RESUMO
Defect detection on rail lines is essential for ensuring safe and efficient transportation. Current image analysis methods with deep neural networks (DNNs) for defect detection often focus on the defects themselves while ignoring the related context. In this work, we propose a fusion model that combines both a targeted defect search and a context analysis, which is seen as a multimodal fusion task. Our model performs rule-based decision-level fusion, merging the confidence scores of multiple individual models to classify rail-line defects. We call the model "hybrid" in the sense that it is composed of supervised learning components and rule-based fusion. We first propose an improvement to existing vision-based defect detection methods by incorporating a convolutional block attention module (CBAM) in the you only look once (YOLO) versions 5 (YOLOv5) and 8 (YOLOv8) architectures for the detection of defects and contextual image elements. This attention module is applied at different detection scales. The domain-knowledge rules are applied to fuse the detection results. Our method demonstrates improvements over baseline models in vision-based defect detection. The model is open for the integration of modalities other than an image, e.g., sound and accelerometer data.
RESUMO
BACKGROUND: Prosthetic restoration of reach and grasp function after a trans-humeral amputation requires control of multiple distal degrees of freedom in elbow, wrist and fingers. However, such a high level of amputation reduces the amount of available myoelectric and kinematic information from the residual limb. METHODS: To overcome these limits, we added contextual information about the target's location and orientation such as can now be extracted from gaze tracking by computer vision tools. For the task of picking and placing a bottle in various positions and orientations in a 3D virtual scene, we trained artificial neural networks to predict postures of an intact subject's elbow, forearm and wrist (4 degrees of freedom) either solely from shoulder kinematics or with additional knowledge of the movement goal. Subjects then performed the same tasks in the virtual scene with distal joints predicted from the context-aware network. RESULTS: Average movement times of 1.22s were only slightly longer than the naturally controlled movements (0.82 s). When using a kinematic-only network, movement times were much longer (2.31s) and compensatory movements from trunk and shoulder were much larger. Integrating contextual information also gave rise to motor synergies closer to natural joint coordination. CONCLUSIONS: Although notable challenges remain before applying the proposed control scheme to a real-world prosthesis, our study shows that adding contextual information to command signals greatly improves prediction of distal joint angles for prosthetic control.
Assuntos
Membros Artificiais , Redes Neurais de Computação , Adulto , Braço , Fenômenos Biomecânicos , Mãos , Força da Mão , Humanos , Masculino , Pessoa de Meia-Idade , Movimento , OmbroRESUMO
PURPOSE: A new real-time MR-thermometry pipeline was developed to measure multiple temperature images per heartbeat with 1.6×1.6×3 mm3 spatial resolution. The method was evaluated on 10 healthy volunteers and during radiofrequency ablation (RFA) in sheep. METHODS: Multislice, electrocardiogram-triggered, echo-planar imaging was combined with parallel imaging, under free breathing conditions. In-plane respiratory motion was corrected on magnitude images by an optical flow algorithm. Motion-related susceptibility artifacts were compensated on phase images by an algorithm based on Principal Component Analysis. Correction of phase drift and temporal filter were included in the pipeline implemented in the Gadgetron framework. Contact electrograms were recorded simultaneously with MR thermometry by an MR-compatible ablation catheter. RESULTS: The temporal standard deviation of temperature in the left ventricle remained below 2 °C on each volunteer. In sheep, focal heated regions near the catheter tip were observed on temperature images (maximal temperature increase of 38 °C) during RFA, with contact electrograms of acceptable quality. Thermal lesion dimensions at gross pathology were in agreement with those observed on thermal dose images. CONCLUSION: This fully automated MR thermometry pipeline (five images/heartbeat) provides direct assessment of lesion formation in the heart during catheter-based RFA, which may improve treatment of cardiac arrhythmia by ablation. Magn Reson Med 77:673-683, 2017. © 2016 International Society for Magnetic Resonance in Medicine.
Assuntos
Ablação por Cateter/métodos , Coração/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Cirurgia Assistida por Computador/métodos , Termometria/métodos , Adulto , Algoritmos , Animais , Arritmias Cardíacas/cirurgia , Artefatos , Humanos , Processamento de Imagem Assistida por Computador , Planejamento da Radioterapia Assistida por Computador , Ovinos , Processamento de Sinais Assistido por ComputadorRESUMO
This work tackles the problem of automatically predicting the grasping intention of humans observing their environment, with eye-tracker glasses and video cameras recording the scene view. Our target application is the assistance to people with motor disabilities and potential cognitive impairments, using assistive robotics. Our proposal leverages the analysis of human attention captured in the form of gaze fixations recorded by an eye-tracker on the first person video, as the anticipation of prehension actions is a well studied and well known phenomenon. We propose a multi-task system that simultaneously addresses the prediction of human attention in the near future, and the anticipation of grasping actions. In our model, visual attention is modeled as a competitive process between a discrete set of states, each one associated to a well-known gaze movement pattern from visual psychology. We additionally consider an asymmetric multitask problem, where attention modeling is an auxiliary task that helps to regularize the learning process of the main action prediction task, and propose a constrained multi-task loss that naturally deals with this asymmetry. Our model shows superior performance than other losses for dynamic multi-task learning, current dominant deep architectures for general action forecasting and particularly-tailored models for predicting grasping intention. In particular, it provides state-of-the-art performance in three datasets for egocentric action anticipation, with an average precision of 0.569 and 0.524 in GITW and Sharon datasets, respectively, and an accuracy of 89.2% and a success rate of 51.7% in Invisible dataset.
