Search

Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human–robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To the best of our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a region proposal network (RPN) and a multimodal two stream convolutional network for object detection to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an average precision of 91% and a mean computation time of 0.1 s per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new data set, ATLAS Dione, for RAS video understanding. Our data set provides video data of ten surgeons from Roswell Park Cancer Institute, Buffalo, NY, USA, performing six different surgical tasks on the daVinci Surgical System (dVSS) with annotations of robotic tools per frame. [ABSTRACT FROM PUBLISHER]

Occlusion boundary detection and figure/ground assignment are among the fundamental challenges for the real world visual pattern recognition applications, such as 3D spatial understanding, robotic navigation and object search. We attack these challenges by extracting an intermediate-level image/video representation, namely, Common-Fate Fragments. A Common-Fate Fragment is composed of both over-segmented region and edge fragments. Physically, it exists as a coupled edge-region fragment bound with dynamic information. Common-Fate Fragment candidates are generated by an integrated line-region growing process, which does not require complete object segmentation or closed object boundary extraction. To identify Common-Fate Fragments from these extracted candidates, we introduce a back-projection verification scheme that can circumvent the notoriously difficult task of direct motion estimation on boundaries. This allows occlusion detection and figure/ground labeling to be jointly conducted within a simple but effective hypothesize-and-test framework. We test the proposed method on YouTube Motion Boundaries (YMB) data set and two benchmark data sets: the CMU and Berkeley motion data sets. Even though the idea of the proposed method is simple and transparent, promising experimental results are observed. [ABSTRACT FROM AUTHOR]

Abstract: We present a new feature extraction method based on two dynamical systems induced by intensity landscape: the negative gradient system and the Hamiltonian system. Given the dynamical systems, features are extracted using the Hamiltonian streamlines. Whereas the majority of popular feature extraction methods are computed on the local gradient, our new features contain global topological information about the intensity landscape. We describe the mathematical properties of the Hamiltonian streamline-guided features as well as algorithms for extracting them. To test the new features, we use a face classification experiment and compare them against a standard local gradient feature: Haar-like features. Our experiments show that the global nature of the Hamiltonian streamline-guided features complements the local Haar-like features. For images of the same size, our feature space is demonstrably more compact and descriptive resulting in significantly fewer features needed for comparative classification accuracy and speed. When the two types of features are combined, superior performance is achieved. [Copyright &y& Elsevier]

Abstract: Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in scene understanding remain local. Pictorial structures have arisen as a fundamental parts-based model for some vision problems, such as articulated object detection. However, the form of classical pictorial structures limits their applicability for global problems, such as semantic pixel labeling. In this paper, we propose an extension of the pictorial structures approach, called pixel-support parts-sparse pictorial structures, or PS3, to overcome this limitation. Our model extends the classical form in two ways: first, it defines parts directly based on pixel-support rather than in a parametric form, and second, it specifies a space of plausible parts-based scene models and permits one to be used for inference on any given image. PS3 makes strides toward unifying object-level and pixel-level modeling of scene elements. In this paper, we implement the first half of our model and rely upon external knowledge to provide an initial graph structure for a given image. Our experimental results on benchmark datasets demonstrate the capability of this new parts-based view of scene modeling. [Copyright &y& Elsevier]

Backbone anatomical structure detection and labeling is a necessary step for various analysis tasks of the vertebral column. Appearance, shape and geometry measurements are necessary for abnormality detection locally at each disc and vertebrae (such as herniation) as well as globally for the whole spine (such as spinal scoliosis). We propose a two-level probabilistic model for the localization of discs from clinical magnetic resonance imaging (MRI) data that captures both pixel- and object-level features. Using a Gibbs distribution, we model appearance and spatial information at the pixel level, and at the object level, we model the spatial distribution of the discs and the relative distances between them. We use generalized expectation-maximization for optimization, which achieves efficient convergence of disc labels. Our two-level model allows the assumption of conditional independence at the pixel-level to enhance efficiency while maintaining robustness. We use a dataset that contains 105 MRI clinical normal and abnormal cases for the lumbar area. We thoroughly test our model and achieve encouraging results on normal and abnormal cases. [ABSTRACT FROM AUTHOR]

The article presents a theoretical model and technological platform for video-based human-computer interfacing. Issues of increased computational ability in computer technology are contrasted with standard input-output structures in data entry. The traditional visual interaction cues (VIC) paradigm is described along with the additional implementation of a 4-dimensional touchpad video input platform to bypass conventional interface restrictions. Challenges facing the combined system, including geometric calibration, foreground segmentation, gesture recognition, and the development of a gesture language are each addressed.

