Yes / The Atkinson-Shiffrin modal model forms the foundation of our understanding of human memory. It consists of three stores (Sensory Memory (SM), also called iconic memory, Short-Term Memory (STM), and Long-Term Memory (LTM)), each tuned to a different time-scale. Since its inception, the STM and LTM components of the modal model have undergone significant modifications, while SM has remained largely unchanged, representing a large capacity system funneling information into STM. In the laboratory, visual memory is usually tested by presenting a brief static stimulus and, after a delay, asking observers to report some aspect of the stimulus. However, under ecological viewing conditions, our visual system receives a continuous stream of inputs, which is segmented into distinct spatio-temporal segments, called events. Events are further segmented into event-segments. Here we show that SM is not an unspecific general funnel to STM but is allocated exclusively to the current event-segment. We used a Multiple-Object Tracking (MOT) paradigm in which observers were presented with disks moving in different directions, along bi-linear trajectories, i.e., linear trajectories, with a single deviation in direction at the mid-point of each trajectory. The synchronized deviation of all of the trajectories produced an event stimulus consisting of two event-segments. Observers reported the pre-deviation or the post-deviation directions of the trajectories. By analyzing observers' responses in partial- and full-report conditions, we investigated the involvement of SM for the two event-segments. The hallmarks of SM hold only for the current event segment. As the large capacity SM stores only items involved in the current event-segment, the need for event-tagging in SM is eliminated, speeding up processing in active vision. By characterizing how memory systems are interfaced with ecological events, this new model extends the Atkinson-Shiffrin model by specifying how events are stored in the first stage of multi-store memory systems.

Emergency landing is a critical safety mechanism for aerial vehicles. Commercial aircraft have triply-redundant systems that greatly increase the probability that the pilot will be able to land the aircraft at a designated airfield in the event of an emergency. In general aviation, the chances of always reaching a designated airfield are lower, but the successful pilot might use landmarks and other visual information to safely land in unprepared locations. For small unmanned aircraft systems (sUAS), triply- or even doubly-redundant systems are unlikely due to size, weight, and power constraints. Additionally, there is a growing demand for beyond visual line of sight (BVLOS) operations, where an sUAS operator would be unable to guide the vehicle safely to the ground. This thesis presents a machine vision-based approach to emergency landing for small unmanned aircraft systems. In the event of an emergency, the vehicle uses a pre-compiled database of potential landing sites to select the most accessible location to land based on vehicle health. Because it is impossible to know the current state of any ground environment, a camera is used for real-time visual feedback. Using the recently developed Recursive-RANSAC algorithm, an arbitrary number of moving ground obstacles can be visually detected and tracked. If obstacles are present in the selected ditch site, the emergency landing system chooses a new ditch site to mitigate risk. This system is called Safe2Ditch.

Video surveillance has long been in use to monitor security sensitive areas such as banks, department stores, crowded public places and borders. The rise in computer speed, availability of cheap large-capacity storage devices and high speed network infrastructure enabled the way for cheaper, multi sensor video surveillance systems. In this thesis, the problem of tracking multiple targets with multiple cameras has been discussed. Cameras have been located so that they have overlapping fields of vision. A dynamic background-modeling algorithm is described for segmenting moving objects from the background, which is capable of adapting to dynamic scene changes and periodic motion, such as illumination change and swaying of trees. After segmentation of foreground scene, the objects to be tracked have been acquired by morphological operations and connected component analysis. For the purpose of tracking the moving objects, an active contour model (snakes) is one of the approaches, in addition to a Kalman tracker. As the main tracking algorithm, a rule based tracker has been developed first for a single camera, and then extended to multiple cameras. Results of used and proposed methods are given in detail.

