Search

Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand segmentation. Here, we focus on appearance gaps for hand regions and backgrounds separately. We propose (i) foreground-aware image stylization and (ii) consensus pseudo-labeling for domain adaptation of hand segmentation. We stylize source images independently for the foreground and background using target images as style. To resolve the domain shift that the stylization has not addressed, we apply careful pseudo-labeling by taking a consensus between the models trained on the source and stylized source images. We validated our method on domain adaptation of hand segmentation from real and simulation images. Our method achieved state-of-the-art performance in both settings. We also demonstrated promising results in challenging multi-target domain adaptation and domain generalization settings. Code is available at https://github.com/ut-vision/FgSty-CPL., Comment: Accepted to IEEE Access 2021

This paper presents CoSummary, an adaptive video fast-forwarding technique for browsing surgical videos recorded by wearable cameras. Current wearable technologies allow us to record complex surgical skills, however, an efficient browsing technique for these videos is not well established. In order to assist browsing surgical videos, our study focuses on adaptively changing playback speeds through the learning and detecting collaborative scenes based on surgeon hand placement and gaze information. Our evaluation shows that the proposed method is able to highlight important collaborative scenes and skip less important scenes during surgical procedures. We have also performed a subjective study with surgeons in order to have professional feedback. The results confirmed the effectiveness of the proposed method in comparison to uniform video fast-forwarding.

Eye gaze estimation is increasingly demanded by recent intelligent systems to facilitate a range of interactive applications. Unfortunately, learning the highly complicated regression from a single eye image to the gaze direction is not trivial. Thus, the problem is yet to be solved efficiently. Inspired by the two-eye asymmetry as two eyes of the same person may appear uneven, we propose the face-based asymmetric regression-evaluation network (FARE-Net) to optimize the gaze estimation results by considering the difference between left and right eyes. The proposed method includes one face-based asymmetric regression network (FAR-Net) and one evaluation network (E-Net). The FAR-Net predicts 3D gaze directions for both eyes and is trained with the asymmetric mechanism, which asymmetrically weights and sums the loss generated by two-eye gaze directions. With the asymmetric mechanism, the FAR-Net utilizes the eyes that can achieve high performance to optimize network. The E-Net learns the reliabilities of two eyes to balance the learning of the asymmetric mechanism and symmetric mechanism. Our FARE-Net achieves leading performances on MPIIGaze, EyeDiap and RT-Gene datasets. Additionally, we investigate the effectiveness of FARE-Net by analyzing the distribution of errors and ablation study.

Recently, many hyperspectral (HS) image superresolution methods that merge a low spatial resolution HS image and a high spatial resolution three-channel RGB image have been proposed in spectral imaging. A largely ignored fact is that most existing commercial RGB cameras capture high resolution images by a single CCD/CMOS sensor equipped with a color filter array (CFA). In this paper, we account for the common imaging mechanism of commercial RGB cameras, and propose to use a mosaic RGB image for HS image super-resolution, which prevents demosaicing error and thus its propagation into the HS image super-resolution results. We design a proper nonlocal low-rank regularization to exploit the intrinsic properties - rich self-repeating patterns and high correlation across spectra - within HS images of natural scenes, and formulate the HS image super-resolution task into a variational optimization problem, which can be efficiently solved via the alternating direction method of multipliers (ADMM). The effectiveness of the proposed method has been evaluated on two benchmark datasets, demonstrating that the proposed method can provide substantial improvement over the current state-of-the-art HS image superresolution methods without considering the mosaicing effect. Finally, we show that our method can also perform well in the real capture system.

This paper presents an egocentric vision (ego-vision) system for hand grasp analysis in unstructured environments. Our goal is to automatically recognize hand grasp types and to discover the visual structures of hand grasps using a wearable camera. In the proposed system, free hand–object interactions are recorded from a first-person viewing perspective. State-of-the-art computer vision techniques are used to detect hands and extract hand-based features. A new feature representation that incorporates hand tracking information is also proposed. Then, grasp classifiers are trained to discriminate among different grasp types from a predefined grasp taxonomy. Based on the trained grasp classifiers, visual structures of hand grasps are learned using an iterative grasp clustering method. In experiments, grasp recognition performance in both laboratory and real-world scenarios is evaluated. The best classification accuracy our system achieves is $\text{92}\%$ and $\text{59}\%$ , respectively. System generality to different tasks and users is also verified by the experiments. Analysis in a real-world scenario shows that it is possible to automatically learn intuitive visual grasp structures that are consistent with expert-designed grasp taxonomies.

