1,721,179 research outputs found
Motion-aware temporal median filtering for robust background estimation
Full text linkGiven an input video sequence, whose frames depict the same scene at different times, the background estimation problem consists in generating a model of the scene background, free of the foreground elements occluding it. In this thesis, we are interested in a unimodal variant of this problem, whose resulting background model is a single image. To date, background estimation, that is often confused with background subtraction, has been marginally explored. The simplest method, called the temporal median filter, consists in computing the median pixel value in each pixel position. While it produces excellent results for basic scenes, it relies on the strong assumption that the background is observed more than half of the time in each pixel position. As this assumption is rarely met in complex video sequences, such as the ones containing a large amount of foreground elements, or subject to background motion and/or intermittent motion, the temporal median filter usually fails to generate a clean background image for realistic scenes.
In this thesis, we propose LaBGen, a new background estimation method built upon the temporal median filter while improving its robustness. It is mainly based on the idea that, if we had an information indicating for a given frame which pixels are in motion, we could filter out foreground pixel values considered during median computations, and relax the need to observe the background more than half of the time. After describing and justifying the design of LaBGen, we test the relevance of the motion detection performed by different popular background subtraction algorithms for our task. It turns out that the simple frame difference algorithm enables LaBGen to achieve its best performance. For this reason, we integrate this algorithm in LaBGen-P, another of our methods that improves LaBGen by avoiding some artifacts that it sometimes introduces into the generated background images. In addition to achieving a better performance than many sophisticated state-of-the-art methods, while having a much lower run time, LaBGen and LaBGen-P were ranked first in the international IEEE Scene Background Modeling Contest organized in 2016.
Thereafter, we study the relationship between the performance of motion detection, and the performance of our methods. Although we do not find an obvious correlation between both, we make the assumption upon previous experimental evidence that a temporally memoryless motion detection is the most relevant for LaBGen. Unlike a temporally aware motion detection that does not ignore the temporal information history, a temporally memoryless approach detects motion between two frames without relying on additional past frames. Based on this hypothesis, we design LaBGen-OF, a variant of LaBGen that leverages temporally memoryless optical flow algorithms (i.e. that determine the displacement of each pixel from one frame to another). A consecutive performance study highlights that LaBGen-OF always performs better than LaBGen embedded with different temporally aware motion detection algorithms. Even better, LaBGen-OF is ranked number 2 over 30 on the popular SBMnet background estimation dataset, and takes the lead in 2 categories over 8.
These promising results lead us to push the temporally memoryless even further. For this purpose, we propose two homemade intra-frame motion detection algorithms that leverage semantic segmentation (i.e. a segmentation indicating which object is currently depicted in a given pixel) to determine the possibility of observing motion from spatial information only. Afterwards, we integrate those algorithms into a new variant of LaBGen-P, called LaBGen-P-Semantic, and determine their relevance to our task. In addition to validate the use of intra-frame motion detection algorithms, a performance evaluation shows that LaBGen-P-Semantic performs better than LaBGen and LaBGen-P, and takes the lead in 3 other SBMnet categories.
Finally, an additional contribution of this thesis lies in the performance evaluation subfield. Indeed, as most evaluation methodologies and datasets are used blindly without ever being questioned, we describe and analyze them in depth in order to determine whether such trust is justified. It turns out that some evaluation tools are mathematically inaccurate, and/or redundant, and/or not well correlated with what the visual perception of a human considers as an acceptable background image. In addition, the public implementations of some of those tools return erroneous results. We thus revisit the performance evaluation paradigms used in background estimation, review the problems, and provide possible solutions. Furthermore, as no methodology to assess online background estimation methods (i.e. generating a background image after each frame of the input video sequence) has been proposed to date, we provide insights into how to evaluate such methods. Our proposal is based on paradigms borrowed from the video quality assessment field, and a proof of concept shows that it is able to discriminate the performance of two different online methods that traditional evaluation tools consider to be identical
Understanding the Interplay Between the Driver, the Vehicle, and the Environment for Adapting Driving Automation
No full textSince the invention of the automobile at the end of the 19th century, driving has continually evolved. From rudimentary vehicles consisting of little more than an engine, a seat, and wheels, today's cars have become technological marvels equipped with hundreds of sensors and intelligent algorithms. Consequently, driving has transformed into a complex activity involving multiple interacting entities: the human driver, the vehicle automation, and the driving environment.
