|
|
Antonio Hernandez, Stan Sclaroff, & Sergio Escalera. (2014). Contextual rescoring for Human Pose Estimation. In 25th British Machine Vision Conference.
Abstract: A contextual rescoring method is proposed for improving the detection of body joints of a pictorial structure model for human pose estimation. A set of mid-level parts is incorporated in the model, and their detections are used to extract spatial and score-related features relative to other body joint hypotheses. A technique is proposed for the automatic discovery of a compact subset of poselets that covers a set of validation images
while maximizing precision. A rescoring mechanism is defined as a set-based boosting classifier that computes a new score for body joint detections, given its relationship to detections of other body joints and mid-level parts in the image. This new score complements the unary potential of a discriminatively trained pictorial structure model. Experiments on two benchmarks show performance improvements when considering the proposed mid-level image representation and rescoring approach in comparison with other pictorial structure-based approaches.
|
|
|
|
Sergio Vera, Debora Gil, & Miguel Angel Gonzalez Ballester. (2014). Anatomical parameterization for volumetric meshing of the liver. In SPIE – Medical Imaging (Vol. 9036).
Abstract: A coordinate system describing the interior of organs is a powerful tool for a systematic localization of injured tissue. If the same coordinate values are assigned to specific anatomical landmarks, the coordinate system allows integration of data across different medical image modalities. Harmonic mappings have been used to produce parametric coordinate systems over the surface of anatomical shapes, given their flexibility to set values
at specific locations through boundary conditions. However, most of the existing implementations in medical imaging restrict to either anatomical surfaces, or the depth coordinate with boundary conditions is given at sites
of limited geometric diversity. In this paper we present a method for anatomical volumetric parameterization that extends current harmonic parameterizations to the interior anatomy using information provided by the
volume medial surface. We have applied the methodology to define a common reference system for the liver shape and functional anatomy. This reference system sets a solid base for creating anatomical models of the patient’s liver, and allows comparing livers from several patients in a common framework of reference.
Keywords: Coordinate System; Anatomy Modeling; Parameterization
|
|
|
|
Bogdan Raducanu, & Fadi Dornaika. (2012). Out-of-Sample Embedding by Sparse Representation. In Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop (Vol. 7626, pp. 336–344). Springer Berlin Heidelberg.
Abstract: A critical aspect of non-linear dimensionality reduction techniques is represented by the construction of the adjacency graph. The difficulty resides in finding the optimal parameters, a process which, in general, is heuristically driven. Recently, sparse representation has been proposed as a non-parametric solution to overcome this problem. In this paper, we demonstrate that this approach not only serves for the graph construction, but also represents an efficient and accurate alternative for out-of-sample embedding. Considering for a case study the Laplacian Eigenmaps, we applied our method to the face recognition problem. Experimental results conducted on some challenging datasets confirmed the robustness of our approach and its superiority when compared to existing techniques.
|
|
|
|
Yi Xiao, Felipe Codevilla, Akhil Gurram, Onay Urfalioglu, & Antonio Lopez. (2020). Multimodal end-to-end autonomous driving. TITS - IEEE Transactions on Intelligent Transportation Systems, , 1–11.
Abstract: A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to drive towards a desired destination. Today, there are different paradigms addressing the development of AI drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception and maneuver planning and control. On the other hand, we find end-to-end driving approaches that try to learn a direct mapping from input raw sensor data to vehicle control signals. The later are relatively less studied, but are gaining popularity since they are less demanding in terms of sensor data annotation. This paper focuses on end-to-end autonomous driving. So far, most proposals relying on this paradigm assume RGB images as input sensor data. However, AVs will not be equipped only with cameras, but also with active sensors providing accurate depth information (e.g., LiDARs). Accordingly, this paper analyses whether combining RGB and depth modalities, i.e. using RGBD data, produces better end-to-end AI drivers than relying on a single modality. We consider multimodality based on early, mid and late fusion schemes, both in multisensory and single-sensor (monocular depth estimation) settings. Using the CARLA simulator and conditional imitation learning (CIL), we show how, indeed, early fusion multimodality outperforms single-modality.
|
|
|
|
Joakim Bruslund Haurum, Meysam Madadi, Sergio Escalera, & Thomas B. Moeslund. (2022). Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification. AC - Automation in Construction, 144, 104614.