An autonomous vehicle is a complex system that requires a good perception of the surrounding environment to operate safely. One part of that is multiple object tracking, which is an essential component in camera-based perception whose responsibility is to estimate object motion from a sequence of images. This requires an association problem to be solved where newly estimated object positions are mapped to previously predicted trajectories, for which different solution strategies exist.  In this work, a multiple hypothesis tracking algorithm is implemented. The purpose is to demonstrate that measurement associations are improved compared to less compute-intensive alternatives. It was shown that the implemented algorithm performed 13 percent better than an intersection over union tracker when evaluated using a standard evaluation metric. Furthermore, this work also investigates the usage of abstraction layers to accelerate time-critical parallel operations on the GPU. It was found that the execution time of the tracking algorithm could be reduced by 42 percent by replacing four functions with implementations written in the purely functional array language Futhark. Finally, it was shown that a GPU code abstraction layer can reduce the knowledge barrier required to write efficient CUDA kernels.

Les interfaces cerveau-machine (ICMs) nous offrent un moyen de fermer la boucle entre notre cerveau et le monde de la technologie numérique. Cela ouvre la porte à une pléthore de nouvelles applications où nous utilisons directement le cerveau comme entrée. S’il est facile de voir le potentiel, il est moins facile de trouver la bonne application avec les bons corrélats neuronaux pour construire un tel système en boucle fermée. Ici, nous explorons une tâche de suivi d’objets multiples en 3D, dans un contexte d’entraînement cognitif (3D-MOT). Notre capacité à suivre plusieurs objets dans un environnement dynamique nous permet d’effectuer des tâches quotidiennes telles que conduire, pratiquer des sports d’équipe et marcher dans un centre commercial achalandé. Malgré plus de trois décennies de littérature sur les tâches MOT, les mécanismes neuronaux sous- jacents restent mal compris. Ici, nous avons examiné les corrélats neuronaux via l’électroencéphalographie (EEG) et leurs changements au cours des trois phases d’une tâche de 3D-MOT, à savoir l’identification, le suivi et le rappel. Nous avons observé ce qui semble être un transfert entre l’attention et la de mémoire de travail lors du passage entre le suivi et le rappel. Nos résultats ont révélé une forte inhibition des fréquences delta et thêta de la région frontale lors du suivi, suivie d’une forte (ré)activation de ces mêmes fréquences lors du rappel. Nos résultats ont également montré une activité de retard contralatérale (CDA en anglais), une activité négative soutenue dans l’hémisphère contralatérale aux positions des éléments visuels à suivre. Afin de déterminer si le CDA est un corrélat neuronal robuste pour les tâches de mémoire de travail visuelle, nous avons reproduit huit études liées au CDA avec un ensemble de données EEG accessible au public. Nous avons utilisé les données EEG brutes de ces huit études et les avons analysées avec le même pipeline de base pour extraire le CDA. Nous avons pu reproduire les résultats de chaque étude et montrer qu’avec un pipeline automatisé de base, nous pouvons extraire le CDA. Récemment, l’apprentissage profond (deep learning / DL en anglais) s’est révélé très prometteur pour aider à donner un sens aux signaux EEG en raison de sa capacité à apprendre de bonnes représentations à partir des données brutes. La question à savoir si l’apprentissage profond présente vraiment un avantage par rapport aux approches plus traditionnelles reste une question ouverte. Afin de répondre à cette question, nous avons examiné 154 articles appliquant le DL à l’EEG, publiés entre janvier 2010 et juillet 2018, et couvrant différents domaines d’application tels que l’épilepsie, le sommeil, les interfaces cerveau-machine et la surveillance cognitive et affective. Enfin, nous explorons la possibilité de fermer la boucle et de créer un ICM passif avec une tâche 3D-MOT. Nous classifions l’activité EEG pour prédire si une telle activité se produit pendant la phase de suivi ou de rappel de la tâche 3D-MOT. Nous avons également formé un classificateur pour les essais latéralisés afin de prédire si les cibles étaient présentées dans l’hémichamp gauche ou droit en utilisant l’activité EEG. Pour la classification de phase entre le suivi et le rappel, nous avons obtenu un 80% lors de