Despite major technological progress, how to best combine driving automation and driver monitoring systems to dynamically allocate driving tasks for safety and comfort purposes remains a key research challenge. Achieving such adaptive driving automation requires a deep understanding of the interplay between the driver, the vehicle, and the environment.
Part I describes the context of this thesis, tracing the evolution of the automobile from mechanical innovation to the integration of driving automation and driver monitoring. It also reviews the state of the art in driver monitoring, with a particular focus on mental workload and distraction.
Part II presents human studies conducted in a driving simulator to examine whether drivers' cognitive distraction and the complexity of the driving environment influence reliance on Adaptive Cruise Control (ACC) and whether such reliance affects driving performance.
Furthermore, it investigates whether and how physiological and behavioral indicators reflect drivers' cognitive distraction under varying traffic conditions and ACC use. Specifically, three Electrodermal Activity (EDA)-based and three gaze-based indicators were analyzed.
Part III introduces engineering approaches for analyzing the driving environment. In particular, it presents a novel Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup in which computer vision models adapt on the fly to a dynamic environment divided into cells. To evaluate a method derived from this setup, a new multi-stream, large-scale synthetic semantic segmentation dataset, called DADE, was released.
In addition, a probabilistic approach to domain characterization is proposed, where domains are characterized as probability distributions. A method is presented for predicting the likelihood of different weather conditions from images captured by vehicle-mounted cameras.
Part IV proposes a closed-loop framework, called DEV, for risk-aware adaptive driving automation that captures the dynamic interplay between the driver, the environment, and the vehicle. The thesis concludes with insights and future perspectives stemming from this research, aimed at fostering safer and more adaptive human–automation cooperation
Application of deep learning techniques for exoplanet detection in high contrast imaging
Full text linkThe direct imaging of exoplanets through 10-m class ground-based telescopes
is now a reality of modern astrophysics. Reaching this milestone is the re-
sult of significant advances in the field of high-contrast imaging, marked by
the development of dedicated telescope instrumentation, including extreme
adaptive optics and advanced coronagraphy. However, despite these advance-
ments, residual optical aberrations persist, generating quasi-static speckles in
the image field of view, whose shape and intensity are similar to potential
companions. Over the past two decades, numerous image post-processing
techniques have been proposed to further eliminate this residual speckle
noise and detect the planet signature. Among these techniques, supervised
deep learning was introduced through the SODINN detection algorithm, a
binary classifier that uses a convolutional neural network to learn a model
that distinguishes between noise and the point-like source in the image.
The recent Exoplanet Imaging Data Challenge (EIDC) served as a platform for
benchmarking SODINN and other image post-processing techniques. The
results revealed that SODINN tends to produce a notable number of false
positives, while the most effective techniques rely on mechanisms to capture
local image noise dependencies. Building upon these findings, this thesis
aims to improve the detection performance of SODINN through capturing
new local noise dependencies. Through the development of new statistical
methods, we explore the possibility to identify different noise regimes across
the angular differential imaging processed image and adapt the SODINN
neural network, and its training process, to work under this stratification
strategy. This model adaptation leads to the creation of a new detection algo-
rithm, called NA-SODINN. Through ROC analyses, NA-SODINN undergoes
rigorous testing against its predecessor, demonstrating an improved balance
between sensitivity and specificity in detection. Furthermore, NA-SODINN
is benchmarked against the full set of detection algorithms submitted in
the EIDC. The results indicate that NA-SODINN either matches or exceeds
the performance of the most powerful detection algorithms. NA-SODINN
is finally used to reanalyze a filtered sample from the recent SHINE exo-
planet survey, providing valuable insights and potential exoplanet candidates.