RESUMO
The present paper proposes an implementation of a hybrid hardware-software system for the visual servoing of prosthetic arms. We focus on the most critical vision analysis part of the system. The prosthetic system comprises a glass-worn eye tracker and a video camera, and the task is to recognize the object to grasp. The lightweight architecture for gaze-driven object recognition has to be implemented as a wearable device with low power consumption (less than 5.6 W). The algorithmic chain comprises gaze fixations estimation and filtering, generation of candidates, and recognition, with two backbone convolutional neural networks (CNN). The time-consuming parts of the system, such as SIFT (Scale Invariant Feature Transform) detector and the backbone CNN feature extractor, are implemented in FPGA, and a new reduction layer is introduced in the object-recognition CNN to reduce the computational burden. The proposed implementation is compatible with the real-time control of the prosthetic arm.
RESUMO
There is an exponential increase in the range of digital products and devices promoting aging in place, in particular, devices aiming at preventing or detecting falls. However, their deployment is still limited and only few studies have been carried out in population-based settings owing to the technological challenges that remain to be overcome and the barriers that are specific to the users themselves, such as the generational digital divide and acceptability factors specific to the older adult population. To date, scarce studies consider these factors. To capitalize technological progress, the future step should be to better consider these factors and to deploy, in a broader and more ecological way, these technologies designed for older adults receiving home care to assess their effectiveness in real life.
RESUMO
BACKGROUND: Alzheimer's Disease (AD) is a neurodegenerative disease characterized by progressive loss of memory and general decline in cognitive functions. Multi-modal imaging such as structural MRI and DTI provide useful information for the classification of patients on the basis of brain biomarkers. Recently, CNN methods have emerged as powerful tools to improve classification using images. NEW METHOD: In this paper, we propose a transfer learning scheme using Convolutional Neural Networks (CNNs) to automatically classify brain scans focusing only on a small ROI: e.g. a few slices of the hippocampal region. The network's architecture is similar to a LeNet-like CNN upon which models are built and fused for AD stage classification diagnosis. We evaluated various types of transfer learning through the following mechanisms: (i) cross-modal (sMRI and DTI) and (ii) cross-domain transfer learning (using MNIST) (iii) a hybrid transfer learning of both types. RESULTS: Our method shows good performances even on small datasets and with a limited number of slices of small brain region. It increases accuracy with more than 5 points for the most difficult classification tasks, i.e., AD/MCI and MCI/NC. COMPARISON WITH EXISTING METHODS: Our methodology provides good accuracy scores for classification over a shallow convolutional network. Besides, we focused only on a small region; i.e., the hippocampal region, where few slices are selected to feed the network. Also, we used cross-modal transfer learning. CONCLUSIONS: Our proposed method is suitable for working with a shallow CNN network for low-resolution MRI and DTI scans. It yields to significant results even if the model is trained on small datasets, which is often the case in medical image analysis.
RESUMO
To this day, despite the increasing motor capability of robotic devices, elaborating efficient control strategies is still a key challenge in the field of humanoid robotic arms. In particular, providing a human "pilot" with efficient ways to drive such a robotic arm requires thorough testing prior to integration into a finished system. Additionally, when it is needed to preserve anatomical consistency between pilot and robot, such testing requires to employ devices showing human-like features. To fulfill this need for a biomimetic test platform, we present Reachy, a human-like life-scale robotic arm with seven joints from shoulder to wrist. Although Reachy does not include a poly-articulated hand and is therefore more suitable for studying reaching than manipulation, a robotic hand prototype from available third-party projects could be integrated to it. Its 3D-printed structure and off-the-shelf actuators make it inexpensive relatively to the price of an industrial-grade robot. Using an open-source architecture, its design makes it broadly connectable and customizable, so it can be integrated into many applications. To illustrate how Reachy can connect to external devices, this paper presents several proofs of concept where it is operated with various control strategies, such as tele-operation or gaze-driven control. In this way, Reachy can help researchers to explore, develop and test innovative control strategies and interfaces on a human-like robot.