l’entraînement d’un SVM sur plusieurs sujets en utilisant la puissance des bandes de fréquences thêta et delta des électrodes frontales. / Brain-computer interfaces (BCIs) offer us a way to close the loop between our brain and the digital world of technology. It opens the door for a plethora of new applications where we use the brain directly as an input. While it is easy to see the disruptive potential, it is less so easy to find the right application with the right neural correlates to build such closed-loop system. Here we explore closing the loop during a cognitive training 3D multiple object tracking task (3D-MOT). Our ability to track multiple objects in a dynamic environment enables us to perform everyday tasks such as driving, playing team sports, and walking in a crowded mall. Despite more than three decades of literature on MOT tasks, the underlying and intertwined neural mechanisms remain poorly understood. Here we looked at the electroencephalography (EEG) neural correlates and their changes across the three phases of a 3D-MOT task, namely identification, tracking and recall. We observed what seems to be a handoff between focused attention and working memory processes when going from tracking to recall. Our findings revealed a strong inhibition in delta and theta frequencies from the frontal region during tracking, followed by a strong (re)activation of these same frequencies during recall. Our results also showed contralateral delay activity (CDA), a sustained negativity over the hemisphere contralateral to the positions of visual items to be remembered. In order to investigate if the CDA is a robust neural correlate for visual working memory (VWM) tasks, we reproduced eight CDA-related studies with a publicly accessible EEG dataset. We used the raw EEG data from these eight studies and analysed all of them with the same basic pipeline to extract CDA. We were able to reproduce the results from all the studies and show that with a basic automated EEG pipeline we can extract a clear CDA signal. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. In order to address such question, we reviewed 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring. Finally, we explore the potential for closing the loop and creating a passive BCI with a 3D-MOT task. We classify EEG activity to predict if such activity is happening during the tracking or the recall phase of the 3D-MOT task. We also trained a classifier for lateralized trials to predict if the targets were presented on the left or right hemifield using EEG brain activity. For the phase classification between tracking and recall, we obtained 80% accuracy when training a SVM across subjects using the theta and delta frequency band power from the frontal electrodes and 83% accuracy when training within subjects.

Multiple-object tracking is a task within the field of computer vision. As the name stated, the task consists of tracking multiple objects in the video, an algorithm that completes such task are called trackers. Many of the existing trackers require supervision, meaning that the location and identity of each object which appears in the training data must be labeled. The procedure of generating these labels, usually through manual annotation of video material, is highly resource-consuming. On the other hand, different from well-known labeled Multiple-object tracking datasets, there exist a massive amount of unlabeled video with different objects, environments, and video specifications. Using such unlabeled video can therefore contribute to cheaper and more diverse datasets. There have been numerous attempts on unsupervised object tracking, but most rely on evaluating the tracker performance on a labeled dataset. The reason behind this is the lack of an evaluation method for unlabeled datasets. This project explores unsupervised pedestrian tracking on video taken from a stationary camera over a long duration. On top of a simple baseline tracker, two methods are proposed to extend the baseline to increase its performance. We then propose an evaluation method that works for unlabeled video, which we use to evaluate the proposed methods. The evaluation method consists of the trajectory completion rate and the number of ID switches. The trajectory completion rate is a novel metric proposed for pedestrian tracking. Pedestrians generally enter and exit the scene for video taken by a stationary camera in specific locations. We define a complete trajectory as a trajectory that goes from one area to another. The completion rate is calculated by the number of complete trajectories over all