scholarly journals Human-level saccade detection performance using deep neural networks

2018 ◽  
Author(s):  
Marie E. Bellet ◽  
Joachim Bellet ◽  
Hendrikje Nienborg ◽  
Ziad M. Hafed ◽  
Philipp Berens

Saccades are ballistic eye movements that rapidly shift gaze from one location of visual space to another. Detecting saccades in eye movement recordings is important not only for studying the neural mechanisms underlying sensory, motor, and cognitive processes, but also as a clinical and diagnostic tool. However, automatically detecting saccades can be difficult, particularly when such saccades are generated in coordination with other tracking eye movements, like smooth pursuits, or when the saccade amplitude is close to eye tracker noise levels, like with microsaccades. In such cases, labeling by human experts is required, but this is a tedious task prone to variability and error. We developed a convolutional neural network (CNN) to automatically detect saccades at human-level performance accuracy. Our algorithm surpasses state of the art according to common performance metrics, and will facilitate studies of neurophysiological processes underlying saccade generation and visual processing.

2019 ◽  
Vol 121 (2) ◽  
pp. 646-661 ◽  
Author(s):  
Marie E. Bellet ◽  
Joachim Bellet ◽  
Hendrikje Nienborg ◽  
Ziad M. Hafed ◽  
Philipp Berens

Saccades are ballistic eye movements that rapidly shift gaze from one location of visual space to another. Detecting saccades in eye movement recordings is important not only for studying the neural mechanisms underlying sensory, motor, and cognitive processes, but also as a clinical and diagnostic tool. However, automatically detecting saccades can be difficult, particularly when such saccades are generated in coordination with other tracking eye movements, like smooth pursuits, or when the saccade amplitude is close to eye tracker noise levels, like with microsaccades. In such cases, labeling by human experts is required, but this is a tedious task prone to variability and error. We developed a convolutional neural network to automatically detect saccades at human-level accuracy and with minimal training examples. Our algorithm surpasses state of the art according to common performance metrics and could facilitate studies of neurophysiological processes underlying saccade generation and visual processing. NEW & NOTEWORTHY Detecting saccades in eye movement recordings can be a difficult task, but it is a necessary first step in many applications. We present a convolutional neural network that can automatically identify saccades with human-level accuracy and with minimal training examples. We show that our algorithm performs better than other available algorithms, by comparing performance on a wide range of data sets. We offer an open-source implementation of the algorithm as well as a web service.


2020 ◽  
Vol 117 (14) ◽  
pp. 8203-8211 ◽  
Author(s):  
Pooya Laamerad ◽  
Daniel Guitton ◽  
Christopher C. Pack

Most people easily learn to recognize new faces and places, and with more extensive practice they can become experts at visual tasks as complex as radiological diagnosis and action video games. Such perceptual plasticity has been thoroughly studied in the context of training paradigms that require constant fixation. In contrast, when observers learn under more natural conditions, they make frequent saccadic eye movements. Here we show that such eye movements can play an important role in visual learning. Observers performed a task in which they executed a saccade while discriminating the motion of a cued visual stimulus. Additional stimuli, presented simultaneously with the cued one, permitted an assessment of the perceptual integration of information across visual space. Consistent with previous results on perisaccadic remapping [M. Szinte, D. Jonikaitis, M. Rolfs, P. Cavanagh, H. Deubel,J. Neurophysiol.116, 1592–1602 (2016)], most observers preferentially integrated information from locations representing the presaccadic and postsaccadic retinal positions of the cue. With extensive training on the saccade task, these observers gradually acquired the ability to perform similar motion integration without making eye movements. Importantly, the newly acquired pattern of spatial integration was determined by the metrics of the saccades made during training. These results suggest that oculomotor influences on visual processing, long thought to subserve the function of perceptual stability, also play a role in visual plasticity.


Eye movements are integrated with cognitive processes, which indeed make it a helpful research basis for the investigation of human practices. Eye movements can be deployed in discovering several cognitive processes of the brain. This research utilizes low-resolution webcam to develop an eye tracker and saccades measurement tool to extensively lower the gadgets expenses. A consistent algorithm is developed to suit the quality of the webcam using open-source software (Python) to record the time series of the eye location. Likewise, several algorithms are proposed to extract high-level eye movement saccadic measurements from the raw gaze outputs. A pilot study is performed on ten normal participants and Multiple Sclerosis (MS) patients. Experimental results demonstrate that the proposed system is quick, simple and efficient for eye tracking and saccade measurement. The developed tool can be used by clinicians and medical physicians for the diagnosis and identification of neurological disorders


2018 ◽  
Vol 46 (11) ◽  
pp. 1869-1880 ◽  
Author(s):  
Di Wu ◽  
Yuntao Gao ◽  
Danmin Miao

