A sliding mode contour detection method - a new direction in image modelling

<p>A biomimetic vision computing model based on multi-level feature channel optimization coding is proposed and applied to image contour detection, combining the end-to-end detection method of full convolutional neural network and the traditional contour detection method based on biological vision mechanism. Considering the effectiveness of the Gabor filter in perceiving the scale and direction of the image target, the Gabor filter is introduced to simulate the multi-level feature response on the visual path. The optimal scale and direction of the Gabor filter are obtained based on the similarity index, and they are used as the frequency separation parameter of the NSCT transform. The contour sub-image obtained by the NSCT transform is combined with the original image for feature enhancement and fusion to realize the primary contour response. The low-dimensional and low-redundancy primary contour response is used as the input sample of the network model to relieve network pressure and reduce computational complexity. A fully improved convolutional neural network model is constructed for multi-scale training, through feature encoder to feature decoder, to achieve end-to-end pixel prediction, and obtain a complete and continuous detection image of the subject contour. Using the BSDS500 atlas as the experimental sample, the average accuracy index is 0.85, which runs on the device CPU at a detection rate of 20+ FPS to achieve a good balance between training efficiency and detection effect.</p>

Download Full-text

An improved contour detection method based on level set and watershed transform

10.1117/12.832902 ◽

2009 ◽

Author(s):

Shuang Wang ◽

Shenggao Fu ◽

Licheng Jiao ◽

Xiaojing Zhang

Keyword(s):

Level Set ◽

Detection Method ◽

Contour Detection ◽

Watershed Transform

Download Full-text

Optimized cyber-attack detection method of power systems using sliding mode observer

Electric Power Systems Research ◽

10.1016/j.epsr.2021.107745 ◽

2022 ◽

Vol 205 ◽

pp. 107745

Author(s):

Mahdieh Adeli ◽

Majid Hajatipour ◽

Mohammad Javad Yazdanpanah ◽

Hamed Hashemi-Dezaki ◽

Mohsen Shafieirad

Keyword(s):

Power Systems ◽

Detection Method ◽

Sliding Mode ◽

Attack Detection ◽

Sliding Mode Observer ◽

Cyber Attack

Download Full-text

Friction Fault Detection of an Electrohydrostatic Actuator

ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, Volume 2 ◽

10.1115/dscc2011-6121 ◽

2011 ◽

Cited By ~ 2

Author(s):

S. A. Gadsden ◽

Y. Song ◽

K. R. McCullough ◽

S. R. Habibi

Keyword(s):

Fault Detection ◽

Detection Method ◽

Sliding Mode ◽

Variable Structure ◽

Interacting Multiple Model ◽

Multiple Model ◽

Estimation Strategy ◽

Operating Modes ◽

Smooth Variable Structure Filter ◽

Novel Model

This article discusses the application of a novel model-based fault detection method. The method is based on the interacting multiple model (IMM) strategy, which makes use of a finite number of known operating modes. A filter is used in conjunction with the IMM in order to estimate the states and parameters of the system. The smooth variable structure filter (SVSF) is a relatively new estimation strategy, and is based on sliding mode concepts which introduces an inherent amount of robustness and stability. The combined SVSF-IMM strategy is applied on an electrohydrostatic actuator (EHA), which is a device used in the aerospace industry. Two different operating modes were created, based on varying degrees of friction acting on the EHA cylinder. The results of the friction fault detection were compared with the popular Kalman filter (KF) based IMM strategy.

Download Full-text

A novel position detection method of sensorless brushless DC motor based on sliding mode observer

2011 4th International Conference on Power Electronics Systems and Applications ◽

10.1109/pesa.2011.5982898 ◽

2011 ◽

Cited By ~ 2

Author(s):

Lin Qinghua ◽

Yang Xiangyu ◽

Zhao Shiwei

Keyword(s):

Detection Method ◽

Sliding Mode ◽

Dc Motor ◽

Sliding Mode Observer ◽

Brushless Dc Motor ◽

Brushless Dc ◽

Position Detection

Download Full-text

A Fully Convolutional Network-Based Tube Contour Detection Method Using Multi-Exposure Images

Sensors ◽

10.3390/s21124095 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4095

Author(s):

Xiaoqi Cheng ◽

Junhua Sun ◽

Fuqiang Zhou

Keyword(s):

Detection Method ◽

Three Dimensional ◽

Contour Detection ◽

Two Dimensional ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Complex Scenes ◽

Dimensional Reconstruction ◽

Overall Evaluation ◽

Evaluation Metric

The tube contours in two-dimensional images are important cues for optical three-dimensional reconstruction. Aiming at the practical problems encountered in the application of tube contour detection under complex background, a fully convolutional network (FCN)-based tube contour detection method is proposed. Multi-exposure (ME) images are captured as the input of FCN in order to get information of tube contours in different dynamic ranges, and the U-Net type architecture is adopted by the FCN to achieve pixel-level dense classification. In addition, we propose a new loss function that can help eliminate the adverse effects caused by the positional deviation and jagged morphology of tube contour labels. Finally, we introduce a new dataset called multi-exposure tube contour dataset (METCD) and a new evaluation metric called dilate inaccuracy at optimal dataset scale (DIA-ODS) to reach an overall evaluation of our proposed method. The experimental results show that the proposed method can effectively improve the integrity and accuracy of tube contour detection in complex scenes.

Download Full-text