Mobile eye tracking captures egocentric vision and is well-suited for naturalistic studies. However, its data is noisy, especially when acquired outdoor with multiple participants over several sessions. Area of interest analysis on moving targets is difficult because A) camera and objects move nonlinearly and may disappear/reappear from the scene; and B) off-the-shelf analysis tools are limited to linearly moving objects. As a result, researchers resort to time-consuming manual annotation, which limits the use of mobile eye tracking in naturalistic studies. We introduce a method based on a fine-tuned Vision Transformer (ViT) model for classifying frames with overlaying gaze markers. After fine-tuning a model on a manually labelled training set made of 1.98% (=7845 frames) of our entire data for three epochs, our model reached 99.34% accuracy as evaluated on hold-out data. We used the method to quantify participants’ dwell time on a tablet during the outdoor user test of a mobile augmented reality application for biodiversity education. We discuss the benefits and limitations of our approach and its potential to be applied to other contexts.

Location-based augmented reality technology for real-world, outdoor experiences is rapidly gaining in popularity in a variety of fields such as engineering, education, and gaming. By anchoring medias to geographic coordinates, it is possible to design immersive experiences remotely, without necessitating an in-depth knowledge of the context. However, the creation of such experiences typically requires complex programming tools that are beyond the reach of mainstream users. We introduce BiodivAR, a web cartographic tool for the authoring of location-based AR experiences. Developed using a user-centered design methodology and open-source interoperable web technologies, it is the second iteration of an effort that started in 2016. It is designed to meet needs defined through use cases co-designed with end users and enables the creation of custom geolocated points of interest. This approach enabled substantial progress over the previous iteration. Its reliance on geolocation data to anchor augmented objects relative to the user’s position poses a set of challenges: On mobile devices, GNSS accuracy typically lies between 1 m and 30 m. Due to its impact on the anchoring, this lack of accuracy can have deleterious effects on usability. We conducted a comparative user test using the application in combination with two different geolocation data types (GNSS versus RTK). While the test’s results are undergoing analysis, we hereby present a methodology for the assessment of our system’s usability based on the use of eye-tracking devices, geolocated traces and events, and usability questionnaires.

While the use of location-based augmented reality (AR) for education has demonstrated benefits on participants’ motivation, engagement, and on their physical activity, geolocation data inaccuracy causes augmented objects to jitter or drift, which is a factor in downgrading user experience. We developed a free and open source web AR application and conducted a comparative user test (n = 54) in order to assess the impact of geolocation data on usability, exploration, and focus. A control group explored biodiversity in nature using the system in combination with embedded GNSS data, and an experimental group used an external module for RTK data. During the test, eye tracking data, geolocated traces, and in-app user-triggered events were recorded. Participants answered usability questionnaires (SUS, UEQ, HARUS).We found that the geolocation data the RTK group was exposed to was less accurate in average than that of the control group. The RTK group reported lower usability scores on all scales, of which 5 out of 9 were significant, indicating that inaccurate data negatively predicts usability. The GNSS group walked more than the RTK group, indicating a partial effect on exploration. We found no significant effect on interaction time with the screen, indicating no specific relation between data accuracy and focus. While RTK data did not allow us to better the usability of location-based AR interfaces, results allow us to assess our system’s overall usability as excellent, and to define optimal operating conditions for future use with pupils.