Automatically characterizing places with opportunistic crowdsensing using smartphones

Chon, Yohan; Lane, Nicholas D.; Li, Fan; Cha, Hojung; Zhao, Feng

doi:10.1145/2370216.2370288

Cited by 234 publications

(151 citation statements)

References 26 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…We found that these features are reliable with respect to the raw video content, but that the videos themselves do not always reflect the place ambiance reported in-situ. 6. We found that participants were compliant when it comes to recording videos in a variety of places, social settings or personal contexts, and privacy-related situations.…”

Section: Introductionmentioning

confidence: 85%

“…Most mobile sensing studies have focused on gathering sensor data including accelerometer, GPS, WiFi, Bluetooth. Other studies have also collected perceptual data including audio and still images for place characterization [6,47,28], life-logging [18], visual perception [37], etc. In contrast, fewer crowdsensing studies have collected visual data in the form of mobile videos.…”

Section: Mobile Sensing For Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

The night is young

Santani

Biel

Labhart

et al. 2016

Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

View full text Add to dashboard Cite

We present a mobile crowdsourcing study to capture and examine the nightlife patterns of two youth populations in Switzerland. Our contributions are three fold. First, we developed a smartphone application to capture data on places, social context and nightlife activities, and to record mobile videos capturing the ambiance of places. Second, we conducted an "in-the-wild" study with more than 200 participants over a period of three months in two Swiss cities, resulting in a total of 1,394 unique place visits and 843 videos that spread across place categories (including personal homes and public parks), social and ambiance variables. Finally, we investigated the use of automatic ambiance features to estimate the loudness and brightness of places at scale, and found that while features are reliable with respect to video content, videos do not always reflect the place ambiance reported by people in-situ. We believe that the developed methodology provides an opportunity to understand the physical mobility, activities, and social context of youth as they experience different aspects of nightlife.

show abstract

Section: Introductionmentioning

confidence: 85%

Section: Mobile Sensing For Data Collectionmentioning

confidence: 99%

The night is young

Santani

Biel

Labhart

et al. 2016

Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

View full text Add to dashboard Cite

show abstract

“…A typical example of opportunistic crowdsensing is CrowdSense@Place, an application that opportunistically capture images and audio clips from smartphones in order to classify places into a variety of categories such as store, restaurant, etc. [26]. However, in participatory sensing, the active involvement of device custodians is required and it is often the case that most community and urban sensing initiatives are participatory in nature [25].…”

Section: Types Of Mobile Crowdsensingmentioning

confidence: 99%

Adopting incentive mechanisms for large-scale participation in mobile crowdsensing: from literature review to a conceptual framework

Ogie

2016

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

Mobile crowdsensing is a burgeoning concept that allows smart cities to leverage the sensing power and ubiquitous nature of mobile devices in order to capture and map phenomena of common interest. At the core of any successful mobile crowdsensing application is active user participation, without which the system is of no value in sensing the phenomenon of interest. A major challenge militating against widespread use and adoption of mobile crowdsensing applications is the issue of how to identify the most appropriate incentive mechanism for adequately and efficiently motivating participants. This paper reviews literature on incentive mechanisms for mobile crowdsensing and proposes the concept of SPECTRUM as a guide for inferring the most appropriate type of incentive suited to any given crowdsensing task. Furthermore, the paper highlights research challenges and areas where additional studies related to the different factors outlined in the concept of SPECTRUM are needed to improve citizen participation in mobile crowdsensing. It is envisaged that the broad range of factors covered in SPECTRUM will enable smart cities to efficiently engage citizens in large-scale crowdsensing initiatives. More importantly, the paper is expected to trigger empirical investigations into how various factors as outlined in SPECTRUM can influence the type of incentive mechanism that is considered most appropriate for any given mobile crowdsensing initiative.

show abstract

“…CenceMe [39] uses ambient audio and movement information to infer activity and conversation type, but simply uses the GPS service for location -recorded images are not used for classification. CrowdSense@Place [9] does use computer vision techniques (alongside processing of recorded audio) to classify location amongst one of seven general categories (e.g., home, workplace, shops) -this system was not evaluated for its ability to perform the specific scene recognition that PlaceAvoider performs but this approach would be useful to identify general types of locations where privacy risks are high.…”

Section: Related Workmentioning

confidence: 99%

PlaceAvoider: Steering First-Person Cameras away from Sensitive Spaces

Templeman

Korayem

Crandall

et al. 2014

Proceedings 2014 Network and Distributed System Security Symposium

104

View full text Add to dashboard Cite

Abstract-Cameras are now commonplace in our social and computing landscapes and embedded into consumer devices like smartphones and tablets. A new generation of wearable devices (such as Google Glass) will soon make 'first-person' cameras nearly ubiquitous, capturing vast amounts of imagery without deliberate human action. 'Lifelogging' devices and applications will record and share images from people's daily lives with their social networks. These devices that automatically capture images in the background raise serious privacy concerns, since they are likely to capture deeply private information. Users of these devices need ways to identify and prevent the sharing of sensitive images.As a first step, we introduce PlaceAvoider, a technique for owners of first-person cameras to 'blacklist' sensitive spaces (like bathrooms and bedrooms). PlaceAvoider recognizes images captured in these spaces and flags them for review before the images are made available to applications. PlaceAvoider performs novel image analysis using both fine-grained image features (like specific objects) and coarse-grained, scene-level features (like colors and textures) to classify where a photo was taken. PlaceAvoider combines these features in a probabilistic framework that jointly labels streams of images in order to improve accuracy. We test the technique on five realistic firstperson image datasets and show it is robust to blurriness, motion, and occlusion.

show abstract

Automatically characterizing places with opportunistic crowdsensing using smartphones

Cited by 234 publications

References 26 publications

The night is young

The night is young

Adopting incentive mechanisms for large-scale participation in mobile crowdsensing: from literature review to a conceptual framework

PlaceAvoider: Steering First-Person Cameras away from Sensitive Spaces

Contact Info

Product

Resources

About