Content-Aware Eye Tracking for Autostereoscopic 3D Display

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.

Download Full-text

Crosstalk Minimization Method for Eye-tracking-based 3D Display

Journal of Imaging Science and Technology ◽

10.2352/j.imagingsci.technol.2020.64.6.060407 ◽

2020 ◽

Author(s):

Seok Lee ◽

Juyong Park ◽

Dongkyung Nam

Keyword(s):

Image Processing ◽

Eye Tracking ◽

Three Dimensional ◽

Processing Method ◽

Eye Position ◽

Relative Location ◽

3D Display ◽

Minimization Method ◽

3D Crosstalk ◽

Pixel Value

In this article, the authors present an image processing method to reduce three-dimensional (3D) crosstalk for eye-tracking-based 3D display. Specifically, they considered 3D pixel crosstalk and offset crosstalk and applied different approaches based on its characteristics. For 3D pixel crosstalk which depends on the viewer’s relative location, they proposed output pixel value weighting scheme based on viewer’s eye position, and for offset crosstalk they subtracted luminance of crosstalk components according to the measured display crosstalk level in advance. By simulations and experiments using the 3D display prototypes, the authors evaluated the effectiveness of proposed method.

Download Full-text

Tracking eye-gaze in smart home systems (SHS): first insights from eye-tracking and self-report measures

Journal of Ambient Intelligence and Humanized Computing ◽

10.1007/s12652-021-03134-8 ◽

2021 ◽

Author(s):

Federico Cassioli ◽

Laura Angioletti ◽

Michela Balconi

Keyword(s):

Eye Tracking ◽

Personality Traits ◽

Smart Home ◽

Near Infrared ◽

Tracking System ◽

Eye Gaze ◽

Self Report ◽

Visual Exploration ◽

Living Room ◽

Psychological Traits

AbstractHuman–computer interaction (HCI) is particularly interesting because full-immersive technology may be approached differently by users, depending on the complexity of the interaction, users’ personality traits, and their motivational systems inclination. Therefore, this study investigated the relationship between psychological factors and attention towards specific tech-interactions in a smart home system (SHS). The relation between personal psychological traits and eye-tracking metrics is investigated through self-report measures [locus of control (LoC), user experience (UX), behavioral inhibition system (BIS) and behavioral activation system (BAS)] and a wearable and wireless near-infrared illumination based eye-tracking system applied to an Italian sample (n = 19). Participants were asked to activate and interact with five different tech-interaction areas with different levels of complexity (entrance, kitchen, living room, bathroom, and bedroom) in a smart home system (SHS), while their eye-gaze behavior was recorded. Data showed significant differences between a simpler interaction (entrance) and a more complex one (living room), in terms of number of fixation. Moreover, slower time to first fixation in a multifaceted interaction (bathroom), compared to simpler ones (kitchen and living room) was found. Additionally, in two interaction conditions (living room and bathroom), negative correlations were found between external LoC and fixation count, and between BAS reward responsiveness scores and fixation duration. Findings led to the identification of a two-way process, where both the complexity of the tech-interaction and subjects’ personality traits are important impacting factors on the user’s visual exploration behavior. This research contributes to understand the user responsiveness adding first insights that may help to create more human-centered technology.

Download Full-text

High precision spot position detection model for the near infrared light

Infrared and Laser Engineering ◽

10.3788/irla201645.0717001 ◽

2016 ◽

Vol 45 (7) ◽

pp. 0717001

Author(s):

吴佳彬 Wu Jiabin ◽

陈云善 Chen Yunshan ◽

高世杰 Gao Shijie ◽

吴志勇 Wu Zhiyong

Keyword(s):

High Precision ◽

Near Infrared ◽

Infrared Light ◽

Near Infrared Light ◽

Detection Model ◽

Position Detection

Download Full-text

Rapid Mosaicking of Unmanned Aerial Vehicle (UAV) Images for Crop Growth Monitoring Using the SIFT Algorithm

Remote Sensing ◽

10.3390/rs11101226 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1226 ◽

Cited By ~ 10

Author(s):

Jianqing Zhao ◽

Xiaohu Zhang ◽

Chenxi Gao ◽

Xiaolei Qiu ◽

Yongchao Tian ◽

...

