Quantifying Dwell Time With Location-based Augmented Reality: Dynamic AOI Analysis on Mobile Eye Tracking Data With Vision Transformer.

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.

Blind Calibration of Environmental Acoustics Measurements Using Smartphones.

Environmental noise control is a major health and social issue. Numerous environmental policies require local authorities to draw up noise maps to establish an inventory of the noise environment and then propose action plans to improve its quality. In general, these maps are produced using numerical simulations, which may not be sufficiently representative, for example, concerning the temporal dynamics of noise levels. Acoustic sensor measurements are also insufficient in terms of spatial coverage. More recently, an alternative approach has been proposed, consisting of using citizens as data producers by using smartphones as tools of geo-localized acoustic measurement. However, a lack of calibration of smartphones can generate a significant bias in the results obtained. Against the classical metrological principle that would aim to calibrate any sensor beforehand for physical measurement, some have proposed mass calibration procedures called "blind calibration". The method is based on the crossing of sensors in the same area at the same time, which are therefore supposed to observe the same phenomenon (i.e., measure the same value). The multiple crossings of a large number of sensors at the scale of a territory and the analysis of the relationships between sensors allow for the calibration of the set of sensors. In this article, we propose to adapt a blind calibration method to data from the NoiseCapture smartphone application. The method's behavior is then tested on NoiseCapture datasets for which information on the calibration values of some smartphones is already available.

Using a Clustering Method to Detect Spatial Events in a Smartphone-Based Crowd-Sourced Database for Environmental Noise Assessment.

Noise has become a very notable source of pollution with major impacts on health, especially in urban areas. To reduce these impacts, proper evaluation of noise is very important, for example by using noise mapping tools. The Noise-Planet project seeks to develop such tools in an open science platform, with a key open-source smartphone tool "NoiseCapture" that allows users to measure and share the noise environment as an alternative to classical methods, such as simulation tools and noise observatories, which have limitations. As an alternative solution, smartphones can be used to create a low-cost network of sensors to collect the necessary data to generate a noise map. Nevertheless, this data may suffer from problems, such as a lack of calibration or a bad location, which lowers its quality. Therefore, quality control is very crucial to enhance the data analysis and the relevance of the noise maps. Most quality control methods require a reference database to train the models. In the context of NC, this reference data can be produced during specifically organized events (NC party), during which contributors are specifically trained to collect measurements. Nevertheless, these data are not sufficient in number to create a big enough reference database, and it is still necessary to complete them. Other communities around the world use NC, and one may want to integrate the data they collected into the learning database. In order to achieve this, one must detect these data within the mass of available data. As these events are generally characterized by a higher density of measurements in space and time, in this paper we propose to apply a classical clustering method, called DBSCAN, to identify them in the NC database. We first tested this method on the existing NC party, then applied it on a global scale. Depending on the DBSCAN parameters, many clusters are thus detected, with different typologies.

NoiseCapture smartphone application as pedagogical support for education and public awareness.

Teaching science subjects such as acoustics to youth or the general public can be facilitated by illustrating physical phenomena or scientific issues using fun experiences. A few years ago, our team developed a smartphone application named NoiseCapture with the aim of offering to anyone the opportunity to measure their sound environment and to share their geolocated measurements with the community in order to build a collective noise map. Since then, NoiseCapture team members have experimented with numerous interventions in schools or scientific events for the general public based on the app to explain not only societal and environmental issues related to noise but also to teach acoustic notions and to address technical and scientific topics associated with sound measurement. This paper describes some of the interventions implemented, in particular, in a school context through training courses given to middle school and university students, as well as teachers of secondary school, that focused on basic knowledge of buildings and environmental acoustics, on the practice of acoustic measurement, and on noise mapping. Some examples of interventions with the general public are also presented that were mostly integrated into scientific events.

A Smartphone-Based Crowd-Sourced Database for Environmental Noise Assessment.

Noise is a major source of pollution with a strong impact on health. Noise assessment is therefore a very important issue to reduce its impact on humans. To overcome the limitations of the classical method of noise assessment (such as simulation tools or noise observatories), alternative approaches have been developed, among which is collaborative noise measurement via a smartphone. Following this approach, the NoiseCapture application was proposed, in an open science framework, providing free access to a considerable amount of information and offering interesting perspectives of spatial and temporal noise analysis for the scientific community. After more than 3 years of operation, the amount of collected data is considerable. Its exploitation for a sound environment analysis, however, requires one to consider the intrinsic limits of each collected information, defined, for example, by the very nature of the data, the measurement protocol, the technical performance of the smartphone, the absence of calibration, the presence of anomalies in the collected data, etc. The purpose of this article is thus to provide enough information, in terms of quality, consistency, and completeness of the data, so that everyone can exploit the database, in full control.

A redesign of OGC Symbology Encoding standard for sharing cartography.

Despite most Spatial Data Infrastructures offering service-based visualization of geospatial data, requirements are often at a very basic level leading to poor quality of maps. This is a general observation for any geospatial architecture as soon as open standards as those of the Open Geospatial Consortium (OGC) are applied. To improve the situation, this paper does focus on improvements at the portrayal interoperability side by considering standardization aspects. We propose two major redesign recommendations. First to consolidate the cartographic theory at the core of the OGC Symbology Encoding standard. Secondly to build the standard in a modular way so as to be ready to be extended with upcoming future cartographic requirements. Thus, we start by defining portrayal interoperability by means of typical-use cases that frame the concept of sharing cartography. Then we bring to light the strengths and limits of the relevant open standards to consider in this context. Finally we propose a set of recommendations to overcome the limits so as to make these use cases a true reality. Even if the definition of a cartographic-oriented standard is not able to act as a complete cartographic design framework by itself, we argue that pushing forward the standardization work dedicated to cartography is a way to share and disseminate good practices and finally to improve the quality of the visualizations.

Collaborative noise data collected from smartphones.

Noise stands for an important human health and environmental issue. Indeed, noise causes annoyance and fatigue, interferes with communication and sleep, damages hearing and entails cardiovascular problems (WHO, 2011) [1]. From an environmental point of view, noise implies a lessening of both the richness and abundance of the animal species, an alteration of the communication, which can threaten the reproduction and predation, etc. (Newport et al., 2014; Shannon et al., 2014) [2], [3]. Consequently, effects related to environmental noise result in a huge cost for society, with 2.2 billion euros in France, for example, for the year 2013 (Bourges and Diel, 2015) [4]. In this context, the reduction of noise in the environment is a burning issue, which requires, firstly, carrying out an evaluation of noise in the environment, and secondly, to establish action plans to reduce noise annoyance. With the development of the concept of participatory measurement, and considering the extremely large number of people equipped with a smartphone while being "in mobility", the use of smartphones is potentially a relevant solution to realize a large-scale environmental noise evaluation. The data presented hereinafter are collected from the Android NoiseCapture application and shared from the OnoMap Spatial Data Infrastructure (SDI). The NoiseCapture approach consists in measuring noise along a path, and then to share data with the community. This approach has been developed within the framework of the European ENERGIC-OD project, which aims at deploying a set of Virtual Hubs (VH) to share heterogeneous data with third parties, in respect with the European INSPIRE, and at developing new and original services that can be useful for the community. The noise data that are acquired by volunteers around the world (citizen observations), are organized in three files, containing the path of measures (a set of points), standardized noise indicators, noise description and other useful variables (GPS accuracy, speed…). These data can be very relevant later to propose an environmental noise evaluation, through simple or complex treatments.