Multi-focus image fusion based on fractional order differentiation and closed image matting

Zhang, Xuefeng; He, Hao; Zhang, Jin-Xi

doi:10.1016/j.isatra.2022.03.003

Cited by 19 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…13 The state of optical flow motion in polar coordinates However, in this paper, attention mechanisms are constitutively fused to recognize motion features by introducing them separately for velocity modalities as well as for acceleration modalities. To investigate the effects of different attention modules on the performance of further motion prediction made by the delivered acceleration modal results, based on the unimodal recognition model, feature-level fusion methods [35], fractional-order fusion methods [36], SEBlock-based [37] and hybrid CBAM-based fusion methods are constructed in this section, respectively.…”

Section: Action Feature Prediction Validationmentioning

confidence: 99%

Approximated acceleration modes-based detection method for violent video

Zhang,

Zeng,

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper first introduces the Pixel Tracking methods to solve the optical flow information from the original video frames, based on which the optical flow field is established. In this paper, the LFN2-2DCNN-ConvLSTM velocity recognition model is constructed based on the optical flow field, and the Acc-2DCNN-ConvLSTM acceleration recognition model is further constructed based on the velocity features. Among them, this paper innovatively gives a regionalized approximation method to approximate the acceleration feature sequence, obtains an efficient approximation of optical flow feature information under acceleration modes, and obtains the velocity and acceleration modes under CBAM mechanism centralized data. We verified the accuracy of the data in our experiments.

show abstract

Section: Action Feature Prediction Validationmentioning

confidence: 99%

Approximated acceleration modes-based detection method for violent video

Zhang,

Zeng,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Yan et al [17] proposed an infrared and visible image fusion algorithm which obtained fusion results suitable for human visual perception. Zhang et al [18] proposed a novel approach to addressing the fusion of multi-focus images in either registered or mis-registered cases which provides better visual perception and higher objective evaluation.…”

Section: Related Workmentioning

confidence: 99%

Surface Defect Detection in Sanitary Ceramics Based on Lightweight Object Detection Network

Hang

Sun

Yu³

et al. 2022

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

Sanitary ceramic products, such as toilet and wash basin, are widely used in our daily life. Sanitary ceramics are expected to have some excellent physical properties, such as corrosion resistance, easy cleaning, and low water absorption. However, surface defects in sanitary ceramics are inevitable due to complex production processes and changing production environment. Therefore, surface defect detection must be performed in the manufacturing process of sanitary ceramics. There are many types of surface defects in sanitary ceramics, and different types of defects have large differences in characteristics and scales. Traditional detection methods with artificially designed features and classifiers are difficult to apply in this context. In addition, there are few studies on surface defect detection methods of sanitary ceramics based on deep neural networks. In this article, a lightweight real-time defect detection network based on the lightweight backbone MobileNetV3 is presented. The proposed network achieves multi-scale detection of surface defects in sanitary ceramics with a multi-layer feature pyramid. Combining region proposal network and anchor-free method, realtime defect detection is achieved. Finally, a detection head with channel attention structure and a low-level mixed feature classification strategy is used to perform defect classification with higher accuracy. Experimental results show that the proposed approach achieves at least 22.9% detection speed improvement and 35.0% average precision improvement while reducing memory consumption by at least 8.4% compared with the classic onestage SSD, YOLO V3 and two-stage Faster R-CNN methods.

show abstract

“…The fractional differential operator can improve the details of the contour and suppress the influence of noise, so this method is selected to achieve. Common fractional differential definitions include Riemann-Liouville (R-L) definition, Caputo definition and Grünwald-Letnikov (G-L) definition, G-L definition is more suitable for digital image processing than the other two definitions, G-L definition [11,12] as follows:…”

Section: Gradient Amplitude Calculationmentioning

confidence: 99%

Path Planning Method of Rolling Brush of Car Washing Machine Based on Fractional Differentiation

Yan

Qiu²,

Hou³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The roller brush cleaning path of the gantry reciprocating automatic car washing machine is the key to determining the quality of the car wash. For the issue that the traditional method cannot accurately and reliably calculate the roller path, a rolling brush path planning scheme combined with fractional differential algorithm is proposed. By analysing the working form of the car washing machine and the appearance characteristics of the car, a multi-view car detection system is designed, and the car images are collected by using multiple cameras. The possibility of the path of each roller brush of the car washing machine is extracted from the contour information, and the contour curve is converted into the roller brush path in the form of coordinate points through software. Finally, the actual size of the car to be washed is calculated by the multi-view camera, and the average error between the calculation result and the actual result is 2.63%, which meets the operating conditions of the gantry reciprocating automatic car washing machine.

show abstract

Multi-focus image fusion based on fractional order differentiation and closed image matting

Cited by 19 publications

References 43 publications

Approximated acceleration modes-based detection method for violent video

Approximated acceleration modes-based detection method for violent video

Surface Defect Detection in Sanitary Ceramics Based on Lightweight Object Detection Network

Path Planning Method of Rolling Brush of Car Washing Machine Based on Fractional Differentiation

Contact Info

Product

Resources

About