We present a new method for automatic segmentation of heterogeneous image data that takes a step toward bridging the gap between bottom-up affinity-based segmentation methods and top-down generative model based approaches. The main contribution of the paper is a Bayesian formulation for incorporating soft model assignments into the calculation of affinities, which are conventionally model free. We integrate the resulting model-aware affinities into the multilevel segmentation by weighted aggregation algorithm, and apply the technique to the task of detecting and segmenting brain tumor and edema in multichannel magnetic resonance (MR) volumes. The computationally efficient method runs orders of magnitude faster than current state-of-the-art techniques giving comparable or improved results. Our quantitative results indicate the benefit of incorporating model-aware affinities into the segmentation process for the difficult case of glioblastoma multiforme brain tumor. [ABSTRACT FROM AUTHOR]

Abstract: Since its inception about three decades ago, modern minimally invasive surgery has made huge advances in both technique and technology. However, the minimally invasive surgeon is still faced with daunting challenges in terms of visualization and hand-eye coordination. At the Center for Computer Integrated Surgical Systems and Technology (CISST) we have been developing a set of techniques for assisting surgeons in navigating and manipulating the three-dimensional space within the human body. In order to develop such systems, a variety of challenging visual tracking, reconstruction and registration problems must be solved. In addition, this information must be tied to methods for assistance that improve surgical accuracy and reliability but allow the surgeon to retain ultimate control of the procedure and do not prolong time in the operating room. In this article, we present two problem areas, eye microsurgery and thoracic minimally invasive surgery, where computational vision can play a role. We then describe methods we have developed to process video images for relevant geometric information, and related control algorithms for providing interactive assistance. Finally, we present results from implemented systems. [Copyright &y& Elsevier]

Semi-supervised clustering seeks to augment traditional clustering methods by incorporating side information provided via human expertise in order to increase the semantic meaningfulness of the resulting clusters. However, most current methods are passive in the sense that the side information is provided beforehand and selected randomly. This may require a large number of constraints, some of which could be redundant, unnecessary, or even detrimental to the clustering results. Thus in order to scale such semi-supervised algorithms to larger problems it is desirable to pursue an active clustering method—i.e., an algorithm that maximizes the effectiveness of the available human labor by only requesting human input where it will have the greatest impact. Here, we propose a novel online framework for active semi-supervised spectral clustering that selects pairwise constraints as clustering proceeds, based on the principle of uncertainty reduction. Using a first-order Taylor expansion, we decompose the expected uncertainty reduction problem into a gradient and a step-scale, computed via an application of matrix perturbation theory and cluster-assignment entropy, respectively. The resulting model is used to estimate the uncertainty reduction potential of each sample in the dataset. We then present the human user with pairwise queries with respect to only the best candidate sample. We evaluate our method using three different image datasets (faces, leaves and dogs), a set of common UCI machine learning datasets and a gene dataset. The results validate our decomposition formulation and show that our method is consistently superior to existing state-of-the-art techniques, as well as being robust to noise and to unknown numbers of clusters. [ABSTRACT FROM AUTHOR]

Metric learning is a key problem for many data mining and machine learning applications, and has long been dominated by Mahalanobis methods. Recent advances in nonlinear metric learning have demonstrated the potential power of non-Mahalanobis distance functions, particularly tree-based functions. We propose a novel nonlinear metric learning method that uses an iterative, hierarchical variant of semi-supervised max-margin clustering to construct a forest of cluster hierarchies, where each individual hierarchy can be interpreted as a weak metric over the data. By introducing randomness during hierarchy training and combining the output of many of the resulting semi-random weak hierarchy metrics, we can obtain a powerful and robust nonlinear metric model. This method has two primary contributions: first, it is semi-supervised, incorporating information from both constrained and unconstrained points. Second, we take a relaxed approach to constraint satisfaction, allowing the method to satisfy different subsets of the constraints at different levels of the hierarchy rather than attempting to simultaneously satisfy all of them. This leads to a more robust learning algorithm. We compare our method to a number of state-of-the-art benchmarks on $k$ -nearest neighbor classification, large-scale image retrieval and semi-supervised clustering problems, and find that our algorithm yields results comparable or superior to the state-of-the-art. [ABSTRACT FROM PUBLISHER]

Abstract: Building facade detection is an important problem in computer vision, with applications in mobile robotics and semantic scene understanding. In particular, mobile platform localization and guidance in urban environments can be enabled with accurate models of the various building facades in a scene. Toward that end, we present a system for detection, segmentation, and parameter estimation of building facades in stereo imagery. The proposed method incorporates multilevel appearance and disparity features in a binary discriminative model, and generates a set of candidate planes by sampling and clustering points from the image with Random Sample Consensus (RANSAC), using local normal estimates derived from Principal Component Analysis (PCA) to inform the planar models. These two models are incorporated into a two-layer Markov Random Field (MRF): an appearance- and disparity-based discriminative classifier at the mid-level, and a geometric model to segment the building pixels into facades at the high-level. By using object-specific stereo features, our discriminative classifier is able to achieve substantially higher accuracy than standard boosting or modeling with only appearance-based features. Furthermore, the results of our MRF classification indicate a strong improvement in accuracy for the binary building detection problem and the labeled planar surface models provide a good approximation to the ground truth planes. [Copyright &y& Elsevier]

