Large-Scale Indoor/Outdoor Image Classification via Expert Decision Fusion (EDF)

Chen, Chen; Ren, Yuzhuo; Kuo, C.-C. Jay

doi:10.1007/978-3-319-16628-5_31

Cited by 8 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also much more complex existing solutions. Some are based on brightness, gamut, exposure, and gain [28], some on a stacking of multiple indicators (in various domains), and deep learning models [29,93,94]. It is also important to note that multiple databases exist to train models (which all have their pros and cons: number of images, low resolution, image size, etc.…”

Section: Scene Analysis/classificationmentioning

confidence: 99%

A Review of Environmental Context Detection for Navigation Based on Multiple Sensors

Feriol

Vivet

Watanabe

2020

Sensors

View full text Add to dashboard Cite

Current navigation systems use multi-sensor data to improve the localization accuracy, but often without certitude on the quality of those measurements in certain situations. The context detection will enable us to build an adaptive navigation system to improve the precision and the robustness of its localization solution by anticipating possible degradation in sensor signal quality (GNSS in urban canyons for instance or camera-based navigation in a non-textured environment). That is why context detection is considered the future of navigation systems. Thus, it is important firstly to define this concept of context for navigation and to find a way to extract it from available information. This paper overviews existing GNSS and on-board vision-based solutions of environmental context detection. This review shows that most of the state-of-the art research works focus on only one type of data. It confirms that the main perspective of this problem is to combine different indicators from multiple sensors.

show abstract

Section: Scene Analysis/classificationmentioning

confidence: 99%

A Review of Environmental Context Detection for Navigation Based on Multiple Sensors

Feriol

Vivet

Watanabe

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In addition, processing time of nonparametric methods is considerably larger than the learning-based methods, which makes them inconvenient for large scale classification systems. In [28], they achieved better performance in large-scale dataset by using bagging method [50].…”

Section: A Machine Learningmentioning

confidence: 99%

“…It consists of 397 well-sampled scene category indexes and 108,754 images. [28] labelled the whole SUN dataset into 47260 indoor images and 61494 outdoor images. Their experiments were conducted with respect to this dataset.…”

Section: Datasetmentioning

confidence: 99%

A Review of Indoor-Outdoor Scene Classification

Tong¹,

Shi²,

Yan

et al. 2017

Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)

View full text Add to dashboard Cite

Abstract-Indoor-Outdoor scene classification problem have been proposed for almost 20 years and widely applied to general scene classification, image retrieval, image processing and robot application. But there is no consensus on one particular scene classification technique that can solve the Indoor-Outdoor scene classification problem perfectly. As larger image dataset has been developed and machine learning technology especially deep learning based methods achieve remarkable performance in computer vision, we aim to provide guidance and direction for researchers to tackle the Indoor-Outdoor scene classification problem with more powerful and robust solution through concluding the Indoor-Outdoor scene classification approaches which have been proposed in last 20 years. In this paper, we review the Indoor-Outdoor scene classification including feature extraction, classifier and related dataset. Their advantages and disadvantages are discussed. At last we conclude some challenging problems remain unsolved and propose some potential solutions.

show abstract

“…We thus propose a semi-supervised approach to augment the training set. This approach has three benefits: (1) it results in a balanced, richer training set; (2) it sets aside the vast majority of images with location for the test set; and (3) it is efficient and largely automated. The proposed procedure first randomly selects 20% of each category in the geolocated dataset as the base training set, and the remaining geolocated images form the test set.…”

Section: Dataset Augmentationmentioning

confidence: 99%

Land use classification using convolutional neural networks applied to ground-level images

Zhu

Newsam

2015

Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Land use mapping is a fundamental yet challenging task in geographic science. In contrast to land cover mapping, it is generally not possible using overhead imagery. The recent, explosive growth of online geo-referenced photo collections suggests an alternate approach to geographic knowledge discovery. In this work, we present a general framework that uses ground-level images from Flickr for land use mapping.Our approach benefits from several novel aspects. First, we address the nosiness of the online photo collections, such as imprecise geolocation and uneven spatial distribution, by performing location and indoor/outdoor filtering, and semisupervised dataset augmentation. Our indoor/outdoor classifier achieves state-of-the-art performance on several benchmark datasets and approaches human-level accuracy. Second, we utilize high-level semantic image features extracted using deep learning, specifically convolutional neural networks, which allow us to achieve upwards of 76% accuracy on a challenging eight class land use mapping problem.

show abstract

Large-Scale Indoor/Outdoor Image Classification via Expert Decision Fusion (EDF)

Cited by 8 publications

References 31 publications

A Review of Environmental Context Detection for Navigation Based on Multiple Sensors

A Review of Environmental Context Detection for Navigation Based on Multiple Sensors

A Review of Indoor-Outdoor Scene Classification

Land use classification using convolutional neural networks applied to ground-level images

Contact Info

Product

Resources

About