PADAr: physician-oriented artificial intelligence-facilitating diagnosis aid for retinal diseases

Purpose: Retinopathy screening via digital imaging is promising for early detection and timely treatment, and tracking retinopathic abnormality over time can help to reveal the risk of disease progression. We developed an innovative physician-oriented artificial intelligence-facilitating diagnosis aid system for retinal diseases for screening multiple retinopathies and monitoring the regions of potential abnormality over time. Approach: Our dataset contains 4908 fundus images from 304 eyes with image-level annotations, including diabetic retinopathy, age-related macular degeneration, cellophane maculopathy, pathological myopia, and healthy control (HC). The screening model utilized a VGG-based feature extractor and multiple-binary convolutional neural network-based classifiers. Images in time series were aligned via affine transforms estimated through speeded-up robust features. Heatmaps of retinopathy were generated from the feature extractor using gradient-weighted class activation mapping++, and individual candidate retinopathy sites were identified from the heatmaps using clustering algorithm. Nested cross-validation with a train-to-test split of 80% to 20% was used to evaluate the performance of the screening model. Results: Our screening model achieved 99% accuracy, 93% sensitivity, and 97% specificity in discriminating between patients with retinopathy and HCs. For discriminating between types of retinopathy, our model achieved an averaged performance of 80% accuracy, 78% sensitivity, 94% specificity, 79% F1-score, and Cohen's kappa coefficient of 0.70. Moreover, visualization results were also shown to provide reasonable candidate sites of retinopathy. Conclusions: Our results demonstrated the capability of the proposed model for extracting diagnostic information of the abnormality and lesion locations, which allows clinicians to focus on patient-centered treatment and untangles the pathological plausibility hidden in deep learning models.

Court Reconstruction for Camera Calibration in Broadcast Basketball Videos

We introduce a technique of calibrating camera motions in basketball videos. Our method particularly transforms player positions to standard basketball court coordinates and enables applications such as tactical analysis and semantic basketball video retrieval. To achieve a robust calibration, we reconstruct the panoramic basketball court from a video, followed by warping the panoramic court to a standard one. As opposed to previous approaches, which individually detect the court lines and corners of each video frame, our technique considers all video frames simultaneously to achieve calibration; hence, it is robust to illumination changes and player occlusions. To demonstrate the feasibility of our technique, we present a stroke-based system that allows users to retrieve basketball videos. Our system tracks player trajectories from broadcast basketball videos. It then rectifies the trajectories to a standard basketball court by using our camera calibration method. Consequently, users can apply stroke queries to indicate how the players move in gameplay during retrieval. The main advantage of this interface is an explicit query of basketball videos so that unwanted outcomes can be prevented. We show the results in Figs. 1, 7, 9, 10 and our accompanying video to exhibit the feasibility of our technique.

Robust action recognition via borrowing information across video modalities

The recent advances in imaging devices have opened the opportunity of better solving the tasks of video content analysis and understanding. Next-generation cameras, such as the depth or binocular cameras, capture diverse information, and complement the conventional 2D RGB cameras. Thus, investigating the yielded multimodal videos generally facilitates the accomplishment of related applications. However, the limitations of the emerging cameras, such as short effective distances, expensive costs, or long response time, degrade their applicability, and currently make these devices not online accessible in practical use. In this paper, we provide an alternative scenario to address this problem, and illustrate it with the task of recognizing human actions. In particular, we aim at improving the accuracy of action recognition in RGB videos with the aid of one additional RGB-D camera. Since RGB-D cameras, such as Kinect, are typically not applicable in a surveillance system due to its short effective distance, we instead offline collect a database, in which not only the RGB videos but also the depth maps and the skeleton data of actions are available jointly. The proposed approach can adapt the interdatabase variations, and activate the borrowing of visual knowledge across different video modalities. Each action to be recognized in RGB representation is then augmented with the borrowed depth and skeleton features. Our approach is comprehensively evaluated on five benchmark data sets of action recognition. The promising results manifest that the borrowed information leads to remarkable boost in recognition accuracy.