In this work, we explore video frame inpainting, a task that lies at the intersection of general video inpainting, frame interpolation, and video prediction. Although our problem can be addressed by applying methods from other video interpolation or extrapolation tasks, doing so fails to leverage the additional context information that our problem provides. To this end, we devise a method specifically designed for video frame inpainting that is composed of two modules: a bidirectional video prediction module and a temporally-aware frame interpolation module. The prediction module makes two intermediate predictions of the missing frames, each conditioned on the preceding and following frames respectively, using a shared convolutional LSTM-based encoder-decoder. The interpolation module blends the intermediate predictions by using time information and hidden activations from the video prediction module to resolve disagreements between the predictions. Our experiments demonstrate that our approach produces smoother and more accurate results than state-of-the-art methods for general video inpainting, frame interpolation, and video prediction. [ABSTRACT FROM AUTHOR]

Modeling human behaviors and activity patterns has attracted significant research interest in recent years. In order to accurately model human behaviors, we need to perform fine-grained human activity understanding in videos. Fine-grained activity understanding in videos has attracted considerable recent attention with a shift from action classification to detailed actor and action understanding that provides compelling results for perceptual needs of cutting-edge autonomous systems. However, current methods for detailed understanding of actor and action have significant limitations: they require large amounts of finely labeled data, and they fail to capture any internal relationship among actors and actions. To address these issues, in this paper, we propose a novel Schatten p-norm robust multi-task ranking model for weakly-supervised actor–action segmentation where only video-level tags are given for training samples. Our model is able to share useful information among different actors and actions while learning a ranking matrix to select representative supervoxels for actors and actions respectively. Final segmentation results are generated by a conditional random field that considers various ranking scores for video parts. Extensive experimental results on both the actor–action dataset and the Youtube-objects dataset demonstrate that the proposed approach outperforms the state-of-the-art weakly supervised methods and performs as well as the top-performing fully supervised method. [ABSTRACT FROM AUTHOR]

Various perceptual domains have underlying compositional semantics that are rarely captured in current models. We suspect this is because directly learning the compositional structure has evaded these models. Yet, the compositional structure of a given domain can be grounded in a separate domain thereby simplifying its learning. To that end, we propose a new approach to modeling bimodal perceptual domains that explicitly relates distinct projections across each modality and then jointly learns a bimodal sparse representation. The resulting model enables compositionality across these distinct projections and hence can generalize to unobserved percepts spanned by this compositional basis. For example, our model can be trained on red triangles and blue squares; yet, implicitly will also have learned red squares and blue triangles. The structure of the projections and hence the compositional basis is learned automatically; no assumption is made on the ordering of the compositional elements in either modality. Although our modeling paradigm is general, we explicitly focus on a tabletop building-blocks setting. To test our model, we have acquired a new bimodal dataset comprising images and spoken utterances of colored shapes (blocks) in the tabletop setting. Our experiments demonstrate the benefits of explicitly leveraging compositionality in both quantitative and human evaluation studies. [ABSTRACT FROM PUBLISHER]

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource. [ABSTRACT FROM AUTHOR]

Abstract: The use of cone beam computed tomography (CBCT) is growing in the clinical arena due to its ability to provide 3D information during interventions, its high diagnostic quality (sub-millimeter resolution), and its short scanning times (60s). In many situations, the short scanning time of CBCT is followed by a time-consuming 3D reconstruction. The standard reconstruction algorithm for CBCT data is the filtered backprojection, which for a volume of size 2563 takes up to 25min on a standard system. Recent developments in the area of Graphic Processing Units (GPUs) make it possible to have access to high-performance computing solutions at a low cost, allowing their use in many scientific problems. We have implemented an algorithm for 3D reconstruction of CBCT data using the Compute Unified Device Architecture (CUDA) provided by NVIDIA (NVIDIA Corporation, Santa Clara, California), which was executed on a NVIDIA GeForce GTX 280. Our implementation results in improved reconstruction times from minutes, and perhaps hours, to a matter of seconds, while also giving the clinician the ability to view 3D volumetric data at higher resolutions. We evaluated our implementation on ten clinical data sets and one phantom data set to observe if differences occur between CPU and GPU-based reconstructions. By using our approach, the computation time for 2563 is reduced from 25min on the CPU to 3.2s on the GPU. The GPU reconstruction time for 5123 volumes is 8.5s. [Copyright &y& Elsevier]