Aiming at reducing the restrictions due to person/scene dependence, we deliver a novel method that solves appearance-based gaze estimation in a novel fashion. First, we introduce and solve an "uncalibrated gaze pattern" solely from eye images independent of the person and scene. The gaze pattern recovers gaze movements up to only scaling and translation ambiguities, via nonlinear dimension reduction and pixel motion analysis, while no training/calibration is needed. This is new in the literature and enables novel applications. Second, our method allows simple calibrations to align the gaze pattern to any gaze target. This is much simpler than conventional calibrations which rely on sufficient training data to compute person and scene-specific nonlinear gaze mappings. Through various evaluations, we show that: 1) the proposed uncalibrated gaze pattern has novel and broad capabilities; 2) the proposed calibration is simple and efficient, and can be even omitted in some scenarios; and 3) quantitative evaluations produce promising results under various conditions.

In recent years, fluorescence analysis of scenes has received attention in computer vision. Fluorescence can provide additional information about scenes, and has been used in applications such as camera spectral sensitivity estimation, 3D reconstruction, and color relighting. In particular, hyperspectral images of reflective-fluorescent scenes provide a rich amount of data. However, due to the complex nature of fluorescence, hyperspectral imaging methods rely on specialized equipment such as hyperspectral cameras and specialized illuminants. In this paper, we propose a more practical approach to hyperspectral imaging of reflective-fluorescent scenes using only a conventional RGB camera and varied colored illuminants. The key idea of our approach is to exploit a unique property of fluorescence: the chromaticity of fluorescent emissions are invariant under different illuminants. This allows us to robustly estimate spectral reflectance and fluorescent emission chromaticity. We then show that given the spectral reflectance and fluorescent chromaticity, the fluorescence absorption and emission spectra can also be estimated. We demonstrate in results that all scene spectra can be accurately estimated from RGB images. Finally, we show that our method can be used to accurately relight scenes under novel lighting.

Hyperspectral imaging is beneficial in a diverse range of applications from diagnostic medicine, to agriculture, to surveillance to name a few. However, hyperspectral images often suffer from degradation such as noise and low resolution. In this paper, we propose an effective model for hyperspectral image (HSI) restoration, specifically image denoising and super-resolution. Our model considers three underlying characteristics of HSIs: sparsity across the spatial-spectral domain, high correlation across spectra, and non-local self-similarity over space. We first exploit high correlation across spectra and non-local self-similarity over space in the degraded HSI to learn an adaptive spatial-spectral dictionary. Then, we employ the local and non-local sparsity of the HSI under the learned spatial-spectral dictionary to design an HSI restoration model, which can be effectively solved by an iterative numerical algorithm with parameters that are adaptively adjusted for different clusters and different noise levels. In experiments on HSI denoising, we show that the proposed method outperforms many state-of-the-art methods under several comprehensive quantitative assessments. We also show that our method performs well on HSI super-resolution.

This paper presents an unconstrained gaze estimation method using an online learning algorithm. We focus on a desktop scenario, where a user operates a personal computer, and use the mouse-clicked positions to infer, where on the screen the user is looking at. Our method continuously captures the user's head pose and eye images with a monocular camera, and each mouse click triggers learning sample acquisition. In order to handle head pose variations, the samples are adaptively clustered according to the estimated head pose. Then, local reconstruction-based gaze estimation models are incrementally updated in each cluster. We conducted a prototype evaluation in real-world environments, and our method achieved an estimation accuracy of 2.9 $^\circ$ .

In this paper, we address the problem of free head motion in appearance-based gaze estimation. This problem remains challenging because head motion changes eye appearance significantly, and thus, training images captured for an original head pose cannot handle test images captured for other head poses. To overcome this difficulty, we propose a novel gaze estimation method that handles free head motion via eye image synthesis based on a single camera. Compared with conventional fixed head pose methods with original training images, our method only captures four additional eye images under four reference head poses, and then, precisely synthesizes new training images for other unseen head poses in estimation. To this end, we propose a single-directional (SD) flow model to efficiently handle eye image variations due to head motion. We show how to estimate SD flows for reference head poses first, and then use them to produce new SD flows for training image synthesis. Finally, with synthetic training images, joint optimization is applied that simultaneously solves an eye image alignment and a gaze estimation. Evaluation of the method was conducted through experiments to assess its performance and demonstrate its effectiveness.