The need for cognition (NC) refers to the tendency for people to vary in the extent to which they engage in, and enjoy, cognitively effortful activities. However, few studies on NC have been conducted to investigate cognitive processes by using eye-tracking technology. Thus, we measured differences in eye movement between individuals high versus low in NC. We presented 43 undergraduates with persuasive messages on postponed retirement. Meanwhile, their eye movements were recorded using eye-tracking technology. Additionally, participants completed measures of attitude and recall of arguments. Our findings showed that participants high in NC recalled more arguments but did not form more favorable attitudes than did those low in NC. Furthermore, compared to those low in NC, those with high NC recorded longer eye fixation duration, more fixations, slower reading speed, and shorter saccade (movement) lengths. Finally, there were no differences between the two groups concerning the distribution (short, medium, and long fixations) and the proportion of regressions. Eye-tracking technology contributes to further understanding of characteristics of individuals high versus low in NC during reading.


2021 ◽  
Author(s):  
Ifedayo-Emmmanuel Adeyefa-Olasupo

Despite the incessant retinal disruptions that necessarily accompany eye movements, our percept of the visual world remains continuous and stable—a phenomenon referred to as spatial constancy. How the visual system achieves spatial constancy remains unclear despite almost four centuries worth of experimentation. Here I measured visual sensitivity at geometrically symmetric locations, observing transient sensitivity differences between them where none should be observed if cells that support spatial constancy indeed faithfully translate or converge. These differences, recapitulated by a novel neurobiological mechanical model, reflect an overriding influence of putative visually transient error signals that curve visual space. Intermediate eccentric locations likely to contain retinal disruptions are uniquely affected by curved visual space, suggesting that visual processing at these locations is transiently turned off before an eye movement, and with the gating off of these error signals, turned back on after an eye-movement— a possible mechanism underlying spatial constancy.


2000 ◽  
Vol 59 (2) ◽  
pp. 85-88 ◽  
Author(s):  
Rudolf Groner ◽  
Marina T. Groner ◽  
Kazuo Koga

2012 ◽  
Vol 17 (4) ◽  
pp. 257-265 ◽  
Author(s):  
Carmen Munk ◽  
Günter Daniel Rey ◽  
Anna Katharina Diergarten ◽  
Gerhild Nieding ◽  
Wolfgang Schneider ◽  
...  

An eye tracker experiment investigated 4-, 6-, and 8-year old children’s cognitive processing of film cuts. Nine short film sequences with or without editing errors were presented to 79 children. Eye movements up to 400 ms after the targeted film cuts were measured and analyzed using a new calculation formula based on Manhattan Metrics. No age effects were found for jump cuts (i.e., small movement discontinuities in a film). However, disturbances resulting from reversed-angle shots (i.e., a switch of the left-right position of actors in successive shots) led to increased reaction times between 6- and 8-year old children, whereas children of all age groups had difficulties coping with narrative discontinuity (i.e., the canonical chronological sequence of film actions is disrupted). Furthermore, 4-year old children showed a greater number of overall eye movements than 6- and 8-year old children. This indicates that some viewing skills are developed between 4 and 6 years of age. The results of the study provide evidence of a crucial time span of knowledge acquisition for television-based media literacy between 4 and 8 years.


2014 ◽  
Vol 519-520 ◽  
pp. 828-832
Author(s):  
He Shan Liu ◽  
Xun Chen ◽  
Jun Zhou ◽  
Wei Liu

In today’s marketplace, external appearance and internal decoration become an increasingly important factor that affecting sales volume of product. Moreover, for loaders, the external appearance and decoration of the cab may influence the driver’s comfort both visually and mentally. In order to find out how it works, we divided the experimental subjects into professional group and nonprofessional group and used eye tracker to record subjects’ responses (eye movements) to the pictures of the loader, and then analyzed these responses with the eye tracker build-in analyzing software. The results show that the professional are more interested in functional parts and the nonprofessionals are more likely to be influenced by appearance shape and color; the instrument panel is less attracted during the whole experiments.


Healthcare ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 10
Author(s):  
Chong-Bin Tsai ◽  
Wei-Yu Hung ◽  
Wei-Yen Hsu

Optokinetic nystagmus (OKN) is an involuntary eye movement induced by motion of a large proportion of the visual field. It consists of a “slow phase (SP)” with eye movements in the same direction as the movement of the pattern and a “fast phase (FP)” with saccadic eye movements in the opposite direction. Study of OKN can reveal valuable information in ophthalmology, neurology and psychology. However, the current commercially available high-resolution and research-grade eye tracker is usually expensive. Methods & Results: We developed a novel fast and effective system combined with a low-cost eye tracking device to accurately quantitatively measure OKN eye movement. Conclusions: The experimental results indicate that the proposed method achieves fast and promising results in comparisons with several traditional approaches.


Sign in / Sign up

Export Citation Format

Share Document