Marker-based watershed algorithm for segmentation of the infrared images

Manda, Manikanta Prahlad; Park, ChanSu; Oh, ByeongCheol; Kim, Hi-Seok

doi:10.1109/isocc47750.2019.9027721

Cited by 3 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This gray scale image was then binarized with a properly chosen grayscale threshold ( Figure 1B ). Next, a watershed method ( 19 , 20 ) was used to segment and label the images of the two rats, even when they were slightly connected ( Figure 1C ). Finally, by calculating the secondary moment of the positions of the pixels belonging to each rat, their postures, centroids, and directions can be roughly represented by two ellipses ( Figure 1D ).…”

Section: Methodsmentioning

confidence: 99%

Electromagnetic Exposure Dosimetry Study on Two Free Rats at 1.8 GHz via Numerical Simulation

Wang

Xia

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

Normally, the impact of electromagnetic exposure on human health is evaluated by animal study. The biological effect caused by electromagnetic exposure on such experimental animals as rats has been proven to be dose-dependent. However, though the dose of radio frequency (RF) electromagnetic exposure described by the specific absorbing rate (SAR) on fixed rats has been relatively well-studied utilizing the numerical simulations, the dosimetry study of exposure on free rat is insufficient, especially in the cases of two or more free rats. Therefore, the present work focuses on the variation of SAR caused by the existence of neighboring free rat in the same cage. Here, infrared thermography was used to record the activity of the two free rats who lived in the same cage that mounted at the far-field region in the microwave darkroom for a duration of 48 h. Then, using image processing techniques, the relative positions and orientations of the two rats are identified, which are defined by three parameters, such as the relative distance (d), relative direction angle (α), and relative orientation angle (β). Using the simulation software XFdtd 7.3, the influence of d, α, and β on the whole-body average SAR (WB-avgSAR) of the rats exposed to 1.8 GHz electromagnetic wave was calculated and analyzed. Then, the average variation of WB-avgSAR of the two rats compared with that of a single rat within 48 h was calculated. The numerical simulation results showed that the relative posture position described by (d, α, and β) of the two rats affects their WB-avgSAR and leads to fluctuations at different positions. However, the variation rate of the 48-h-average WB-avgSAR was only 10.3%, which implied that the over-time average SAR of two or more rats can be roughly described by the WB-avgSAR of a single free rat, except when a real-time precise control of exposure dose is necessary.

show abstract

Section: Methodsmentioning

confidence: 99%

Electromagnetic Exposure Dosimetry Study on Two Free Rats at 1.8 GHz via Numerical Simulation

Wang

Xia

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Despite this method is also fast and safe, requires no contact connections and is widely used in practice [1], this identification method is very susceptible to the interference of artificial factors, and the resulting image has such demerits as a poor resolution, low contrast, visual blurring and other shortcomings that affect the recognition accuracy. At present, the existing methods to solve the infrared image recognition method mainly focus on the technology improvement research [2][3][4] and segmentation technology research [5][6][7]. So, these methods can improve the recognition effect of infrared images, but these algorithms have a high degree of complexity, increasing the difficulty of image analysis and detection.…”

Section: Introductionmentioning

confidence: 99%

Research on power equipment troubleshooting based on improved AlexNet neural network

Xu,

Liu,

Zhang

2024

J. meas. eng.

View full text Add to dashboard Cite

Power equipment is an important component of the whole power system, so that it is obvious that it is required to develop a correct method for accurate analysis of the infrared image features of the equipment in the field of detection and recognition. This study proposes a troubleshooting strategy for the power equipment based on the improved AlexNet neural network. Multi-scale images based on the Pan model are used to determine the equipment features, and to determine the shortcomings of AlexNet neural network, such as slower recognition speed and easy overfitting. After knowing these shortcomings, it would become possible to improve the specific recognition model performance by adding a pooling layer, modifying the activation function, replacing the LRN with BN layer, and optimizing the parameters of the improved WOA algorithm, and other measures. In the simulation experiments, this paper's algorithm was compared with AlexNet, YOLO v3, and Faster R-CNN algorithms in the lightning arrester fault detection, circuit breaker fault detection, mutual transformer fault detection, and insulator fault detection improved by an average of 5.47 %, 4.69 %, and 3.42 %, which showed that the algorithm had a better recognition effect.

show abstract

Designer Face Mask Detection Using Marker-Based Watershed Transform and YOLOv2 CNN Model

Vyas,

Sharma

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Marker-based watershed algorithm for segmentation of the infrared images

Cited by 3 publications

References 4 publications

Electromagnetic Exposure Dosimetry Study on Two Free Rats at 1.8 GHz via Numerical Simulation

Electromagnetic Exposure Dosimetry Study on Two Free Rats at 1.8 GHz via Numerical Simulation

Research on power equipment troubleshooting based on improved AlexNet neural network

Designer Face Mask Detection Using Marker-Based Watershed Transform and YOLOv2 CNN Model

Contact Info

Product

Resources

About