Spectral analysis of natural scenes can provide much more detailed information about the scene than an ordinary RGB camera. The richer information provided by hyperspectral images has been beneficial to numerous applications, such as understanding natural environmental changes and classifying plants and soils in agriculture based on their spectral properties. In this paper, we present an efficient manifold learning based method for accurately reconstructing a hyperspectral image from a single RGB image captured by a commercial camera with known spectral response. By applying a nonlinear dimensionality reduction technique to a large set of natural spectra, we show that the spectra of natural scenes lie on an intrinsically low dimensional manifold. This allows us to map an RGB vector to its corresponding hyperspectral vector accurately via our proposed novel manifold-based reconstruction pipeline. Experiments using both synthesized RGB images using hyperspectral datasets and real world data demonstrate our method outperforms the state-of-the-art.

This work aims to develop a computer-vision technique for understanding objects jointly attended by a group of people during social interactions. As a key tool to discover such objects of joint attention, we rely on a collection of wearable eye-tracking cameras that provide a first-person video of interaction scenes and points-of-gaze data of interacting parties. Technically, we propose a hierarchical conditional random field-based model that can 1) localize events of joint attention temporally and 2) segment objects of joint attention spatially. We show that by alternating these two procedures, objects of joint attention can be discovered reliably even from cluttered scenes and noisy points-of-gaze data. Experimental results demonstrate that our approach outperforms several state-of-the-art methods for co-segmentation and joint attention discovery.

We propose a new multi-frame method for efficiently computing scene flow (dense depth and optical flow) and camera ego-motion for a dynamic scene observed from a moving stereo camera rig. Our technique also segments out moving objects from the rigid scene. In our method, we first estimate the disparity map and the 6-DOF camera motion using stereo matching and visual odometry. We then identify regions inconsistent with the estimated camera motion and compute per-pixel optical flow only at these regions. This flow proposal is fused with the camera motion-based flow proposal using fusion moves to obtain the final optical flow and motion segmentation. This unified framework benefits all four tasks - stereo, optical flow, visual odometry and motion segmentation leading to overall higher accuracy and efficiency. Our method is currently ranked third on the KITTI 2015 scene flow benchmark. Furthermore, our CPU implementation runs in 2-3 seconds per frame which is 1-3 orders of magnitude faster than the top six methods. We also report a thorough evaluation on challenging Sintel sequences with fast camera and object motion, where our method consistently outperforms OSF [Menze and Geiger, 2015], which is currently ranked second on the KITTI benchmark., 15 pages. To appear at IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017). Our results were submitted to KITTI 2015 Stereo Scene Flow Benchmark in November 2016

Cell image analysis is important for research and discovery in biology and medicine. In this paper, we present our cell tracking methods, which is capable of obtaining fine-grain cell behavior metrics. In order to address difficulties under dense culture conditions, where cell detection cannot be done reliably since cell often touch with blurry intercellular boundaries, we proposed two methods which are global data association and jointly solving cell detection and association. We also show the effectiveness of the proposed methods by applying the method to the biological researches.

We investigate the appearance-based gaze estimation problem, with respect to its essential difficulty in reducing the number of required training samples, and other practical issues such as slight head motion, image resolution variation, and eye blinking. We cast the problem as mapping high-dimensional eye image features to low-dimensional gaze positions, and propose an adaptive linear regression (ALR) method as the key to our solution. The ALR method adaptively selects an optimal set of sparsest training samples for the gaze estimation via ℓ(1)-optimization. In this sense, the number of required training samples is significantly reduced for high accuracy estimation. In addition, by adopting the basic ALR objective function, we integrate the gaze estimation, subpixel alignment and blink detection into a unified optimization framework. By solving these problems simultaneously, we successfully handle slight head motion, image resolution variation and eye blinking in appearance-based gaze estimation. We evaluated the proposed method by conducting experiments with multiple users and variant conditions to verify its effectiveness.

When estimating human gaze directions from captured eye appearances, most existing methods assume a fixed head pose because head motion changes eye appearance greatly and makes the estimation inaccurate. To handle this difficult problem, in this paper, we propose a novel method that performs accurate gaze estimation without restricting the user's head motion. The key idea is to decompose the original free-head motion problem into subproblems, including an initial fixed head pose problem and subsequent compensations to correct the initial estimation biases. For the initial estimation, automatic image rectification and joint alignment with gaze estimation are introduced. Then compensations are done by either learning-based regression or geometric-based calculation. The merit of using such a compensation strategy is that the training requirement to allow head motion is not significantly increased; only capturing a 5-s video clip is required. Experiments are conducted, and the results show that our method achieves an average accuracy of around 3^o by using only a single camera.