Abstract: A crucial part of image classification consists of capturing non-local spatial semantics of image content. This paper describes the multi-scale hybrid vision transformer (MSHViT), an extension of the classical convolutional neural network (CNN) backbone, for multi-label sewer defect classification. To better model spatial semantics in the images, features are aggregated at different scales non-locally through the use of a lightweight vision transformer, and a smaller set of tokens was produced through a novel Sinkhorn clustering-based tokenizer using distinct cluster centers. The proposed MSHViT and Sinkhorn tokenizer were evaluated on the Sewer-ML multi-label sewer defect classification dataset, showing consistent performance improvements of up to 2.53 percentage points.
Keywords: Sewer Defect Classification; Vision Transformers; Sinkhorn-Knopp; Convolutional Neural Networks; Closed-Circuit Television; Sewer Inspection
|
|
|
|
Panagiota Spyridonos, Fernando Vilariño, Jordi Vitria, Petia Radeva, Fernando Azpiroz, & Juan Malagelada. (2011). Device, system and method for automatic detection of contractile activity in an image frame.
Abstract: A device, system and method for automatic detection of contractile activity of a body lumen in an image frame is provided, wherein image frames during contractile activity are captured and/or image frames including contractile activity are automatically detected, such as through pattern recognition and/or feature extraction to trace image frames including contractions, e.g., with wrinkle patterns. A manual procedure of annotation of contractions, e.g. tonic contractions in capsule endoscopy, may consist of the visualization of the whole video by a specialist, and the labeling of the contraction frames. Embodiments of the present invention may be suitable for implementation in an in vivo imaging system.
|
|
|
|
Hugo Prol, Vincent Dumoulin, & Luis Herranz. (2018). Cross-Modulation Networks for Few-Shot Learning.
Abstract: A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and query examples at a very late stage of the prediction pipeline. Inspired by this observation, we hypothesize that there may be benefits to combining the information at various levels of abstraction along the pipeline. We present an architecture called Cross-Modulation Networks which allows support and query examples to interact throughout the feature extraction process via a feature-wise modulation mechanism. We adapt the Matching Networks architecture to take advantage of these interactions and show encouraging initial results on miniImageNet in the 5-way, 1-shot setting, where we close the gap with state-of-the-art.
|
|
|
|
Lluis Pere de las Heras, Ahmed Sheraz, Marcus Liwicki, Ernest Valveny, & Gemma Sanchez. (2014). Statistical Segmentation and Structural Recognition for Floor Plan Interpretation. IJDAR - International Journal on Document Analysis and Recognition, 17(3), 221–237.
Abstract: A generic method for floor plan analysis and interpretation is presented in this article. The method, which is mainly inspired by the way engineers draw and interpret floor plans, applies two recognition steps in a bottom-up manner. First, basic building blocks, i.e., walls, doors, and windows are detected using a statistical patch-based segmentation approach. Second, a graph is generated, and structural pattern recognition techniques are applied to further locate the main entities, i.e., rooms of the building. The proposed approach is able to analyze any type of floor plan regardless of the notation used. We have evaluated our method on different publicly available datasets of real architectural floor plans with different notations. The overall detection and recognition accuracy is about 95 %, which is significantly better than any other state-of-the-art method. Our approach is generic enough such that it could be easily adopted to the recognition and interpretation of any other printed machine-generated structured documents.
|
|
|
|
Aura Hernandez-Sabate, Monica Mitiko, Sergio Shiguemi, & Debora Gil. (2010). A validation protocol for assessing cardiac phase retrieval in IntraVascular UltraSound. In Computing in Cardiology (Vol. 37, pp. 899–902). IEEE.