Cross-camera knowledge transfer for multiview people counting

We present a novel two-pass framework for counting the number of people in an environment, where multiple cameras provide different views of the subjects. By exploiting the complementary information captured by the cameras, we can transfer knowledge between the cameras to address the difficulties of people counting and improve the performance. The contribution of this paper is threefold. First, normalizing the perspective of visual features and estimating the size of a crowd are highly correlated tasks. Hence, we treat them as a joint learning problem. The derived counting model is scalable and it provides more accurate results than existing approaches. Second, we introduce an algorithm that matches groups of pedestrians in images captured by different cameras. The results provide a common domain for knowledge transfer, so we can work with multiple cameras without worrying about their differences. Third, the proposed counting system is comprised of a pair of collaborative regressors. The first one determines the people count based on features extracted from intracamera visual information, whereas the second calculates the residual by considering the conflicts between intercamera predictions. The two regressors are elegantly coupled and provide an accurate people counting system. The results of experiments in various settings show that, overall, our approach outperforms comparable baseline methods. The significant performance improvement demonstrates the effectiveness of our two-pass regression framework.

Simultaneous tensor decomposition and completion using factor priors

The success of research on matrix completion is evident in a variety of real-world applications. Tensor completion, which is a high-order extension of matrix completion, has also generated a great deal of research interest in recent years. Given a tensor with incomplete entries, existing methods use either factorization or completion schemes to recover the missing parts. However, as the number of missing entries increases, factorization schemes may overfit the model because of incorrectly predefined ranks, while completion schemes may fail to interpret the model factors. In this paper, we introduce a novel concept: complete the missing entries and simultaneously capture the underlying model structure. To this end, we propose a method called simultaneous tensor decomposition and completion (STDC) that combines a rank minimization technique with Tucker model decomposition. Moreover, as the model structure is implicitly included in the Tucker model, we use factor priors, which are usually known a priori in real-world tensor objects, to characterize the underlying joint-manifold drawn from the model factors. By exploiting this auxiliary information, our method leverages two classic schemes and accurately estimates the model factors and missing entries. We conducted experiments to empirically verify the convergence of our algorithm on synthetic data and evaluate its effectiveness on various kinds of real-world data. The results demonstrate the efficacy of the proposed method and its potential usage in tensor-based applications. It also outperforms state-of-the-art methods on multilinear model analysis and visual data completion tasks.

Human object inpainting using manifold learning-based posture sequence estimation

We propose a human object inpainting scheme that divides the process into three steps: 1) human posture synthesis; 2) graphical model construction; and 3) posture sequence estimation. Human posture synthesis is used to enrich the number of postures in the database, after which all the postures are used to build a graphical model that can estimate the motion tendency of an object. We also introduce two constraints to confine the motion continuity property. The first constraint limits the maximum search distance if a trajectory in the graphical model is discontinuous, and the second confines the search direction in order to maintain the tendency of an object's motion. We perform both forward and backward predictions to derive local optimal solutions. Then, to compute an overall best solution, we apply the Markov random field model and take the potential trajectory with the maximum total probability as the final result. The proposed posture sequence estimation model can help identify a set of suitable postures from the posture database to restore damaged/missing postures. It can also make a reconstructed motion sequence look continuous.

Learning atomic human actions using variable-length Markov models

Visual analysis of human behavior has generated considerable interest in the field of computer vision because of its wide spectrum of potential applications. Human behavior can be segmented into atomic actions, each of which indicates a basic and complete movement. Learning and recognizing atomic human actions are essential to human behavior analysis. In this paper, we propose a framework for handling this task using variable-length Markov models (VLMMs). The framework is comprised of the following two modules: a posture labeling module and a VLMM atomic action learning and recognition module. First, a posture template selection algorithm, based on a modified shape context matching technique, is developed. The selected posture templates form a codebook that is used to convert input posture sequences into discrete symbol sequences for subsequent processing. Then, the VLMM technique is applied to learn the training symbol sequences of atomic actions. Finally, the constructed VLMMs are transformed into hidden Markov models (HMMs) for recognizing input atomic actions. This approach combines the advantages of the excellent learning function of a VLMM and the fault-tolerant recognition ability of an HMM. Experiments on realistic data demonstrate the efficacy of the proposed system.

A new iterated two-band diffusion equation: theory and its application

In this paper, we propose an iterated two-band filtering method to solve the selective image smoothing problem. We prove that a discrete computation step in an iterated nonlinear diffusion-based filtering algorithm is equivalent to a sequence of operations, including decomposition, regularization, and then reconstruction, in the proposed two-band filtering scheme. To correctly separate the high frequency components from the low frequency ones in the decomposition process, we adopt a dyadic wavelet-based approximation scheme. In the regularization process, we use a diffusivity function as a guide to retain useful data and suppress noises. Finally, the signal of the next stage, which is a "smoother" version of the signal at the previous stage, can be computed by reconstructing the decomposed low frequency component and the regularized high frequency component. Based on the proposed scheme, the smoothing operation can be applied to the correct targets. Experimental results show that our new approach is really efficient in noise removing.