Spectral reflectance is an intrinsic characteristic of objects that is independent of illumination and the used imaging sensors. This direct representation of objects is useful for various computer vision tasks, such as color constancy and material discrimination. In this work, we present a novel system for spectral reflectance recovery with high temporal resolution by exploiting the unique color-forming mechanism of digital light processing (DLP) projectors. DLP projectors use color wheels, which are composed of a number of color segments and rotate quickly to produce the desired colors. Making effective use of this mechanism, we show that a DLP projector can be used as a light source with spectrally distinct illuminations when the appearance of a scene under the projector's irradiation is captured with a high-speed camera. Based on the measurements, the spectral reflectance of scene points can be recovered using a linear approximation of the surface reflectance. Our imaging system is built from off-the-shelf devices, and is capable of taking multi-spectral measurements as fast as 100 Hz. We carefully evaluated the accuracy of our system and demonstrated its effectiveness by spectral relighting of static as well as dynamic scenes containing different objects.

This paper presents an appearance-based method for estimating head direction that automatically adapts to individual scenes. Appearance-based estimation methods usually require a ground-truth dataset taken from a scene that is similar to test video sequences. However, it is almost impossible to acquire many manually labeled head images for each scene. We introduce an approach that automatically aggregates labeled head images by inferring head direction labels from walking direction. Furthermore, in order to deal with large variations that occur in head appearance even within the same scene, we introduce an approach that segments a scene into multiple regions according to the similarity of head appearances. Experimental results demonstrate that our proposed method achieved higher accuracy in head direction estimation than conventional approaches that use a scene-independent generic dataset.

We propose a gaze sensing method using visual saliency maps that does not need explicit personal calibration. Our goal is to create a gaze estimator using only the eye images captured from a person watching a video clip. Our method treats the saliency maps of the video frames as the probability distributions of the gaze points. We aggregate the saliency maps based on the similarity in eye images to efficiently identify the gaze points from the saliency maps. We establish a mapping between the eye images to the gaze points by using Gaussian process regression. In addition, we use a feedback loop from the gaze estimator to refine the gaze probability maps to improve the accuracy of the gaze estimation. The experimental results show that the proposed method works well with different people and video clips and achieves a 3.5-degree accuracy, which is sufficient for estimating a user's attention on a display.

We propose uncalibrated photometric stereo methods that address the problem due to unknown isotropic reflectance. At the core of our methods is the notion of “constrained half-vector symmetry” for general isotropic BRDFs. We show that such symmetry can be observed in various real-world materials, and it leads to new techniques for shape and light source estimation. Based on the 1D and 2D representations of the symmetry, we propose two methods for surface normal estimation; one focuses on accurate elevation angle recovery for surface normals when the light sources only cover the visible hemisphere, and the other for comprehensive surface normal optimization in the case that the light sources are also non-uniformly distributed. The proposed robust light source estimation method also plays an essential role to let our methods work in an uncalibrated manner with good accuracy. Quantitative evaluations are conducted with both synthetic and real-world scenes, which produce the state-of-the-art accuracy for all of the non-Lambertian materials in MERL database and the real-world datasets.

Our goal is to automate the understanding of natural hand-object manipulation by developing computer visionbased techniques. Our hypothesis is that it is necessary to model the grasp types of hands and the attributes of manipulated objects in order to accurately recognize manipulation actions. Specifically, we focus on recognizing hand grasp types, object attributes and actions from a single image within an unified model. First, we explore the contextual relationship between grasp types and object attributes, and show how that context can be used to boost the recognition of both grasp types and object attributes. Second, we propose to model actions with grasp types and object attributes based on the hypothesis that grasp types and object attributes contain complementary information for characterizing different actions. Our proposed action model outperforms traditional appearance-based models which are not designed to take into account semantic constraints such as grasp types or object attributes. Experiment results on public egocentric activities datasets strongly support our hypothesis.