Abstract: A good reliable approach to cardiac triggering is of utmost importance in obtaining accurate quantitative results of atherosclerotic plaque burden from the analysis of IntraVascular UltraSound. Although, in the last years, there has been an increase in research of methods for retrospective gating, there is no general consensus in a validation protocol. Many methods are based on quality assessment of longitudinal cuts appearance and those reporting quantitative numbers do not follow a standard protocol. Such heterogeneity in validation protocols makes faithful comparison across methods a difficult task. We propose a validation protocol based on the variability of the retrieved cardiac phase and explore the capability of several quality measures for quantifying such variability. An ideal detector, suitable for its application in clinical practice, should produce stable phases. That is, it should always sample the same cardiac cycle fraction. In this context, one should measure the variability (variance) of a candidate sampling with respect a ground truth (reference) sampling, since the variance would indicate how spread we are aiming a target. In order to quantify the deviation between the sampling and the ground truth, we have considered two quality scores reported in the literature: signed distance to the closest reference sample and distance to the right of each reference sample. We have also considered the residuals of the regression line of reference against candidate sampling. The performance of the measures has been explored on a set of synthetic samplings covering different cardiac cycle fractions and variabilities. From our simulations, we conclude that the metrics related to distances are sensitive to the shift considered while the residuals are robust against fraction and variabilities as far as one can establish a pair-wise correspondence between candidate and reference. We will further investigate the impact of false positive and negative detections in experimental data.
|
|
|
|
Josep Llados, Enric Marti, & Jaime Lopez-Krahe. (1999). A Hough-based method for hatched pattern detection in maps and diagrams. In Proceeding of the Fifth Int. Conf. Document Analysis and Recognition ICDAR ’99 (pp. 479–482).
Abstract: A hatched area is characterized by a set of parallel straight lines placed at regular intervals. In this paper, a Hough-based schema is introduced to recognize hatched areas in technical documents from attributed graph structures representing the document once it has been vectorized. Defining a Hough-based transform from a graph instead of the raster image allows to drastically reduce the processing time and, second, to obtain more reliable results because straight lines have already been detected in the vectorization step. A second advantage of the proposed method is that no assumptions must be made a priori about the slope and frequency of hatching patterns, but they are computed in run time for each hatched area.
|
|
|
|
Michal Drozdzal, Santiago Segui, Carolina Malagelada, Fernando Azpiroz, Jordi Vitria, & Petia Radeva. (2011). Interactive Labeling of WCE Images. In J. Vitria, J. M. R. Sanches, & M. Hernández (Eds.), 5th Iberian Conference on Pattern Recognition and Image Analysis (Vol. 6669, pp. 143–150). Springer.
Abstract: A high quality labeled training set is necessary for any supervised machine learning algorithm. Labeling of the data can be a very expensive process, specially while dealing with data of high variability and complexity. A good example of such data are the videos from Wireless Capsule Endoscopy. Building a representative WCE data set means many videos to be labeled by an expert. The problem that occurs is the data diversity, in the space of the features, from different WCE studies. That means that when new data arrives it is highly probable that it will not be represented in the training set, thus getting a high probability of performing an error when applying machine learning schemes. In this paper an interactive labeling scheme that allows reducing expert effort in the labeling process is presented. It is shown that the number of human interventions can be significantly reduced. The proposed system allows the annotation of informative/non-informative frames of the WCE video with less than 100 clicks
|
|
|
|
Helena Muñoz, Fernando Vilariño, & Dimosthenis Karatzas. (2019). Eye-Movements During Information Extraction from Administrative Documents. In International Conference on Document Analysis and Recognition Workshops (pp. 6–9).
Abstract: A key aspect of digital mailroom processes is the extraction of relevant information from administrative documents. More often than not, the extraction process cannot be fully automated, and there is instead an important amount of manual intervention. In this work we study the human process of information extraction from invoice document images. We explore whether the gaze of human annotators during an manual information extraction process could be exploited towards reducing the manual effort and automating the process. To this end, we perform an eye-tracking experiment replicating real-life interfaces for information extraction. Through this pilot study we demonstrate that relevant areas in the document can be identified reliably through automatic fixation classification, and the obtained models generalize well to new subjects. Our findings indicate that it is in principle possible to integrate the human in the document image analysis loop, making use of the scanpath to automate the extraction process or verify extracted information.
|
|
|
|
Jiaolong Xu, Sebastian Ramos, David Vazquez, & Antonio Lopez. (2016). Hierarchical Adaptive Structural SVM for Domain Adaptation. IJCV - International Journal of Computer Vision, 119(2), 159–178.
