Shrinivas Pundlik

Schepens Eye Research Institute

The regular full-length version of the letter paper "Low-cost real-time VLSI system for high-accuracy optical flow estimation using biological motion features and random forests"

This study proposes a low-cost, real-time, very large-scale integration (VLSI) architecture for optical flow estimation. The architecture adopts parallel spatiotemporal filters to extract bio-inspired motion features at each pixel location and uses hardware random forests to infer the motion speed. Our system achieves higher estimation accuracy at...

Purpose To investigate whether head-mounted vision assistance devices may address a different set of visual needs as compared to handheld video magnifiers. Methods Daily app usage data (e.g. launch frequency, duration, among others) across 8 months was collected from tens of thousands global active users of two mobile vision assistance apps: handh...

Tracking head movement in outdoor activities is more challenging than in controlled indoor lab environments. Large-magnitude head scanning is common under natural conditions. Compensatory gaze (head and eye) scanning while walking may be critical for people with visual field loss. We compared the accuracy of two outdoor head tracking methods: diffe...

Dark adaptation (DA) refers to the slow recovery of visual sensitivity in darkness following exposure to intense or prolonged illumination, which bleaches a significant amount of the rhodopsin. This natural process also offers an opportunity to understand cellular function in the outer retina and evaluate for presence of disease. How our eyes adapt...

Purpose: Quantification of dark adaptation (DA) response using the conventional rod intercept time (RIT) requires very long testing time and may not be measurable in the presence of impairments due to diseases such as age-related macular degeneration (AMD). The goal of this study was to investigate the advantages of using area under the DA curve (...

Background: Millions of visually impaired use mobile vision assistance apps to help with their daily activities. The most widely used vision assistance apps are magnifier apps. It is still largely unknown what the apps are used for. Lack of insight in the visual needs of visually impaired people is a hurdle for development of more effective assist...

Purpose To evaluate the effect of central serous chorioretinopathy (CSCR) on retinal function using dark adaptation in a human subject, and to follow it through resolution of the disease. Patients Single patient, 50 years old male patient, with acute CSCR in one eye and resolved old CSCR in the other eye. Observations Observational study in patie...

Background Strabismus is the leading risk factor for amblyopia, which should be early detected for minimized visual impairment. However, traditional school screening for strabismus can be challenged due to several factors, most notably training, mobility and cost. The purpose of our study is to evaluate the feasibility of using a smartphone applica...

Background: Strabismus is the leading risk factor for amblyopia, which should be early detected for minimized visual impairment. However, traditional school screening for strabismus can be challenged due to several factors, most notably training, mobility and cost. The purpose of our study is to evaluate the feasibility of using a smartphone applic...

Objective To describe and evaluate a secure video call system combined with a suite of iPad vision testing apps to improve access to vision rehabilitation assessment for inpatients. Design Retrospective. Setting Two acute care inpatient rehabilitation hospitals (AR1 and AR2) and 1 long-term acute care hospital (LTAC). Participants Records of inp...

A normally sighted person can see a grating of 30 cycles per degree or higher, but spatial frequencies needed for motion perception are much lower than that. It is unknown for natural images with a wide spectrum how all the visible spatial frequencies contribute to motion speed perception. In this work, we studied the effect of spatial frequency co...

Significance: To judge the feasibility of virtual reality (VR) headsets for vision testing and treatment of binocular vision disorders and low vision, angular resolution (logMAR) and field of view must be known and may not be reliably provided. This is the first study to measure the limitations of VR systems for eye care applications. Purpose: T...

Purpose: Evaluating mobility aids in naturalistic conditions across many days is challenging owing to the sheer amount of data and hard-to-control environments. For a wearable video camera-based collision warning device, we present the methodology for acquisition, reduction, review, and coding of video data for quantitative analyses of mobility ou...

A smartphone app has been developed to perform the automated photographic Hirschberg test for objective measurement of ocular misalignment. By computing the difference in corneal reflection generated by the phone camera flash relative to the iris center based on high resolution images, the app can measure misalignment with a much higher precision t...