Describing the color and textural information of a person image is one of the most crucial aspects of person re-identification. In this paper, we present a novel descriptor based on a hierarchical distribution of pixel features. A hierarchical covariance descriptor has been successfully applied for image classification. However, the mean information of pixel features, which is absent in covariance, tends to be major discriminative information of person images. To solve this problem, we describe a local region in an image via hierarchical Gaussian distribution in which both means and covariances are included in their parameters. More specifically, we model the region as a set of multiple Gaussian distributions in which each Gaussian represents the appearance of a local patch. The characteristics of the set of Gaussians are again described by another Gaussian distribution. In both steps, unlike the hierarchical covariance descriptor, the proposed descriptor can model both the mean and the covariance information of pixel features properly. The results of experiments conducted on five databases indicate that the proposed descriptor exhibits re-markably high performance which outperforms the state-of-the-art descriptors for person re-identification.

Conventional scanning and multiplexing techniques for hyperspectral imaging suffer from limited temporal and/or spatial resolution. To resolve this issue, coding techniques are becoming increasingly popular in developing snapshot systems for high-resolution hyperspectral imaging. For such systems, it is a critical task to accurately restore the 3D hyperspectral image from its corresponding coded 2D image. In this paper, we propose an effective method for coded hyperspectral image restoration, which exploits extensive structure sparsity in the hyperspectral image. Specifically, we simultaneously explore spectral and spatial correlation via low-rank regularizations, and formulate the restoration problem into a variational optimization model, which can be solved via an iterative numerical algorithm. Experimental results using both synthetic data and real images show that the proposed method can significantly outperform the state-of-the-art methods on several popular coding-based hyperspectral imaging systems.

The goal of this work is to discover objects of joint attention, i.e., objects being viewed by multiple people using head-mounted cameras and eye trackers. Such objects of joint attention are expected to act as an important cue for understanding social interactions in everyday scenes. To this end, we develop a commonality-clustering method tailored to first-person videos combined with points-of-gaze sources. The proposed method uses multiscale spatiotemporal tubes around points of gaze as a candidate of objects, making it possible to deal with various sizes of objects observed in the first-person videos. We also introduce a new dataset of multiple pairs of first-person videos and points-of-gaze data. Our experimental results show that our approach can outperform several state-of-the-art commonality-clustering methods.

We aim to understand the dynamics of social interactions between two people by recognizing their actions and reactions using a head-mounted camera. Our work will impact several first-person vision tasks that need the detailed understanding of social interactions, such as automatic video summarization of group events and assistive systems. To recognize micro-level actions and reactions, such as slight shifts in attention, subtle nodding, or small hand actions, where only subtle body motion is apparent, we propose to use paired egocentric videos recorded by two interacting people. We show that the first-person and second-person points-of-view features of two people, enabled by paired egocentric videos, are complementary and essential for reliably recognizing micro-actions and reactions. We also build a new dataset of dyadic (two-persons) interactions that comprises more than 1000 pairs of egocentric videos to enable systematic evaluations on the task of micro-action and reaction recognition.

In this work, we investigate how remote collaboration between a local worker and a remote collaborator will change if eye fixations of the collaborator are presented to the worker. We track the collaborator's points of gaze on a monitor screen displaying a physical workspace and visualize them onto the space by a projector or through an optical see-through head-mounted display. Through a series of user studies, we have found the followings: 1) Eye fixations can serve as a fast and precise pointer to objects of the collaborator's interest. 2) Eyes and other modalities, such as hand gestures and speech, are used differently for object identification and manipulation. 3) Eyes are used for explicit instructions only when they are combined with speech. 4) The worker can predict some intentions of the collaborator such as his/her current interest and next instruction.

We present an accurate stereo matching method using local expansion moves based on graph cuts. This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms. The local expansion moves are presented as many alpha-expansions defined for small grid regions. The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation. By localization, we use different candidate alpha-labels according to the locations of local alpha-expansions. By spatial propagation, we design our local alpha-expansions to propagate currently assigned labels for nearby regions. With this localization and spatial propagation, our method can efficiently infer MRF models with a continuous label space using randomized search. Our method has several advantages over previous approaches that are based on fusion moves or belief propagation; it produces submodular moves deriving a subproblem optimality; it helps find good, smooth, piecewise linear disparity maps; it is suitable for parallelization; it can use cost-volume filtering techniques for accelerating the matching cost computations. Even using a simple pairwise MRF, our method is shown to have best performance in the Middlebury stereo benchmark V2 and V3., 14 pages. An extended version of our preliminary conference paper [39], Taniai et al. "Graph Cut based Continuous Stereo Matching using Locally Shared Labels" in the proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014). Our results were submitted to Middlebury Stereo Benchmark Version 2 on April 22, 2015, and to Version 3 on July 4, 2017

