New method for the fusion of complementary information from infrared and visual images for object detection

Ulusoy, İlkay; Yürük, Hüseyin

doi:10.1049/iet-ipr.2009.0374

Cited by 42 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tone Mapped image Quality Index (TMQI) is an objective quality assessment algorithm for tone mapped images [18].It consists of two building blocks structural fidelity(S) and naturalness (N).Fidelity measure is based on modified SSIM index and naturalness is based on intensity statistics of images. The structural fidelity of TMQI is computed using a sliding window across the entire image.…”

Section: B Toned Mapped Optimization Algorithm (Tmqi-ii)mentioning

confidence: 99%

A Novel Technique for Optimizing Panchromatic and Multispectral image fusion using Discrete Wavelet Transform

Ezhilarasi¹,

Rajeswari²,

M³

et al. 2018

IJET

View full text Add to dashboard Cite

Abstract--Image Fusion refers to the process of obtaining a single image by integrating two or more images. The fused image must have complete information which is more useful for human or machine perception .The main aim of image fusion in the satellite images is to improve the information content of the source images, so that the reliability and capability of the image is increased. The vital application of image fusion in remote sensing is to merge the Panchromatic and the Multispectral image. This paper mainly focuses on obtaining a pan sharpened satellite image from Multispectral (MS) and Panchromatic (PAN) images using Discrete Wavelet Transform (DWT) and an iterative algorithm called Tone Mapped image quality index (TMQI-II) is used for optimization. This algorithm mainly improves the structural fidelity and statistical naturalness of the fused image. The earliest fusion schemes perform the fusion on the source images, which often have serious side-effects such as reducing the contrast and spectral distortion. In order to overcome the spectral distortion, Discrete Wavelet Transform is used. IKONOS and Quick Bird satellite images are used to assess the quality of this technique.Keyword--Multispectral (MS), Panchromatic (PAN) images, Discrete Wavelet Transform (DWT), Tone Mapped image quality index (TMQI-II), structural fidelity, statistical naturalness.I. INTRODUCTION Image Fusion is a technique that integrates multiple images and produces a single image which retains the important information from each of its source image. The images are acquired from different instrument modalities of the same scene (like multi-sensor, multi-focus and multi modal images). Image fusion is widely used in image and signal processing applications such as aerial and satellite imaging, computer vision, robotics, concealed weapon detection and remote sensing. Pan sharpened images are produced by combining the high spectral resolution multispectral image and the high spatial resolution panchromatic image .Panchromatic images are collected in large visual wavelength range and it's rendered in black and white. Multispectral images are obtained from more than one spectral or wavelength interval [11]. Each and every individual image is usually of the same physical location but with various spectral bands [1]. The objective of image fusion algorithms is to make full use of spatial and spectral information in the Panchromatic and Multispectral images respectively, in order to reduce the potential colour distortion and provide clear image. Image fusion improves the quality and increase the application of usage of the data. Image fusion can be classified, depending on whether the images are fused either in the spatial domain or they are transformed into another domain [23].However, the spatial domain image fusion techniques produce spectral distortion while performing the fusion process. In this paper DWT (Discrete wavelet Transform) is used for image fusion using different fusion rules. Further two different types of wavelet are used f...

show abstract

Section: B Toned Mapped Optimization Algorithm (Tmqi-ii)mentioning

confidence: 99%

A Novel Technique for Optimizing Panchromatic and Multispectral image fusion using Discrete Wavelet Transform

Ezhilarasi¹,

Rajeswari²,

M³

et al. 2018

IJET

View full text Add to dashboard Cite

show abstract

“…min(K 2 , U 2 )] matched SURF-based feature points. Given the combination as L 1 + L 2 = N, we then calculate the weighted Gaussian probabilistic density function by (7) and remain S (S ≤ N) effectively matched feature points via (8). Next, cumulative detection accuracy and average detection accuracy are obtained by (9).…”

Section: Detection Accuracy Based On Weighted Gaussian Probabilistic mentioning

confidence: 99%

Interesting components detection for space satellites from inverse synthetic aperture radar image via feature probabilistic estimation

Zhang

Xing

et al. 2015

IET Image Processing

View full text Add to dashboard Cite

Since inverse synthetic aperture radar (ISAR) imaging is a valuable technique in the identification of space satellites, it can potentially detect interesting components of space satellites in ISAR images to further conduct identification. This study proposes a novel method, defined as feature probabilistic estimation (FPE), to detect interesting components of space satellites based on ISAR image registration. In FPE, area feature registration is provoked to establish the relationship between space satellites and off-line templates of interesting components, followed by detection accuracy based on weighted Gaussian probabilistic density function. Electromagnetic simulations with different aspects, interesting components' structures and scenery noise demonstrate the efficiency and robustness of the proposed FPE, compared with the normalised cross coefficient.

show abstract

“…The improved segmentation of foreground objects was achieved through fusion of reliable sensor measurements. In [20], Ulusoy et al implemented background modeling using a single Gaussian and foreground detection respectively in infrared image, intensity image and color image, and then fused the detection results. The resulting foreground regions were used as a mask on the infrared image, and snake algorithm was applied to detect object boundaries.…”

Section: Related Workmentioning

confidence: 99%

Object Detection based on Combination of Visible and Thermal Videos using A Joint Sample Consensus Background Model

Han¹,

Xi²,

Wang³

2013

JSW

View full text Add to dashboard Cite

In uncontrolled video surveillance environments, performing efficient foreground segmentation is very challenging. In order to improve robustness and accuracy of object detection, we take advantage of spectral information of both visible and thermal videos. This paper presents a novel joint background model combining visible and thermal videos for foreground object detection in complex scenarios. Different from traditional methods that first detected moving objects in either domain respectively and then fused the detection results, we provide a joint sample consensus background model with four channels (red, green, blue and thermal) to accomplish the object detection and fusion of complementary information simultaneously, which lowers the computational cost of our method. Raw foreground segmentation is obtained in the thermal domain, making initial foreground more accurate. Meantime this can enhance the efficiency of further steps. Time out map (TOM) is utilized to deal with the problem that a newly exposed background is wrongly marked as foreground for a long time. In the updating phase, unlike most sample-based methods using first-in first-out policy, we intentionally employ a random update policy to reserve some older samples. That is, when a pixel is classified as background, we randomly pick up one of the background samples stored for the corresponding pixel to discard. In this manner, the backgrounds, occluded by slow moving foreground or temporally still foreground, can be recovered promptly when they reappear. Experimental results show that the proposed method can achieve accurate and precise detection results

show abstract

New method for the fusion of complementary information from infrared and visual images for object detection

Cited by 42 publications

References 16 publications

A Novel Technique for Optimizing Panchromatic and Multispectral image fusion using Discrete Wavelet Transform

A Novel Technique for Optimizing Panchromatic and Multispectral image fusion using Discrete Wavelet Transform

Interesting components detection for space satellites from inverse synthetic aperture radar image via feature probabilistic estimation

Object Detection based on Combination of Visible and Thermal Videos using A Joint Sample Consensus Background Model

Contact Info

Product

Resources

About