RESUMO
An opportune early diagnosis of Alzheimer's disease (AD) would help to overcome symptoms and improve the quality of life for AD patients. Research studies have identified early manifestations of AD that occur years before the diagnosis. For instance, eye movements of people with AD in different tasks differ from eye movements of control subjects. In this review, we present a summary and evolution of research approaches that use eye tracking technology and computational analysis to measure and compare eye movements under different tasks and experiments. Furthermore, this review is targeted to the feasibility of pioneer work on developing computational tools and techniques to analyze eye movements under naturalistic scenarios. We describe the progress in technology that can enhance the analysis of eye movements everywhere while subjects perform their daily activities and give future research directions to develop tools to support early AD diagnosis through analysis of eye movements.
Assuntos
Doença de Alzheimer/diagnóstico , Movimentos Oculares , Algoritmos , Diagnóstico Precoce , Humanos , Qualidade de VidaRESUMO
Combining multimodal concept streams from heterogeneous sensors is a problem superficially explored for activity recognition. Most studies explore simple sensors in nearly perfect conditions, where temporal synchronization is guaranteed. Sophisticated fusion schemes adopt problem-specific graphical representations of events that are generally deeply linked with their training data and focused on a single sensor. This paper proposes a hybrid framework between knowledge-driven and probabilistic-driven methods for event representation and recognition. It separates semantic modeling from raw sensor data by using an intermediate semantic representation, namely concepts. It introduces an algorithm for sensor alignment that uses concept similarity as a surrogate for the inaccurate temporal information of real life scenarios. Finally, it proposes the combined use of an ontology language, to overcome the rigidity of previous approaches at model definition, and a probabilistic interpretation for ontological models, which equips the framework with a mechanism to handle noisy and ambiguous concept observations, an ability that most knowledge-driven methods lack. We evaluate our contributions in multimodal recordings of elderly people carrying out IADLs. Results demonstrated that the proposed framework outperforms baseline methods both in event recognition performance and in delimiting the temporal boundaries of event instances.
Assuntos
Modelos Estatísticos , Reconhecimento Automatizado de Padrão , Semântica , Algoritmos , HumanosRESUMO
Recently, several pattern recognition methods have been proposed to automatically discriminate between patients with and without Alzheimer's disease using different imaging modalities: sMRI, fMRI, PET and SPECT. Classical approaches in visual information retrieval have been successfully used for analysis of structural MRI brain images. In this paper, we use the visual indexing framework and pattern recognition analysis based on structural MRI data to discriminate three classes of subjects: normal controls (NC), mild cognitive impairment (MCI) and Alzheimer's disease (AD). The approach uses the circular harmonic functions (CHFs) to extract local features from the most involved areas in the disease: hippocampus and posterior cingulate cortex (PCC) in each slice in all three brain projections. The features are quantized using the Bag-of-Visual-Words approach to build one signature by brain (subject). This yields a transformation of a full 3D image of brain ROIs into a 1D signature, a histogram of quantized features. To reduce the dimensionality of the signature, we use the PCA technique. Support vector machines classifiers are then applied to classify groups. The experiments were conducted on a subset of ADNI dataset and applied to the "Bordeaux-3City" dataset. The results showed that our approach achieves respectively for ADNI dataset and "Bordeaux-3City" dataset; for AD vs NC classification, an accuracy of 83.77% and 78%, a specificity of 88.2% and 80.4% and a sensitivity of 79.09% and 74.7%. For NC vs MCI classification we achieved for the ADNI datasets an accuracy of 69.45%, a specificity of 74.8% and a sensitivity of 62.52%. For the most challenging classification task (AD vs MCI), we reached an accuracy of 62.07%, a specificity of 75.15% and a sensitivity of 49.02%. The use of PCC visual features description improves classification results by more than 5% compared to the use of hippocampus features only. Our approach is automatic, less time-consuming and does not require the intervention of the clinician during the disease diagnosis.
Assuntos
Doença de Alzheimer/patologia , Giro do Cíngulo/patologia , Hipocampo/patologia , Interpretação de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Imageamento por Ressonância Magnética/métodos , Idoso , Idoso de 80 Anos ou mais , Algoritmos , Feminino , Humanos , Aumento da Imagem/métodos , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
Real-time magnetic resonance imaging is a promising tool for image-guided interventions. For applications such as thermotherapy on moving organs, a precise image-based compensation of motion is required in real time to allow quantitative analysis, retrocontrol of the interventional device, or determination of the therapy endpoint. Reduced field-of-view imaging represents a promising way to improve spatial and/or temporal resolution. However, it introduces new challenges for target motion estimation, since structures near the target may appear transiently due to the respiratory motion and the limited spatial coverage. In this paper, a new image-based motion estimation method is proposed combining a global motion estimation with a novel optical flow approach extending the initial Horn and Schunck (H&S) method by an additional regularization term. This term integrates the displacement of physiological landmarks into the variational formulation of the optical flow problem. This allowed for a better control of the optical flow in presence of transient structures. The method was compared to the same registration pipeline employing the H&S approach on a synthetic dataset and in vivo image sequences. Compared to the H&S approach, a significant improvement (p<0.05) of the Dice's similarity criterion computed between the reference and the registered organ positions was achieved.