Wenmiao Lu

Color filter array demosaicking: new method and performance measures

Single-sensor digital cameras capture imagery by covering the sensor surface with a color filter array (CFA) such that each sensor pixel only samples one of three primary color values. To render a full-color image, an interpolation process, commonly referred to as CFA demosaicking, is required to estimate the other two missing color values at each pixel. In this paper, we present two contributions to the CFA demosaicking: a new and improved CFA demosaicking method for producing high quality color images and new image measures for quantifying the performance of demosaicking methods. The proposed demosaicking method consists of two successive steps: an interpolation step that estimates missing color values by exploiting spatial and spectral correlations among neighboring pixels, and a post-processing step that suppresses noticeable demosaicking artifacts by adaptive median filtering. Moreover, in recognition of the limitations of current image measures, we propose two types of image measures to quantify the performance of different demosaicking methods; the first type evaluates the fidelity of demosaicked images by computing the peak signal-to-noise ratio and CIELAB DeltaE(*)(ab) for edge and smooth regions separately, and the second type accounts for one major demosaicking artifact-zipper effect. We gauge the proposed demosaicking method and image measures using several existing methods as benchmarks, and demonstrate their efficacy using a variety of test images.

A color histogram based people tracking system

A system using color histogram based recognition technique is presented for tracking of moving people. The proposed system aims to resolve the identity of each tracked person after an occlusion, which is a common problem encountered in tracking of multiple objects. The system recognizes and keeps track of moving people with the aid of their color histograms. To make the recognition more robust against change of background illumination, a shadow-removal scheme is designed to select only those pixels belonging to the tracked people for constructing their color histograms. Experimental results of real video data are reported to show the efficacy of the proposed system.

A vision-based approach to early detection of drowning incidents in swimming pools

We present in this paper a vision-based approach to detection of drowning incidents in swimming pools at the earliest possible stage. The proposed approach consists of two main parts: a vision component which can reliably detect and track swimmers in spite of large scene variations of monitored pool areas, and an event-inference module which parses observation sequences of swimmer features for possible drowning behavioral signs. The vision component employs a model-based approach to represent and differentiate the background pool areas and foreground swimmers. The event-inference module is constructed based on a finite state machine, which integrates several reasoning rules formulated from universal motion characteristics of drowning swimmers. Possible drowning incidents are quickly detected using a sequential change detection algorithm. We have applied the proposed approach to a number of video clips of simulated drowning and obtained promising results as reported in this paper.

A camera-based system for early detection of drowning incidents

We present in this paper a camera-based system for detecting drowning incidents in a swimming pool at the earliest possible stage. The system consists of two main parts: a vision component which can reliably detect and track swimmers in spite of large scene variations of monitored pool areas, and an event-inference module which parses observation sequences of swimmer features for possible drowning behavioral signs. The vision component employs a model-based approach to represent and differentiate background pool areas and foreground swimmers. The event-inference module is constructed based on a finite state machine, which integrates several reasoning rules formulated from universal motion characteristics of drowning swimmers. Possible drowning incidents are quickly detected using a sequential change detection algorithm. The proposed system has been applied to a number of video clips of simulated drowning, and promising results have been obtained.

Image denoising using multi-stage sparse representations

This paper presents a novel image denoising method based on multiscale sparse representations. The denoising is performed in a multi-stage framework where sparse representations are obtained in different scales to capture multiscale image features. Based on the multi-stage structure, we introduce a new stopping criterion for sparse coding to capture image structures more accurately than previous methods. Furthermore we propose a thresholding technique to effectively avoid artifacts which are usually introduced due to the erroneous pursuit for noise-induced structures. Experimental results demonstrate that the proposed method achieves PSNR performance comparable to other state-of-the-art methods while producing denoised images with superior visual quality.

Layering-based color filter array interpolation

This paper presents a new method to interpolate the color filter array (CFA) pattern that is commonly used in a single-sensor digital camera. The proposed method involves two main steps: slicing the color planes into layers to identify smooth local image regions; estimating the missing color values based on the spectral correlation between color planes. The performance of the proposed algorithm is evaluated by comparing the results with those generated by other existing methods. It shows that the proposed method outperforms other methods in terms of both subjective and objective image quality.

Segmenting human knee cartilage automatically from multi-contrast MR images using support vector machines and discriminative random fields

This paper presents a novel solution toward the accurate and automatic cartilage segmentation with multi-contrast MR images based on pixel classification. The previous pixel classification based works for cartilage segmentation only rely on the labeling by a trained classifier, such as support vector machines (SVM) or k-nearest neighbors. However, these frameworks do not consider the spatial information. To incorporate spatial dependencies in pixel classification, we explore a principled framework of pixel classification based on the convex optimization of an SVM-based association potential and a discriminative random fields (DRF) based interaction potential for our task of cartilage segmentation. The local image structure based features as well as the features based on geometrical information are adopted as the features. We finally perform the loopy belief propagation inference algorithm to find the optimal label configuration. Our framework is validated on a dataset of multi-contrast MR images. Experimental results show that the combined features compare favorably to the two types of separate features and our pixel classification framework outperforms the conventional frameworks based solely on SVM or DRF for cartilage segmentation in subject-specific training scenario.

Orthonormal expansion ℓ 1 -minimization for compressed sensing in MRI

Compressed sensing (CS) enables the reconstruction of MR images from highly under-sampled k-space data via a constrained ℓ1-minimization problem. However, existing convex optimization techniques to solve such a constrained optimization problem suffer from slow convergence rate when dealing with data of a large size. On the other hand, many iterative thresholding techniques improve the convergence rate but at the cost of accuracy. In this work, we present a new iterative optimization technique to efficiently solve the constrained ℓ1 optimization without compromising the accuracy of the solution. The key idea is to expand the sensing matrix into an orthonormal matrix, which casts the ℓ1 constrained optimization into an equivalent convex optimization problem that can be exactly solved by the joint application of augmented Lagrange multipliers (ALM) method and alternating direction method (ADM). The proposed algorithm, dubbed as One - ℓ1, provides much faster convergence rate without compromising the reconstruction accuracy, when compared with commonly used optimization techniques, such as nonlinear conjugate gradient (NCG) method, as demonstrated with both phantom and in-vivo MR experiments.

ROBUST COLOR OBJECT TRACKING WITH APPLICATION TO PEOPLE MONITORING

We present an automated and complete camera-based monitoring system that makes use of low-level color features to perform detection, tracking and recognition of multiple people in video sequence. Specifically, the system employs a novel coverage check-up method to segment detected foreground regions into isolated people and then localize each of them. During tracking, the appearances of people are modeled by their color histograms so that the system can keep aware of their identities and recognize them after occlusions by maximizing the joint likelihood. To make the recognition more robust against shadows or changes of background illumination, the system also incorporates a shadow removal scheme to suppress shadow effects and hence improve the quality of color histogram. The proposed system has been used to identify people who re-enter the field of view of a monitoring camera in a closed-environment. Experimental results of real video data demonstrate the efficacy of the proposed people monitoring system.

Edge-preserving color image interpolation using spatial and spectral correlations

Abstract We propose in this paper a new and effective method to interpolate digital color images by exploiting inherent image spatial and spectral correlations. The proposed method consists of two main steps: interpolating the green image plane based on local spatial correlation within the plane, and interpolating red and blue image planes based on spectral correlation between different color planes. When compared with conventional and contemporary methods of color image interpolation, our proposed method can better preserve image attributes that have great influence on visual quality of interpolated color images, in particular edge sharpness and color consistency.