A novel algorithm for fast compression and reconstruction of infrared thermographic sequence based on image segmentation

Zhang, Jinyu; Zhang, Wei; Yang, Zhengwei; Tian, Guohui

doi:10.1016/j.infrared.2014.08.009

Cited by 15 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described in the introduction above, there are four key parameters in our algorithm: the minimum scale value of the structural element B, denoted as s in Equations ( 6) and ( 7); the maximum scale value of the structural element B, denoted as e in Equations ( 6) and (7); the weight ω i in Equation ( 9); the constant k in Equation (10) to binarize the saliency map. In order to detect small targets and, at the same time, find large targets with prominent contours, we set s as 3 and e as 15.…”

Section: Discussion Of Key Parametersmentioning

confidence: 99%

“…Thus, we propose a multiscale morphological reconstruction (MMR) method that uses several structuring elements with different scales at the same time to process a grayscale image. The forms of multiscale dilation-based reconstruction (MDR) and multiscale erosion-based reconstruction (MER) are defined in Equations ( 6) and (7), respectively.…”

Section: Multiscale Saliency Mapmentioning

confidence: 99%

“…In the past few decades, researchers have developed many methods for infrared ship target detection, including methods based on the following: local contrast measure (LCM) [ 1 , 3 , 4 , 5 , 6 ], threshold segmentation [ 7 , 8 , 9 ], background modeling [ 10 , 11 ], deep learning [ 12 , 13 , 14 , 15 ], and morphological reconstruction [ 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…This kind of method has advantages in that it is simple and easy to implement. Classical threshold segmentation methods, such as Otsu [ 7 ], have been widely used in the field of detection. However, classical methods are too simple and cannot cope with noise interference.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Multiscale Method for Infrared Ship Detection Based on Morphological Reconstruction and Two-Branch Compensation Strategy

Chen,

Qiu,

Zhang

2023

Sensors

View full text Add to dashboard Cite

Infrared ship target detection is crucial technology in marine scenarios. Ship targets vary in scale throughout navigation because the distance between the ship and the infrared camera is constantly changing. Furthermore, complex backgrounds, such as sea clutter, can cause significant interference during detection tasks. In this paper, multiscale morphological reconstruction-based saliency mapping, combined with a two-branch compensation strategy (MMRSM-TBC) algorithm, is proposed for the detection of ship targets of various sizes and against complex backgrounds. First, a multiscale morphological reconstruction method is proposed to enhance the ship targets in the infrared image and suppress any irrelevant background. Then, by introducing a structure tensor with two feature-based filter templates, we utilize the contour information of the ship targets and further improve their intensities in the saliency map. After that, a two-branch compensation strategy is proposed, due to the uneven distribution of image grayscale. Finally, the target is extracted using an adaptive threshold. The experimental results fully show that our proposed algorithm achieves strong performance in the detection of different-sized ship targets and has a higher accuracy than other existing methods.

show abstract

Section: Discussion Of Key Parametersmentioning

confidence: 99%

Section: Multiscale Saliency Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Multiscale Method for Infrared Ship Detection Based on Morphological Reconstruction and Two-Branch Compensation Strategy

Chen,

Qiu,

Zhang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…To analyze the constraint relationship among different images, some image processing approaches are applied. Zhang et al utilize the image segmentation method to detect defect regions for fast compression and reconstruction of IRT [12]. A minimum spanning tree clustering algorithm is used to consider the temperature differences and spatial distances together [13].…”

Section: Introductionmentioning

confidence: 99%

Nondestructive detection and analysis based on data enhanced thermography

Li¹,

Xiao²,

Zhang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

The machine learning and data fusion methods have played a significant role in the non-destructive testing (NDT) of the composite materials in modern industries. Among them, the feature extraction thermography models like principal component thermography (PCT) have been well studied and applied due to their advantages of dimensionality reduction and discriminative representation. However, the current pulse thermal imaging technology can only collect limited images since the tested materials usually cannot be overheated, which will also decrease the performance of the feature extraction thermography models. In this paper, an improved denoising convolutional autoencoder with the U-net architecture is proposed for data enhancement purpose. Using the developed structure, the enhanced images are generated, in which the deep spatial information in the original images is maintained while the measurement noises are well decreased simultaneously. Using the original and enhanced images together, the NDT performance based on feature extraction thermography is further improved. Finally, the feasibility and effectiveness of the proposed methods are demonstrated by two defect detection experiments of the carbon fiber reinforced polymer.

show abstract

A New Modification of Fuzzy C-Means via Particle Swarm Optimization for Noisy Image Segmentation

Mirghasemi

Rayudu

Zhang

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A novel algorithm for fast compression and reconstruction of infrared thermographic sequence based on image segmentation

Cited by 15 publications

References 10 publications

A Multiscale Method for Infrared Ship Detection Based on Morphological Reconstruction and Two-Branch Compensation Strategy

A Multiscale Method for Infrared Ship Detection Based on Morphological Reconstruction and Two-Branch Compensation Strategy

Nondestructive detection and analysis based on data enhanced thermography

A New Modification of Fuzzy C-Means via Particle Swarm Optimization for Noisy Image Segmentation

Contact Info

Product

Resources

About