Keyword(s):

Unmanned Aerial Vehicle ◽

Near Infrared ◽

Similarity Index ◽

Crop Growth ◽

Contrast Threshold ◽

Growth Monitoring ◽

Scale Invariant ◽

Sift Algorithm ◽

Aerial Vehicle ◽

Uav Images

To improve the efficiency and effectiveness of mosaicking unmanned aerial vehicle (UAV) images, we propose in this paper a rapid mosaicking method based on scale-invariant feature transform (SIFT) for mosaicking UAV images used for crop growth monitoring. The proposed method dynamically sets the appropriate contrast threshold in the difference of Gaussian (DOG) scale-space according to the contrast characteristics of UAV images used for crop growth monitoring. Therefore, this method adjusts and optimizes the number of matched feature point pairs in UAV images and increases the mosaicking efficiency. Meanwhile, based on the relative location relationship of UAV images used for crop growth monitoring, the random sample consensus (RANSAC) algorithm is integrated to eliminate the influence of mismatched point pairs in UAV images on mosaicking and to keep the accuracy and quality of mosaicking. Mosaicking experiments were conducted by setting three types of UAV images in crop growth monitoring: visible, near-infrared, and thermal infrared. The results indicate that compared to the standard SIFT algorithm and frequently used commercial mosaicking software, the method proposed here significantly improves the applicability, efficiency, and accuracy of mosaicking UAV images in crop growth monitoring. In comparison with image mosaicking based on the standard SIFT algorithm, the time efficiency of the proposed method is higher by 30%, and its structural similarity index of mosaicking accuracy is about 0.9. Meanwhile, the approach successfully mosaics low-resolution UAV images used for crop growth monitoring and improves the applicability of the SIFT algorithm, providing a technical reference for UAV application used for crop growth and phenotypic monitoring.

Download Full-text

Experimental Study of Interactions between Purple and Green Sulfur Bacteria in Sandy Sediments Exposed to Illumination Deprived of Near-Infrared Wavelengths

Applied and Environmental Microbiology ◽

10.1128/aem.68.6.2972-2981.2002 ◽

2002 ◽

Vol 68 (6) ◽

pp. 2972-2981 ◽

Cited By ~ 12

Author(s):

Astrid Massé ◽

Olivier Pringault ◽

Rutger de Wit

Keyword(s):

Mixed Culture ◽

Near Infrared ◽

Single Species ◽

Fine Sand ◽

Green Sulfur Bacteria ◽

Infrared Light ◽

Light Conditions ◽

Purple Sulfur Bacterium ◽

Prosthecochloris Aestuarii ◽

Green Sulfur

ABSTRACT Sedimentary biofilms of the green sulfur bacterium Prosthecochloris aestuarii strain CE 2404, the purple sulfur bacterium Thiocapsa roseopersicina strain 5811, and a mixed culture of both were cultured in fine sand (100- to 300-μm grain size) within counter gradients of oxygen and sulfide. The artificial sediments were exposed to illumination deprived of near-infrared light (NIR) by filtering out the wavelengths longer than 700 nm to simulate the critical light conditions in submerged aquatic sediments. A 16 h of visible light-8 h of dark regimen was used. We studied the effects of these light conditions on the metabolisms of and interactions between both species by comparing the single species biofilms with the mixed biofilm. The photosynthesis rates of P. aestuarii were shown to be highly limited by the imposed light conditions, because the sulfide photooxidation rates were strongly stimulated when NIR was added. T. roseopersicina performed both aerobic chemosynthesis and photosynthesis, but the photosynthesis rates were low and poorly stimulated by the addition of NIR. This species decreased the penetration depth of oxygen in the sediment by about 1 mm by actively respiring oxygen. This way, the strict anaerobe P. aestuarii was able to grow closer to the surface in the mixed culture. As a result, P. aestuarii benefited from the presence of T. roseopersicina in the mixed culture, which was reflected by an increase in the biomass. In contrast, the density of the latter species was almost completely unaffected by the interaction. Both species coexisted in a layer of the same depth in the mixed culture, and the ecological and evolutionary implications of coexistence are discussed.

Download Full-text