RESUMEN

This study develops an eye tracking method for autostereoscopic three-dimensional (3D) display systems for use in various environments. The eye tracking-based autostereoscopic 3D display provides low crosstalk and high-resolution 3D image experience seamlessly without 3D eyeglasses by overcoming the viewing position restriction. However, accurate and fast eye position detection and tracking are still challenging, owing to the various light conditions, camera control, thick eyeglasses, eyeglass sunlight reflection, and limited system resources. This study presents a robust, automated algorithm and relevant systems for accurate and fast detection and tracking of eye pupil centers in 3D with a single visual camera and near-infrared (NIR) light emitting diodes (LEDs). Our proposed eye tracker consists of eye-nose detection, eye-nose shape keypoint alignment, a tracker checker, and tracking with NIR LED on/off control. Eye-nose detection generates facial subregion boxes, including the eyes and nose, which utilize an Error-Based Learning (EBL) method for the selection of the best learnt database (DB). After detection, the eye-nose shape alignment is processed by the Supervised Descent Method (SDM) with Scale-invariant Feature Transform (SIFT). The aligner is content-aware in the sense that corresponding designated aligners are applied based on image content classification, such as the various light conditions and wearing eyeglasses. The conducted experiments on real image DBs yield promising eye detection and tracking outcomes, even in the presence of challenging conditions.

Asunto(s)

RESUMEN

In this paper we present an autostereoscopic 3D display using a directional subpixel rendering algorithm in which clear left-right images are expressed in real time based on a viewer's 3D eye positions. In order to maintain the 3D image quality over a wide viewing range, we designed an optical layer that generates a uniformly distributed light field. The proposed 3D rendering method is simple, and each pixel processing can be performed independently in parallel computing environments. To prove the effectiveness of our display system, we implemented 31.5" 3D monitor and 10.1" 3D tablet prototypes in which the 3D rendering is processed in the GPU and FPGA board, respectively.

RESUMEN

We present a method to enhance depth quality of a time-of-flight (ToF) camera without additional devices or hardware modifications. By controlling the turn-off patterns of the LEDs of the camera, we obtain depth and normal maps simultaneously. Sixteen subphase images are acquired with variations in gate-pulse timing and light emission pattern of the camera. The subphase images allow us to obtain a normal map, which are combined with depth maps for improved depth details. These details typically cannot be captured by conventional ToF cameras. By the proposed method, the average of absolute differences between the measured and laser-scanned depth maps has decreased from 4.57 to 3.77 mm.

RESUMEN

In this paper, we propose a novel method for generating a realistic 3D human face from a single 2D face image for the purpose of synthesizing new 2D face images at arbitrary poses using gender and ethnicity specific models. We employ the Generic Elastic Model (GEM) approach, which elastically deforms a generic 3D depth-map based on the sparse observations of an input face image in order to estimate the depth of the face image. Particularly, we show that Gender and Ethnicity specific GEMs (GE-GEMs) can approximate the 3D shape of the input face image more accurately, achieving a better generalization of 3D face modeling and reconstruction compared to the original GEM approach. We qualitatively validate our method using publicly available databases by showing each reconstructed 3D shape generated from a single image and new synthesized poses of the same person at arbitrary angles. For quantitative comparisons, we compare our synthesized results against 3D scanned data and also perform face recognition using synthesized images generated from a single enrollment frontal image. We obtain promising results for handling pose and expression changes based on the proposed method.

Asunto(s)

RESUMEN

Classical face recognition techniques have been successful at operating under well-controlled conditions; however, they have difficulty in robustly performing recognition in uncontrolled real-world scenarios where variations in pose, illumination, and expression are encountered. In this paper, we propose a new method for real-world unconstrained pose-invariant face recognition. We first construct a 3D model for each subject in our database using only a single 2D image by applying the 3D Generic Elastic Model (3D GEM) approach. These 3D models comprise an intermediate gallery database from which novel 2D pose views are synthesized for matching. Before matching, an initial estimate of the pose of the test query is obtained using a linear regression approach based on automatic facial landmark annotation. Each 3D model is subsequently rendered at different poses within a limited search space about the estimated pose, and the resulting images are matched against the test query. Finally, we compute the distances between the synthesized images and test query by using a simple normalized correlation matcher to show the effectiveness of our pose synthesis method to real-world data. We present convincing results on challenging data sets and video sequences demonstrating high recognition accuracy under controlled as well as unseen, uncontrolled real-world scenarios using a fast implementation.

Asunto(s)