SIGNIFICANCE To judge the feasibility of virtual reality (VR) headsets for vision testing and treatment of binocular vision disorders and low vision, angular resolution (LogMAR) and field of view must be known and may not be reliably provided. This is the first study to measure the limitations of VR systems. PURPOSE To measure, in a sample of VR he...

Keyword search in a cluttered environment is difficult in general, and even more challenging for people with low vision. While magnification can help in reading for low vision people, it does not facilitate efficient visual search due to the constriction of the field of view. The motivating observation for this study is that, in a large number of v...

This work proposes a hardware-friendly, dense optical flow-based Time-to-Collision (TTC) estimation algorithm intended to be deployed on smart video sensors for collision avoidance. The algorithm optimized for hardware first extracts biological visual motion features (motion energies), and then utilizes a Random Forests regressor to predict robust...

Purpose: We evaluate a smartphone application (app) performing an automated photographic Hirschberg test for measurement of eye deviations. Methods: Three evaluation studies were conducted to measure eye deviations in the horizontal direction. First, gaze angles were measured with respect to the ground truth in nonstrabismic subjects (n = 25) as...

Purpose: We evaluated the feasibility of a smartphone application-based dark adaptation (DA) measurement method (MOBILE-DA). Methods: On a Samsung Galaxy S8 smartphone, MOBILE-DA presented a 1.5° flashing stimulus (wavelength = 453 nm) between -1.15 and -4.33 log candela (cd)/m2 at 8° eccentricity using an adaptive staircase, and logged timing o...

Significance: This work describes a preliminary evaluation of a wearable collision warning device for blind individuals. The device was found to provide mobility benefit in subjects without (or deprived of) vision. This preliminary evaluation will facilitate further testing of this developmental stage device in more naturalistic conditions. Purpo...

Speed perception is an important task performed by our visual system in various daily life tasks. In various psychophysical tests, relationship between spatial frequency, temporal frequency, and speed has been examined in human subjects. The role of vision impairment in speed perception has also been previously examined. In this work, we examine th...

Magnification is a key accessibility feature used by low-vision smartphone users. However, small screen size can lead to loss of context and make interaction with magnified displays challenging. We hypothesize that controlling the viewport with head motion can be natural and help in gaining access to magnified displays. We implement this idea using...

Most gaze tracking techniques estimate gaze points on screens, on scene images, or in confined spaces. Tracking of gaze in open-world coordinates, especially in walking situations, has rarely been addressed. We use a head-mounted eye tracker combined with two inertial measurement units (IMU) to track gaze orientation relative to the heading directi...

The well-known main sequence of saccadic eye movements can have a large variability; the peak velocity of saccades with the same amplitude can be dramatically different. We explored an alternative approach to describing the saccade characteristics by looking into the in-flight shift timeline of saccades. We gathered 929 natural saccades made by two...

A pocket-sized collision warning device equipped with a video camera was developed to predict impending collisions based on time to collision rather than proximity. A study was conducted in a high density obstacle course to evaluate the effect of the device on collision avoidance in people with peripheral field loss (PFL). The 41 meter long loop-sh...

Motion estimation in videos is a computationally intensive process. A popular strategy for dealing with such a high processing load is to accelerate algorithms with dedicated hardware such as graphic processor units (GPU), field programmable gate arrays (FPGA), and digital signal processors (DSP). Previous approaches addressed the problem using acc...

A real-time collision detection system using a body-mounted camera is developed for visually impaired and blind people. The system computes sparse optical flow in the acquired videos, compensates for camera self-rotation using external gyro-sensor, and estimates collision risk in local image regions based on the motion estimates. Experimental resul...

The camera function in smart phones has a great potential to help visually impaired people with discerning scene details. Many apps have been developed to turn a smart phone into a handy video magnifier using digital zoom. As digital zoom normally cannot provide sufficient magnification for distant objects, optical telescopic devices attached to th...

This paper investigates the effectiveness of local appearance features such as Local Binary Patterns, Histograms of Oriented Gradient, Discrete Cosine Transform, and Local Color Histograms extracted from periocular region images for soft classification on gender and ethnicity. These features are classified by Artificial Neural Network or Support Ve...

