured environments. In this paper, autonomous navigation and collision detection will be focused, where it is proposed a nove...
Article
Full-text available
This work presents a method for simultaneous segmentation and modeling of objects, detected in range data gathered by a laserscanner mounted on-board ground-robotic platforms. Superquadrics are used as model for both segmentation and object shape fitting. The proposed method, which we name Simultaneous Segmentation and Superquadrics Fitting (S3F),...
Article
Full-text available
The cascade classifier is a usual approach in object detection based on vision, since it successively rejects negative occurrences, e.g., background images, in a cascade structure, keeping the processing time suitable for on-the-fly applications. On the other hand, similar to other classifier ensembles, cascade classifiers are likely to have high V...
Article
Full-text available
This paper presents an experimental study on pedestrian classification and detection in far infrared (FIR) images. The study includes an in-depth evaluation of several combinations of features and classifiers, which include features previously used for daylight scenarios, as well as a new descriptor (HOPE – Histograms of Oriented Phase Energy), spe...
Article
Full-text available
In this work, a context-based multisensor system, applied to pedestrian detection in urban environments, is presented. The proposed system comprises three main processing modules: (i) a LIDAR-based module acting as the primary object detector, (ii) a module which supplies the system with contextual information obtained from a semantic map of the ro...
Conference Paper
Full-text available
Many robotic systems combine cameras with Laser Rangefinders (LRF) for simultaneously achieving multi-purpose visual sensing and accurate depth recovery. Employing a single sensor modality for accomplishing both goals is an appealing proposition because it enables substantial savings in equipment, and tends to decrease the overall complexity of the...
Conference Paper
Full-text available
Pedestrian detection systems constitute an important field of research and development in computer vision, specially when applied in protection/safety systems in urban scenarios due to their direct impact in the society, specifically in terms of traffic casualties. In order to face such challenge, this work exploits some developments on statistical...
Conference Paper
Full-text available
In this paper we present a multistage method applied in pedestrian detection using information from a LIDAR and a monocular-camera mounted on an electric vehicle driving in urban scenarios. The proposed method is a cascade of classifiers trained in two subsets of features, one with laser-based features and the other with a set of image-based featur...
Conference Paper
Full-text available
Reliable detection and classification of vulnerable road users constitute a critical issue on safety/protection systems for intelligent vehicles driving in urban zones. In this subject, most of the perception systems have LIDAR and/or radar as primary detection modules and vision-based systems for object classification. This work, on the other hand...
Article
Full-text available
A perception system for pedestrian detection in urban scenarios using information from a LIDAR and a single camera is presented. Two sensor fusion architectures are described, a centralized and a decentralized one. In the former, the fusion process occurs at the feature level, i.e., features from LIDAR and vision spaces are combined in a single vec...
Conference Paper
Full-text available
This paper presents a sensorial-cooperative architecture to detect, track and classify entities in semi-structured outdoor scenarios for intelligent vehicles. In order to accomplish this task, information provided by in-vehicle Lidar and monocular vision is used. The detection and tracking phases are performed in the laser space, and the object cla...
Conference Paper
Full-text available
Intelligent vehicles need reliable information about the environment in order to operate with total safety. In this paper we propose a flexible multi-module architecture for a multi-target detection and tracking system (MTDTS) complemented with a Bayesian object classification layer based on finite Gaussian mixture models (GMM). The GMM parameters...