MétaCan
Menu
Back to cohort
Record W2955592451 · doi:10.1145/3328938

Learning to Recognize Unmodified Lights with Invisible Features

2019· article· en· W2955592451 on OpenAlexfundno aff
Huanhuan Zhang, Anfu Zhou, Shaoqing Xu, Xinyu Zhang, Huadóng Ma

Bibliographic record

VenueProceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · 2019
Typearticle
Languageen
FieldEngineering
TopicIndoor and Outdoor Localization Technologies
Canadian institutionsnot available
FundersNational Natural Science Foundation of ChinaCanadian Institute for Advanced Research
KeywordsComputer scienceArtificial intelligenceComputer visionDiscriminative modelAndroid (operating system)Deep learningDeep neural networks

Abstract

fetched live from OpenAlex

To enable accurate indoor localization at low cost, recent research in visible light positioning (VLP) proposed to employ existing ceiling lights as location landmarks, and use smartphone cameras or light sensors to identify the different lights using statistical visual/optical features. Despite the potential, we find such solutions are unreliable: the features are easily corrupted with a slight rotation of the smartphone, and are not discriminative enough for many practical light models with different size/shape/intensity. In this work, we propose Auto-Litell to resolve these critical challenges and make VLP truly robust. Auto-Litell builds a customized deep-learning neural network model to automatically distill the "invisible" visual features from the lights, which are resilient to smartphone orientation and light models. Moreover, Auto-Litell introduces a Light-CycleGAN to generate "fake" light images to augment the training data, so as to relieve human labors in data collection and labeling. We have implemented Auto-Litell as a real-time localization and navigation system on Android. Our experiments demonstrate Auto-Litell's high accuracy in discriminating the lights in the same building, and high reliability across a variety of practical usage scenarios.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.244
Threshold uncertainty score0.661

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.004
GPT teacher head0.203
Teacher spread0.199 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the ACM on Interactive Mobile Wearable and Ubiquitous TechnologiesSame topicIndoor and Outdoor Localization TechnologiesFrench-language works237,207