trajectories. Results showed that the two proposed methods had increased the trajectory completion rate on top of the original baseline performance. Moreover, both proposed methods did so without significantly increasing the number of ID switches. / Spårning av flera objekt är en uppgift inom området datorseende. Som namnet angav består uppgiften av att spåra flera objekt i videon, en algoritm som slutför en sådan uppgift kallas trackers. Många av de befintliga spårarna kräver övervakning, vilket innebär att platsen och identiteten för varje objekt som visas i träningsdata måste märkas. Proceduren för att generera dessa etiketter, vanligtvis genom manuell anteckning av videomaterial, är mycket resurskrävande. Å andra sidan, till skillnad från välkända märkta uppsättningar för spårning av flera objekt, finns det en enorm mängd omärkt video med olika objekt, miljöer och videospecifikationer. Att använda sådan omärkt video kan därför bidra till billigare och mer varierande datauppsättningar. Det har gjorts många försök med oövervakad objektspårning, men de flesta förlitar sig på att utvärdera spårningsprestandan på en märkt dataset. Anledningen till detta är avsaknaden av en utvärderingsmetod för omärkta datamängder. Detta projekt utforskar oövervakad fotgängarspårning på video som tagits från en stillastående kamera under lång tid. Utöver en enkel baslinjespårare föreslås två metoder för att utöka baslinjen för att öka dess prestanda. Vi föreslår sedan en utvärderingsmetod som fungerar för omärkt video, som vi använder för att utvärdera de föreslagna metoderna. Utvärderingsmetoden består av banans slutförandegrad och antalet ID-växlar. Banans slutförandegrad är ett nytt mått som föreslås för spårning av fotgängare. Fotgängare går vanligtvis in och lämnar scenen för video tagna med en stillastående kamera på specifika platser. Vi definierar en komplett bana som en bana som går från ett område till ett annat. Färdigställandegraden beräknas av antalet kompletta banor över alla banor. Resultaten visade att de två föreslagna metoderna hade ökat graden av fullbordande av banan utöver den ursprungliga baslinjeprestandan. Dessutom gjorde båda de föreslagna metoderna det utan att nämnvärt öka antalet ID-växlar.

Multiple object tracking (MOT) is the task of detecting multiple objects in a scene and associating detections over time to form tracks. It is essential for many scene understanding tasks like surveillance, robotics and autonomous driving. Nowadays, the dominating tracking pipeline is to first detect all individual objects in a scene followed by a separate data association step, also known as tracking-by-detection. Recently, methods doing simultaneous detection and tracking has emerged, combining the task of detection and tracking into one single framework. In this project, we analyse performance of multiple object tracking algorithms belonging to both tracking categories. The goal is to examine strengths, weaknesses, and real-time capability of different tracking approaches in order to understand their suitability in different applications. Results show that a tracking-by-detection system with Scaled-YOLOv4 and SORT achieves 46.8% accuracy at over 28 frames per second (FPS) on Nvidia GTX 1080. By reducing the input resolution, inference speed is increased to almost 50 FPS, making it well suitable for real-time application. The addition of a deep re-identification CNN reduces the number of identity switches by 47%. However, association speed drops as low as 14 FPS for densely populated scenes. This indicates that re-identification CNNs may be impractical for safety critical applications like autonomous driving, especially in urban environments. Simultaneous detection and tracking results suggests an increased tracking robustness. The removal of a complex data association strategy improves robustness with respect to extended modules like re-identification. This indicates that the inherent simplicity in the simultaneous detection and tracking paradigm can provide robust baseline trackers for a variety of applications. We note that further research is required to strengthen this notion. / Multipel objektspårning handlar om att detektera alla objekt i bilder och associera dem över tid för att bilda spår. Det är ett viktigt ämne inom datorseende för flera applikationer, däribland kameraövervakning, robotik och självkörande fordon. Idag är det dominerande tillvägagångsättet inom objektspårning att först detektera alla objekt och sedan associera dem i ett separat steg, också kallat spårning-genom-detektion. På senare tid har det framkommit nya