Bayesian fusion of camera metadata cues in semantic scene classification

Boutell, Matthew; Luo, Jiebo

doi:10.1109/cvpr.2004.1315222

Cited by 50 publications

(51 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example [24] presents a BN framework for combining low level features to detect the most significant object within an image. Another example is [25], which uses a simple BN to combine colour and texture data with camera metadata (focal length, exposure time and flash activation) to ascertain whether the photo was taken indoors or outdoors. This paper aims to use a Bayesian network to perform probabilistic data fusion for classification of a pre-segmented image.…”

Section: Bayesian Networkmentioning

confidence: 99%

Machine Vision for UAS Ground Operations

Coombes

Eaton

Chen

2017

J Intell Robot Syst

View full text Add to dashboard Cite

This paper discusses the machine vision element of a system designed to allow Unmanned Aerial System (UAS) to perform automated taxiing around civil aerodromes, with only a monocular camera. The purpose of the computer vision system is to provide direct sensor data which can be used to validate vehicle position, in addition to detecting potential collision risks. In practice, untrained clustering is used to segment the visual feed before descriptors of each cluster (primarily colour and texture) are used to estimate the class. As the competency of each individual estimate can vary dependent on multiple factors (number of pixels, lighting conditions and even surface type). A Bayesian network is used to perform probabilistic data fusion, in order to improve the classification results. This result is shown to perform accurate image segmentation in real-world conditions, providing information viable for localisation and obstacle detection.M. Coombes ( ) · W. Eaton

show abstract

Section: Bayesian Networkmentioning

confidence: 99%

Machine Vision for UAS Ground Operations

Coombes

Eaton

Chen

2017

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…Boutell and Luo have used EXIF metadata in digital photographs for classifying based on camera specifications [21] and to perform scene classification [23] and Alvarez [7] uses EXIF metadata in digital photographs to verify authenticity of a picture and determine whether it has been altered. Bohm and Rakow [20] discuss the different aspects of classifying multimedia documents based on document metadata.…”

Section: "Metadata Includes Information About the Document Or File Thmentioning

confidence: 99%

Digital forensic research: current state of the art

Raghavan

2012

CSIT

115

View full text Add to dashboard Cite

Abstract-Digital Forensics is the process of employing scientific principles and processes analyze electronically stored information to determine the sequence of events which led to a particular incident. In this digital age, it is important for researchers to become aware of the recent developments in this dynamic field and understand scope for the future. The past decade has witnessed significant technological advancements to aid during a digital investigation. Many methodologies, tools and techniques have found their way into the field designed on forensic principles. Digital forensics has also witnessed many innovative approaches that have been explored to acquire and analyze digital evidence from diverse sources. In this paper, we review the research literature since 2000 and categorize developments in the field into 4 major categories. In recent years the exponential growth of technological has also brought with it some serious challenges for digital forensic research which is elucidated. Within each category, research is sub-classified into conceptual and practical advancements. We highlight the observations made by previous researchers and summarize the research directions for the future.

show abstract

“…In addition to some of these low-level cues, [Datta et al 2006[Datta et al , 2007 investigate the impact of features such as familiarity measures, wavelet responses on textures, aspect ratio, and region composition on the aesthetic appeal of natural images. Boutell and Luo [2004] explore a variety of metrics including ISO speed rating, F-number and shutter speed, extracted directly from camera metadata, to determine their impact on photographic quality. These methods, as observed by Luo and Tang [2008] and Sun et al [2009], capture only fine-grained details about the photograph that are mainly introduced due to sensors used during the image formation process.…”

Section: Related Workmentioning

confidence: 99%

A holistic approach to aesthetic enhancement of photographs

Bhattacharya

Sukthankar

Shah

2011

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

This article presents an interactive application that enables users to improve the visual aesthetics of their digital photographs using several novel spatial recompositing techniques. This work differs from earlier efforts in two important aspects: (1) it focuses on both photo quality assessment and improvement in an integrated fashion, (2) it enables the user to make informed decisions about improving the composition of a photograph. The tool facilitates interactive selection of one or more than one foreground objects present in a given composition, and the system presents recommendations for where it can be relocated in a manner that optimizes a learned aesthetic metric while obeying semantic constraints. For photographic compositions that lack a distinct foreground object, the tool provides the user with crop or expansion recommendations that improve the aesthetic appeal by equalizing the distribution of visual weights between semantically different regions. The recomposition techniques presented in the article emphasize learning support vector regression models that capture visual aesthetics from user data and seek to optimize this metric iteratively to increase the image appeal. The tool demonstrates promising aesthetic assessment and enhancement results on variety of images and provides insightful directions towards future research.

show abstract

Bayesian fusion of camera metadata cues in semantic scene classification

Abstract: Abstract

Cited by 50 publications

References 13 publications

Machine Vision for UAS Ground Operations

Machine Vision for UAS Ground Operations

Digital forensic research: current state of the art

A holistic approach to aesthetic enhancement of photographs

Contact Info

Product

Resources

About