Abstract: A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain. This is being recognized as a very relevant problem for many
computer vision tasks such as image classification, object detection, and object category recognition. In this paper, we present a novel domain adaptation method that leverages multiple target domains (or sub-domains) in a hierarchical adaptation tree. The core idea is to exploit the commonalities and differences of the jointly considered target domains.
Given the relevance of structural SVM (SSVM) classifiers, we apply our idea to the adaptive SSVM (A-SSVM), which only requires the target domain samples together with the existing source-domain classifier for performing the desired adaptation. Altogether, we term our proposal as hierarchical A-SSVM (HA-SSVM).
As proof of concept we use HA-SSVM for pedestrian detection, object category recognition and face recognition. In the former we apply HA-SSVM to the deformable partbased model (DPM) while in the rest HA-SSVM is applied to multi-category classifiers. We will show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data. Since, the sub-domains of the target data are not always known a priori, we shown how HA-SSVM can incorporate sub-domain discovery for object category recognition.
Keywords: Domain Adaptation; Pedestrian Detection
|
|
|
|
Jaykishan Patel, Alban Flachot, Javier Vazquez, David H. Brainard, Thomas S. A. Wallis, Marcus A. Brubaker, et al. (2023). A deep convolutional neural network trained to infer surface reflectance is deceived by mid-level lightness illusions. JV - Journal of Vision, 23(9), 4817.
Abstract: A long-standing view is that lightness illusions are by-products of strategies employed by the visual system to stabilize its perceptual representation of surface reflectance against changes in illumination. Computationally, one such strategy is to infer reflectance from the retinal image, and to base the lightness percept on this inference. CNNs trained to infer reflectance from images have proven successful at solving this problem under limited conditions. To evaluate whether these CNNs provide suitable starting points for computational models of human lightness perception, we tested a state-of-the-art CNN on several lightness illusions, and compared its behaviour to prior measurements of human performance. We trained a CNN (Yu & Smith, 2019) to infer reflectance from luminance images. The network had a 30-layer hourglass architecture with skip connections. We trained the network via supervised learning on 100K images, rendered in Blender, each showing randomly placed geometric objects (surfaces, cubes, tori, etc.), with random Lambertian reflectance patterns (solid, Voronoi, or low-pass noise), under randomized point+ambient lighting. The renderer also provided the ground-truth reflectance images required for training. After training, we applied the network to several visual illusions. These included the argyle, Koffka-Adelson, snake, White’s, checkerboard assimilation, and simultaneous contrast illusions, along with their controls where appropriate. The CNN correctly predicted larger illusions in the argyle, Koffka-Adelson, and snake images than in their controls. It also correctly predicted an assimilation effect in White's illusion. It did not, however, account for the checkerboard assimilation or simultaneous contrast effects. These results are consistent with the view that at least some lightness phenomena are by-products of a rational approach to inferring stable representations of physical properties from intrinsically ambiguous retinal images. Furthermore, they suggest that CNN models may be a promising starting point for new models of human lightness perception.
|
|
|
|
Debora Gil, Antonio Esteban Lansaque, Agnes Borras, Esmitt Ramirez, & Carles Sanchez. (2020). Intraoperative Extraction of Airways Anatomy in VideoBronchoscopy. ACCESS - IEEE Access, 8, 159696–159704.
Abstract: A main bottleneck in bronchoscopic biopsy sampling is to efficiently reach the lesion navigating across bronchial levels. Any guidance system should be able to localize the scope position during the intervention with minimal costs and alteration of clinical protocols. With the final goal of an affordable image-based guidance, this work presents a novel strategy to extract and codify the anatomical structure of bronchi, as well as, the scope navigation path from videobronchoscopy. Experiments using interventional data show that our method accurately identifies the bronchial structure. Meanwhile, experiments using simulated data verify that the extracted navigation path matches the 3D route.
|
|