SUMMARY The ability to find the speaker’s face region in a video is useful for various applications. In this work, we develop a novel technique tofind this region within different time windows, which is robust against the changes of view, scale, and background. The main thrust of our technique is to integrate audiovisual correlation analysis into a video segmentation framework. We analyze the audiovisual correlation locally by computing quadratic mutual information between our audiovisual features. The computation of quadratic mutual information is based on the probability density functions estimated by kernel density estimation with adaptive kernel bandwidth. The results of this audiovisual correlation analysis are incorporated into graph cut-based video segmentation to resolve a globally optimum extraction of the speaker’s face region. The setting of any heuristic threshold in this segmentation is avoided by learning the correlation distributions of speaker and background by expectation maximization. Experimental results demonstrate that our method can detect the speaker’s face region accurately and robustly for different views, scales, and backgrounds.

We present a novel technique for enhancing an image captured in low light by using near-infrared flash images. The main idea is to combine a color image with near-infrared flash images captured at the same time without causing any interference with the color image. In this work, near-infrared flash images are effectively used for removing annoying effects that are commonly observed in images of dimly lit environments, namely, image noise and motion blur. Our denoising method uses a pair of color and near-infrared flash images captured simultaneously. Therefore it is applicable to dynamic scenes, whereas existing methods assume stationary scenes and require a pair of flash and no-flash color images captured sequentially. Our deblurring method utilizes a set of near-infrared flash images captured during the exposure time of a single color image and directly acquires a motion blur kernel based on optical flow. We implemented a multispectral imaging system and confirmed the effectiveness of our technique through experiments using real images.

In this paper, we propose a method for pose-invariant facial expression recognition from monocular video sequences. The advantage of our method is that, unlike existing methods, our method uses a simple model, called the variable-intensity template, for describing different facial expressions. This makes it possible to prepare a model for each person with very little time and effort. Variable-intensity templates describe how the intensities of multiple points, defined in the vicinity of facial parts, vary with different facial expressions. By using this model in the framework of a particle filter, our method is capable of estimating facial poses and expressions simultaneously. Experiments demonstrate the effectiveness of our method. A recognition rate of over 90% is achieved for all facial orientations, horizontal, vertical, and in-plane, in the range of ±40 degrees, ±20 degrees, and ±40 degrees from the frontal view, respectively.

This chapter introduces new techniques we developed for sensing and guiding human gaze non-invasively in daily living space. Such technologies are the key to realize human-harmonized information systems which can provide us various kinds of supports effectively without distracting our activities. Toward the goal of realizing non-invasive gaze sensing, we developed gaze estimation techniques, which requires very limited or no calibration effort by exploiting various cues such as spontaneous attraction of our visual attention to visual stimuli. For shifting our gaze to desired locations in a non-disturbing and natural way, we exploited two approaches for gaze control: subtle modulation of visual stimuli based on visual saliency models, and non-verbal gestures in human-robot interactions.

The appearance of an object greatly changes under different lighting conditions. Even so, previous studies have demonstrated that the appearance of an object under varying illumination conditions can be represented by a linear subspace. A set of basis images spanning such a linear subspace can be obtained by applying the principal component analysis (PCA) for a large number of images taken under different lighting conditions. Since little is known about how to sample the appearance of an object in order to correctly obtain its basis images, it was a common practice to use as many input images as possible. In this study, we present a novel method for analytically obtaining a set of basis images of an object for varying illumination from input images of the object taken properly under a set of light sources, such as point light sources or extended light sources. Our proposed method incorporates the sampling theorem of spherical harmonics for determining a set of lighting directions to efficiently sample the appearance of an object. We further consider the issue of aliasing caused by insufficient sampling of the object's appearance. In particular, we investigate the effectiveness of using extended light sources for modeling the appearance of an object under varying illumination without suffering the aliasing caused by insufficient sampling of its appearance.

