Our system is currently under heavy load due to increased usage. We're actively working on upgrades to improve performance. Thank you for your patience.
Proceedings of IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI2003.
DOI: 10.1109/mfi-2003.2003.1232650
|View full text |Cite
|
Sign up to set email alerts
|

Physics-based models of color and IR video for sensor fusion

Abstract: Physics based sensor fusion attempts to utilize the phenomenology of sensors to combine external conditions with data collected by the sensors into a global consistent dynamic representation. Although there have been a few approaches using this paradigm, it is still not entirely clear what kinds of physical models are appropriate for different sensing devices and conditions. We provide physical models that are suitable for the visible and infrared region of the spectrum. The physical models are described in de… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
8
0

Publication Types

Select...
5
1
1

Relationship

2
5

Authors

Journals

citations
Cited by 10 publications
(8 citation statements)
references
References 14 publications
0
8
0
Order By: Relevance
“…In IR video, the most used feature is IR intensity but texture feature can be a further tool to gain more robustness against weather changes (clouds, rain). To solve these problems, Nadimi and Bhanu [18] proposed to use color features in addition of IR intensity. On the other hand, Latecki et al Figure 2.…”
Section: Choice Of Featuresmentioning
confidence: 99%
“…In IR video, the most used feature is IR intensity but texture feature can be a further tool to gain more robustness against weather changes (clouds, rain). To solve these problems, Nadimi and Bhanu [18] proposed to use color features in addition of IR intensity. On the other hand, Latecki et al Figure 2.…”
Section: Choice Of Featuresmentioning
confidence: 99%
“…BraceForce also embraces modeldriven data acquisition (MDDA) [14,21,22,24,27] to reduce energy costs of integrating sensing in mobile applications. MDDA suppresses sensor readings that are predictable according to some a priori or learned model.…”
Section: Introductionmentioning
confidence: 99%
“…MDDA suppresses sensor readings that are predictable according to some a priori or learned model. BraceForce supports (i) temporal models based on previous sensor readings [24]; (ii) models based on underlying physics principles [21]; (iii) models derived from applying data mining to prior sensed data [14]; and (iv) models expressing correlations of data in space and time [27]. While the use of MDDA is itself not novel to BraceForce, what is new is that BraceForce provides existing libraries for a few MDDA models and allows customized MDDA models to be plugged into the framework through an extensible programming interface.…”
Section: Introductionmentioning
confidence: 99%
“…There are a number of video surveillance systems [1] [2] [3], which consist of a single camera or hundreds of cameras. To achieve the 24-7 continuous monitoring, some IR cameras are used along with the optical cameras under low illuminations [4].…”
Section: Introductionmentioning
confidence: 99%
“…The surveillance task can be described as the sequential processes where multiple moving objects are to be extracted (detection), followed (tracking), distinguished (recognition), and their interactions understood (activity recognition) [4]. Each part of this process presents challenging problems and may depend on the outcome of the previous step.…”
Section: Introductionmentioning
confidence: 99%