Throughout the supervised machine learning case, this study illustrates and
reinforces the importance of adapting the task of detection to the local content
of processed images.Application of deep learning techniques for exoplanet detection in high contrast imagin
Design, performance analysis, and implementation of a positioning system for autonomous mobile robots
Full text linkPositioning is a fundamental issue in mobile robot applications, and it can be achieved in
multiple ways. Among these methods, triangulation based on angle measurements is widely
used, robust, and flexible. In this thesis, we present an original beacon-based angle measurement system, an original triangulation algorithm, and a calibration method, which are
parts of an absolute robot positioning system in the 2D plane. Also, we develop a theoretical
model, useful for evaluating the performance of our system.
In the first part, we present the hardware system, named BeAMS, which introduces several
innovations. A simple infrared receiver is the main sensor for the angle measurements, and
the beacons are common infrared LEDs emitting an On-Off Keying signal containing the
beacon ID. Furthermore, the system does not require an additional synchronization channel
between the beacons and the robot. BeAMS introduces a new mechanism to measure angles:
it detects a beacon when it enters and leaves an angular window. This allows the sensor to
analyze the temporal evolution of the received signal inside the angular window. In our case,
this feature is used to code the beacon ID. Then, a theoretical framework for a thorough
performance analysis of BeAMS is provided. We establish the upper bound of the variance
and its exact evolution as a function of the angular window. Finally, we validate our theory
by means of simulated and experimental results.
The second part of the thesis is concerned with triangulation algorithms. Most triangulation algorithms proposed so far have major limitations. For example, some of them need a
particular beacon ordering, have blind spots, or only work within the triangle defined by the
three beacons. More reliable methods exist, but they have an increasing complexity or they
require to handle certain spatial arrangements separately. Therefore, we have designed our
own triangulation algorithm, named ToTal, that natively works in the whole plane, and for
any beacon ordering. We also provide a comprehensive comparison between other algorithms,
and benchmarks show that our algorithm is faster and simpler than similar algorithms. In
addition to its inherent efficiency, our algorithm provides a useful and unique reliability measure, assessable anywhere in the plane, which can be used to identify pathological cases, or
as a validation gate in data fusion algorithms.
Finally, in the last part, we concentrate on the biases that affect the angle measurements.
We show that there are four sources of errors (or biases) resulting in inaccuracies in the
computed positions. Then, we establish a model of these errors, and we propose a complete
calibration procedure in order to reduce the final bias. Based on the results obtained with
our calibration setup, the angular RMS error of BeAMS has been evaluated to 0.4 deg without calibration, and to 0.27 deg, after the calibration procedure. Even for the uncalibrated
hardware, BeAMS has a better performance than other prototypes found in the literature
and, when the system is calibrated, BeAMS is close to state of the art commercial systems
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
An anonymised longitudinal GPS location dataset to understand changes in activity-travel behaviour between pre- and post-COVID periods
Full text linkpeer reviewedCollecting GPS data using mobile devices is essential to understanding human mobility. However, getting this type of data is tricky because of some specific features of mobile operating systems, the high-power consumption of mobile devices, and users’ privacy concerns. Therefore, data of this kind are rarely publicly available for scientific purposes, while private companies that own the data are often reluctant to share it. Here we present a large anonymous longitudinal dataset of Activity Point Location (APL) generated from mobile devices’ GPS tracking. The GPS data were collected by using the Google Location History (GLH), accessible in the Google Maps application. Our dataset, named AnLoCOV hereafter, includes anonymised data from 338 persons with corresponding socio-demographics over approximately ten years (2012–2022), thus covering pre- and post-COVID periods, and calculates over 2 million weekly-classified APL extracted from approximately 16 million GPS tracking points in Ecuador. Furthermore, we made our models publicly available to enable advanced analysis of human mobility and activity spaces based on the collected datasets
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