Hyperspectral imaging is beneficial in a diverse range of applications from diagnostic medicine, to agriculture, to surveillance to name a few. However, hyperspectral images often times suffer from degradation due to the limited light, which introduces noise into the imaging process. In this paper, we propose an effective model for hyperspectral image (HSI) denoising that considers underlying characteristics of HSIs: sparsity across the spatial-spectral domain, high correlation across spectra, and non-local self-similarity over space. We first exploit high correlation across spectra and non-local self-similarity over space in the noisy HSI to learn an adaptive spatial-spectral dictionary. Then, we employ the local and non-local sparsity of the HSI under the learned spatial-spectral dictionary to design an HSI denoising model, which can be effectively solved by an iterative numerical algorithm with parameters that are adaptively adjusted for different clusters and different noise levels. Experimental results on HSI denoising show that the proposed method can provide substantial improvements over the current state-of-the-art HSI denoising methods in terms of both objective metric and subjective visual quality.

This paper introduces a novel method to separate fluorescent and reflective components in the spectral domain. In contrast to existing methods, which require to capture two or more images under varying illuminations, we aim to achieve this separation task by using a single hyperspectral image. After identifying the critical hurdle in single-image component separation, we mathematically design the optimal illumination spectrum, which is shown to contain substantial high-frequency components in the frequency domain. This observation, in turn, leads us to recognize a key difference between reflectance and fluorescence in response to the frequency modulation effect of illumination, which fundamentally explains the feasibility of our method. On the practical side, we successfully find an off-the-shelf lamp as the light source, which is strong in irradiance intensity and cheap in cost. A fast linear separation algorithm is developed as well. Experiments using both synthetic data and real images have confirmed the validity of the selected illuminant and the accuracy of our separation algorithm.

We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances. Our method uses a pixel intensity profile, which is a sequence of radiance intensities recorded at a pixel under unknown varying directional illumination. We show that for general isotropic materials and uniformly distributed light directions, the geodesic distance between intensity profiles is linearly related to the angular difference of their corresponding surface normals, and that the intensity distribution of the intensity profile reveals reflectance properties. Based on these observations, we develop two methods for surface normal estimation; one for a general setting that uses only the recorded intensity profiles, the other for the case where a BRDF database is available while the exact BRDF of the target scene is still unknown. Quantitative and qualitative evaluations are conducted using both synthetic and real-world scenes, which show the state-of-the-art accuracy of smaller than $10$ degree without using reference data and $5$ degree with reference data for all $100$ materials in MERL database.

In this paper, we proposed a novel edge-based method for intrinsic image decomposition. To be specific, to address this ill-posed problem via single image, we employed the information of chromaticity gradient to guide recovering the reflectance gradient map, and regularized the Retinex assumption by the l 0 -norm to render the reflectance layer piece-wise smooth. Our method is simple but effective. Qualitative together with quantitative experiments were carried out on some public datasets. The comparison results show that our method runs much faster than the state-of-art methods with comparable performance.

This paper addresses the problem of uncalibrated photometric stereo with isotropic reflectances. Existing methods face difficulty in solving for the elevation angles of surface normals when the light sources only cover the visible hemisphere. Here, we introduce the notion of “constrained half-vector symmetry” for general isotropic BRDFs and show its capability of elevation angle recovery. This sort of symmetry can be observed in a 1D BRDF slice from a subset of surface normals with the same azimuth angle, and we use it to devise an efficient modeling and solution method to constrain and recover the elevation angles of surface normals accurately. To enable our method to work in an uncalibrated manner, we further solve for light sources in the case of general isotropic BRDFs. By combining this method with the existing ones for azimuth angle estimation, we can get state-of-the-art results for uncalibrated photometric stereo with general isotropic reflectances.

This paper addresses the illumination and reflectance spectra separation (IRSS) problem of a hyperspectral image captured under general spectral illumination. The huge amount of pixels in a hypersepctral image poses tremendous challenges on computational efficiency, yet in turn offers greater color variety that might be utilized to improve separation accuracy and relax the restrictive subspace illumination assumption in existing works. We show that this IRSS problem can be modeled into a low-rank matrix factorization problem, and prove that the separation is unique up to an unknown scale under the standard low-dimensionality assumption of reflectance. We also develop a scalable algorithm for this separation task that works in the presence of model error and image noise. Experiments on both synthetic data and real images have demonstrated that our separation results are sufficiently accurate, and can benefit some important applications, such as spectra relighting and illumination swapping.