metoder som detekterar och spårar samtidigt. I detta projekt analyserar vi prestanda av metoder som tillämpar båda tillvägagångssätt. Målet med projektet är att undersöka styrkor, svagheter och hur väl metoderna lämpar sig för att användas i realtid. Detta för att förstå hur olika objektspårare kan anpassas till olika praktiska applikationer. Resultaten visar att ett system som tillämpar spårning-genom-detektion med Scaled-YOLOv4 och SORT, uppnår 46.8% noggrannhet med en hastighet på över 28 bildrutor per sekund. Detta på en Nvidia GTX 1080. Genom att minska bildupplösningen når hastigheten nästan hela vägen upp till 50 bildrutor per sekund, vilket gör systemet väl lämpat för realtidsapplikation. Genom att addera ett djupt nätverk för återidentifiering minskar antalet identitetsbyten med 47%. Samtidigt minskar också hastigheten för spårning till 14 bildrutor per sekund i välbefolkade miljöer. Detta indikerar att djupa nätverk för återidentifiering inte lämpar sig för säkerhetskritiska applikationer såsom självkörande fordon. Särskilt i urbana miljöer. Resultat för system som detekterar och spårar samtidigt antyder att de är mer robusta. Genom att ta bort komplexa strategier för associering blir systemen robusta mot ytterligare moduler såsom återidentifiering. Det ger en indikation på att den inneboende enkelheten i dessa system resulterar i objektspårare som kan fungera som grunder i många olika applikationer. Vi noterar att ytterligare forsking behövs för att styrka denna idé.

No description available.

L’intralogistique (ou logistique interne) s’intéresse au traitement et à l’optimisation des flux physiques au sein des entrepôts, centres de distribution et usines. Les systèmes de manutention automatisés sont au cœur de la logistique interne de plusieurs industries comme le commerce en ligne, la messagerie postale, la grande distribution, l’industrie manufacturière, le transport aéroportuaire, etc. Ces équipements composés de lignes de convoyage haute cadence permettent un transport sûr et fiable d’un volume considérable de biens et de marchandises tout en réduisant les coûts.L’automatisation de l’acheminement des flux physiques par les systèmes de manutention repose sur l’identification et le suivi en temps réel des charges transportées. Dans cette thèse, nous explorons une solution de suivi qui emploie un réseau de caméras intelligentes à champs recouvrants. L’objectif final étant de fournir l’information de suivi sur les charges transportées pour le pilotage d’un système de manutention.Le suivi d’objets est un problème fondamental de la vision par ordinateur qui a de nombreuses applications comme la vidéosurveillance, la robotique, les voitures autonomes, etc. Nous avons intégré plusieurs briques de base issues de la vidéosurveillance et traditionnellement appliquées aux scènes de surveillance automobile ou de surveillance des activités humaines pour constituer une chaine de suivi de référence. Cette chaine d’analyse vidéo étalon nous a permis de caractériser des hypothèses propres au convoyage d’objet. Nous proposons dans cette thèse d’incorporer cette connaissance métier dans la chaine de suivi pour en améliorer les performances. Nous avons, notamment pris en compte, dans l’étape de segmentation des images, le fait que les objets doivent pouvoir s’arrêter sans pour autant être intégrés aux modèles d’arrière-plan. Nous avons également exploité la régularité des trajectoires des objets convoyés dans les installations, permettant d’améliorer les modèles prédictifs de la position et de la vitesse des objets, dans les étapes de suivi. Enfin, nous avons intégré des contraintes de stricte monotonie dans l’ordre des colis sur le convoyeur, contraintes qui n’existent pas dans les scènes généralistes, pour ré-identifier les objets dans les situations où ils sont proches des eux les autres.Nous nous sommes par ailleurs attelés à un problème pratique d’optimisation des performances sur l’architecture multi-cœurs couplée aux caméras intelligentes. Dans ce cadre, nous avons a mis en place un apprentissage dynamique de la zone de l’image contenant le convoyeur. Cette zone d’intérêt nous a permis de limiter la mise à jour du modèle de fond à cette seule zone. Nous avons, par la suite, proposé une stratégie de parallélisation qui partitionne de manière adaptative cette région d’intérêt de l’image, afin d’équilibrer au mieux la charge de travail entre les différents cœurs de l’architecture des caméras intelligentes.Nous avons également traité la problématique du suivi sur plusieurs caméras. Nous avons proposé une approche basée sur un système de