We present an approach to estimate collision risk using a single uncalibrated camera attached to a moving platform. The proposed approach is based on computing the local scale change from image motion information obtained by tracking feature points. A fuzzy logic based thresholding step is applied to the tracked feature points to obtain the set of...

Developing newer approaches to deal with non-ideal scenarios in face and iris biometrics has been a key focus of research in recent years. The same reason motivates the study of the periocular biometrics as its use has a potential of significantly impacting the iris- and face-based recognition. In this paper, we explore the utility of the various a...

Computer-vision based collision risk assessment is important in collision detection and obstacle avoidance tasks. We present an approach to determine both time to collision (TTC) and collision risk for semi-rigid obstacles from videos obtained with an uncalibrated camera. TTC for a body moving relative to the camera can be calculated using the rati...

A non-ideal iris image segmentation approach based on graph cuts is presented that uses both the appearance and eye geometry information. A texture measure based on gradients is computed to discriminate between eyelash and non-eyelash regions, combined with image intensity differences between the iris, pupil, and the background (region surrounding...

The human periocular region is known to be one of the most discriminative regions of a face image, and recent studies have indicated its potential as a biometric trait. However, the bulk of the previous work concerning the periocular region consists of feasibility studies that report recognition results on controlled data, and lacks rigorous perfor...

With periocular biometrics gaining attention recently, the goal of this paper is to investigate the effectiveness of local appearance features extracted from the periocular region images for soft biométrie classification. We extract gender and ethnicity information from the periocular region images using grayscale pixel intensities and periocular t...

Human recognition based on the iris biometric is severely impacted when encountering non-ideal images of the eye characterized by occluded irises, motion and spatial blur, poor contrast, and illumination artifacts. This paper discusses the use of the periocular region surrounding the iris, along with the iris texture patterns, in order to improve t...

We evaluate the utility of the periocular region appearance cues for biometric identification. Even though periocular region is considered to be a highly discriminative part of a face, its utility as an independent modality or as a soft biometric is still an open ended question. It is our goal to establish a performance metric for the periocular re...

In this paper, we propose the use of periocular skin texture as a biometric modality. Salient skin texture features are extracted and represented using Local Binary Patterns (LBPs). Matching is performed using CityBlock distance as a measure of similarity. We investigate the use of each periocular region separately in addition to their use in conju...

We present an approach for articulated motion detection and pose estimation that uses only motion information. To estimate the pose and viewpoint we introduce a novel motion descriptor that computes the spatial relationships of motion vectors representing various parts of the person using the trajectories of a number of sparse points. A nearest nei...

We present a real-time incremental approach to motion segmentation operating on sparse feature points. In contrast to previous work, the algorithm allows for a variable number of image frames to affect the segmentation process, thus enabling an arbitrary number of objects traveling at different relative speeds to be detected. Feature points are det...

Sparse features have traditionally been tracked from frame to frame independently of one another. We propose a framework in which features are tracked jointly. Combining ideas from Lucas-Kanade and Horn-Schunck, the estimated motion of a feature is influenced by the estimated motion of neighboring features. The approach also handles the prob- lem o...

A non-ideal iris segmentation approach using graph cuts is presented. Unlike many existing algorithms for iris localization which extensively utilize eye geometry, the proposed approach is predominantly based on image intensities. In a step-wise procedure, first eyelashes are segmented from the input images using image texture, then the iris is seg...

We present an incremental approach to motion segmentation. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a region-growing algorithm with an affine moti on model. The primary parameter used by the algorithm is the amount of evidence that must accumulate before features are grouped. Contraste...

We propose an approach for vehicle tracking in a low an-gle camera sequences based on background subtraction and region tracking. We extract vehicle contours and use the shape and size information of the foreground objects to ob-tain occlusion boundaries. Along the same lines, a gradient based approach is described for segmenting occluded ve-hicles...

We present a novel method for visually monitoring a highway when the camera is relatively low to the ground and on the side of the road. In such a case, occlusion and the perspective effects due to the heights of the vehicles cannot be ignored. Features are detected and tracked throughout the image sequence, and then grouped together using a multil...