Our goal is to automatically recognize hand grasps and to discover the visual structures (relationships) between hand grasps using wearable cameras. Wearable cameras provide a first-person perspective which enables continuous visual hand grasp analysis of everyday activities. In contrast to previous work focused on manual analysis of first-person videos of hand grasps, we propose a fully automatic vision-based approach for grasp analysis. A set of grasp classifiers are trained for discriminating between different grasp types based on large margin visual predictors. Building on the output of these grasp classifiers, visual structures among hand grasps are learned based on an iterative discriminative clustering procedure. We first evaluated our classifiers on a controlled indoor grasp dataset and then validated the analytic power of our approach on real-world data taken from a machinist. The average F1 score of our grasp classifiers achieves over 0.80 for the indoor grasp dataset. Analysis of real-world video shows that it is possible to automatically learn intuitive visual grasp structures that are consistent with expert-designed grasp taxonomies.

In this paper, we introduce a method for recovering an illumination distribution of a scene from image brightness inside shadows cast by an object of known shape in the scene. In a natural illumination condition, a scene includes both direct and indirect illumination distributed in a complex way, and it is often difficult to recover an illumination distribution from image brightness observed on an object surface. The main reason for this difficulty is that there is usually not adequate variation in the image brightness observed on the object surface to reflect the subtle characteristics of the entire illumination. In this study, we demonstrate the effectiveness of using occluding information of incoming light in estimating an illumination distribution of a scene. Shadows in a real scene are caused by the occlusion of incoming light and, thus, analyzing the relationships between the image brightness and the occlusions of incoming light enables us to reliably estimate an illumination distribution of a scene even in a complex illumination environment. This study further concerns the following two issues that need to be addressed. First, the method combines the illumination analysis with an estimation of the reflectance properties of a shadow surface. This makes the method applicable to the case where reflectance properties of a surface are not known a priori and enlarges the variety of images applicable to the method. Second, we introduce an adaptive sampling framework for efficient estimation of illumination distribution. Using this framework, we are able to avoid a unnecessarily dense sampling of the illumination and can estimate the entire illumination distribution more efficiently with a smaller number of sampling directions of the illumination distribution. To demonstrate the effectiveness of the proposed method, we have successfully tested the proposed method by using sets of real images taken in natural illumination conditions with different surface materials of shadow regions.

Augmented desk interfaces and other virtual reality systems depend on accurate, real-time hand and fingertip tracking for seamless integration between real objects and associated digital information. We introduce a method for discerning fingertip locations in image frames and measuring fingertip trajectories across image frames. We also propose a mechanism for combining direct manipulation and symbolic gestures based on multiple fingertip motions. Our method uses a filtering technique, in addition to detecting fingertips in each image frame, to predict fingertip locations in successive image frames and to examine the correspondences between the predicted locations and detected fingertips. This lets us obtain multiple complex fingertip trajectories in real time and improves fingertip tracking. This method can track multiple fingertips reliably even on a complex background under changing lighting conditions without invasive devices or color markers.

Color quantization is a technique for decreasing the color depth of an image. Less number of color means less space is needed for storage. Such kind of algorithms ([Heckbert 1982], [Verevka and Buchanan 1995]) have invoked a big interest in the computer science domain especially for researchers in the network field, since color reduction could benefit hardware and network resources. However, few of the existing color reduction algorithms consider preservation of image details while reducing color depth.

In this talk, I will describe our recent works on human visual attention from three aspects: sensing, predicting, and utilizing visual attention. Over the last two decades, the concept of visual saliency and its computational models have attracted a lot of interest, inspired by the seminal work by Koch and Ullman on a computational model of visual saliency. Visual saliency models predict our eye fixations driven by our vision system's bottom-up control triggered by visual stimuli, and it has been shown experimentally that a visual saliency map computed by a visual saliency model is highly correlated with an actual distribution of our fixation points. Based on this observation, we introduce a method for estimating gaze directions using visual saliency maps without explicit personal calibration. The key idea is to use the saliency maps of the video frames that a person is looking at as the probability distributions of the gaze points so that we can avoid cumbersome calibration procedures asking a user to fixate calibration targets. I will explain the details of our method and experimental results. I will also talk about our recent attempt to develop a new computational model of visual saliency for better accuracy in predicting gaze fixation points. Unlike the existing visual saliency models, our model elaborates the fact that the characteristics of human eyes vary significantly within the visual field, e.g., fovea and peripheral vision. Experiments using human fixation data in a wide field of view setting demonstrate that our visual saliency model achieves higher accuracy than a current state-of-the-art model. Lastly, we briefly talk about several applications of eye movements for activity recognition and image analysis.