composition d’évènements. Cette approche nous a permis de fusionner les données de suivi local pour former les trajectoires globales des colis, tout en intégrant des informations issues du processus métier, par exemple la saisie de l’information de destination par des opérateurs sur un terminal avant la dépose des colis. Nous avons validé cette approche sur un système de manutention mis en place dans un centre de tri postal de grande envergure. Le réseau de caméras déployé est composé de 32 caméras qui assurent le suivi de plus de 400.000 colis/jour sur des lignes de dépose. Le taux d’erreur du suivi obtenu est inférieur à 1 colis sur 1000 (0,1%). / Intralogistics (or internal logistics) focuses on the management and optimization of internal production and distribution processes within warehouses, distribution centers, and factories. Automated handling systems play a crucial role in the internal logistics of several industries such as e-commerce, postal messaging, retail, manufacturing, airport transport, etc. These systems are composed by multiple high-speed conveyor lines that provide safe and reliable transportation of a large volume of goods and merchandise while reducing costs.The automation of the conveying process relies on the identification and the real-time tracking of the transported loads. In this thesis, we designed a tracking solution that employs a network of smart cameras with an overlapping field of view. The goal is to provide tracking information to control an automated handling system.Multiple object tracking is a fundamental problem of computer vision that has many applications such as video surveillance, robotics, autonomous cars, etc. We integrated several building blocks traditionally applied to traffic surveillance or human activities monitoring to constitute a tracking pipeline. We used this baseline tracking pipeline to characterize contextual scene information proper to the conveying scenario. We integrated this contextual information to the tracking pipeline to enhance the performance. In particular, we took into account the state of moving objects that become stationary in the background subtraction step to prevent their absorption to the background model. We have also exploited the regularity of objects trajectory to enhance the motion model associated with the tracked objects. Finally, we integrated the precedence ordering constraint among the conveyed object to reidentify them when they are close to each other.We have also tackled practical problems related to the optimization the execution of the proposed tracking problem in the multi-core architectures of smart cameras. In particular, we proposed a dynamic learning process that extracts the region of the image that corresponds to the conveyor lines. We reduced the number of the processed pixel by restricting the processing to this region of interest. We also proposed a parallelization strategy that adaptively partitions this region of interest of the image, in order to balance the workload between the different cores of the smart cameras.Finally, we proposed a multiple cameras tracking algorithms based on event composition. This approach fuses the local tracking generated by the smart cameras to form global object trajectories and information from third party systems such as the destination of the object entered by operators on a terminal. We validated the proposed approach for the control of a sorting system deployed in a postal distribution warehouse. A network of cameras composed of 32 cameras tracks more than 400.000 parcel/day in injections lines. The tracking error rate is less than 1 parcel in a 1000 (0.1%).

This thesis proposes a system for extraction of vehicle trajectories from aerial video data for traffic analysis. The system is designed to analyse video sequence of a single traffic scene captured by an action camera mounted on an arbitrary UAV flying at the altitudes of approximately 150 m. Each video frame is geo-registered using visual correspondence of extracted ORB features. For the detection of vehicles, MB-LBP classifier cascade is deployed, with additional step of pre-filtering of detection candidates based on movement and scene context. Multi-object tracking is achieved by Bayesian bootstrap filter with an aid of the detection algorithm. The performance of the system was evaluated on three extensively annotated datasets. The results show that on the average, 92% of all extracted trajectories are corresponding to the reality. The system is already being used in the research to aid the process of design and analysis of road infrastructures.