scholarly journals Research on Generation Method of Grasp Strategy Based on DeepLab V3+ for Three-Finger Gripper

Information ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 278
Author(s):  
Sanlong Jiang ◽  
Shaobo Li ◽  
Qiang Bai ◽  
Jing Yang ◽  
Yanming Miao ◽  
...  
Keyword(s):  
Field Of View ◽  
Convolution Kernel ◽  
Parallel Connection ◽  
Multi Scale ◽  
Spatial Pyramid Pooling ◽  
The Stability ◽  
Parameter Values ◽  
Filter Layer ◽  
Complex Dataset ◽  
Better Than

A reasonable grasping strategy is a prerequisite for the successful grasping of a target, and it is also a basic condition for the wide application of robots. Presently, mainstream grippers on the market are divided into two-finger grippers and three-finger grippers. According to human grasping experience, the stability of three-finger grippers is much better than that of two-finger grippers. Therefore, this paper’s focus is on the three-finger grasping strategy generation method based on the DeepLab V3+ algorithm. DeepLab V3+ uses the atrous convolution kernel and the atrous spatial pyramid pooling (ASPP) architecture based on atrous convolution. The atrous convolution kernel can adjust the field-of-view of the filter layer by changing the convolution rate. In addition, ASPP can effectively capture multi-scale information, based on the parallel connection of multiple convolution rates of atrous convolutional layers, so that the model performs better on multi-scale objects. The article innovatively uses the DeepLab V3+ algorithm to generate the grasp strategy of a target and optimizes the atrous convolution parameter values of ASPP. This study used the Cornell Grasp dataset to train and verify the model. At the same time, a smaller and more complex dataset of 60 was produced according to the actual situation. Upon testing, good experimental results were obtained.

scholarly journals Multi scale switchable atrous convolution for target detection based on feature pyramid

2022 ◽  
Vol 355 ◽  
pp. 03011
Author(s):  
Cheng Fang ◽  
Ziqiang Hao ◽  
Jiaxin Chen
Keyword(s):  
Feature Extraction ◽  
Field Of View ◽  
Convolution Kernel ◽  
Data Set ◽  
Sample Distribution ◽  
Multi Scale ◽  
Average Accuracy ◽  
Repeated Observation ◽  
Feature Pyramid ◽  
Low Efficiency

Repeated observation mechanism can effectively solve the problem of low efficiency of feature extraction. By extracting features for many times to strengthen target features, this paper proposed a multi-scale switchable atrous convolution based on feature pyramid, SPC. The head of the detector adopted pyramid convolution mode, constructs 3-D convolution in the feature pyramid, and detected the same target in different pyramid levels by using the shared convolution with different stride changes, which realized the repeated observation of target features on multi-scale. The module optimized the convolution layer, extracted the features of the same image by convolution check of different sizes, and then selected and integrated the extracted results by using switch function, which effectively expanded the field of view of convolution kernel. In this paper, we choosed retinanet as the baseline network, and improved the loss function of focal loss proposed by retinanet to further solved the problem of unbalanced number of samples and sample distribution in the network model. The proposed method performed well on MS coco data set, improved the average accuracy of 9.8% on the basis of retinanet to 48.9%, and achieved FPS of 5.1 in 1333 * 800 images.

scholarly journals Bridge Crack Detection Based on SSENets

2020 ◽  
Vol 10 (12) ◽  
pp. 4230 ◽  
Author(s):  
Haotian Li ◽  
Hongyan Xu ◽  
Xiaodong Tian ◽  
Yi Wang ◽  
Huaiyu Cai ◽  
...  
Keyword(s):  
Neural Networks ◽  
Computational Complexity ◽  
Crack Detection ◽  
Contextual Information ◽  
Detection Accuracy ◽  
Multi Scale ◽  
Surrounding Environment ◽  
Spatial Pyramid Pooling ◽  
Spatial Pyramid ◽  
Better Than

Bridge crack detection is essential to prevent transportation accidents. However, the surrounding environment has great interference with the detection of cracks, which makes it difficult to ensure the accuracy of the detection. In order to accurately detect bridge cracks, we proposed an end-to-end model named Skip-Squeeze-and-Excitation Networks (SSENets). It is mainly composed of the Skip-Squeeze-Excitation (SSE) module and the Atrous Spatial Pyramid Pooling (ASPP) module. The SSE module uses skip-connection strategy to enhance the gradient correlation between the shallow network and deeper network, alleviating the vanishing gradient caused by the deepening of the network. The ASPP module can extract multi-scale contextual information of images, while the depthwise separable convolution reduces computational complexity. In order to avoid destroying the topology of crack, we used atrous convolution instead of the pooling layer. The proposed SSENets achieved a detection accuracy of 97.77%, which performed better than the models we compared it with. The designed SSE module which used skip-connection strategy can be embedded in other convolutional neural networks (CNNs) to improve their performance.

Recent Patents on Nanoporous Filtration Membranes with Complex Pores

2020 ◽  
Vol 14 (2) ◽  
pp. 229-233
Author(s):  
Yongbin Zhang
Keyword(s):  
Geometrical Parameter ◽  
Filtration Membranes ◽  
Analytical Results ◽  
Parameter Values ◽  
Mechanical Strengths ◽  
Better Than

Background:: The challenges to nanoporous filtration membranes are small fluxes and low membrane mechanical strengths. Objective:: To introduce newly invented nanoporous filtration membranes with complex pores, improved fluxes and mechanical strengths as registered in patents. Methods:: The analytical results are presented for the addressed membranes. Results:: The geometrical parameter values of the addressed membranes can be optimized for the highest fluxes. Conclusion:: The overall performances of nanoporous filtration membranes with complex cylindrical or/and conical pores can be significantly better than that of the conventional nanoporous filtration membranes with single cylindrical or conical pores.

scholarly journals Dispersion of Carbon Nanotubes with “Green” Detergents

Molecules ◽  
2021 ◽  
Vol 26 (10) ◽  
pp. 2908
Author(s):  
Kazuo Umemura ◽  
Ryo Hamano ◽  
Hiroaki Komatsu ◽  
Takashi Ikuno ◽  
Eko Siswoyo
Keyword(s):  
Carbon Nanotubes ◽  
Sodium Dodecyl ◽  
Detergent Solution ◽  
Absorbance Spectroscopy ◽  
Fundamental Research ◽  
The Stability ◽  
Single Walled Cnts ◽  
Better Than ◽  
Walled Cnts ◽  
Cnt Suspensions

Solubilization of carbon nanotubes (CNTs) is a fundamental technique for the use of CNTs and their conjugates as nanodevices and nanobiodevices. In this work, we demonstrate the preparation of CNT suspensions with “green” detergents made from coconuts and bamboo as fundamental research in CNT nanotechnology. Single-walled CNTs (SWNTs) with a few carboxylic acid groups (3–5%) and pristine multi-walled CNTs (MWNTs) were mixed in each detergent solution and sonicated with a bath-type sonicator. The prepared suspensions were characterized using absorbance spectroscopy, scanning electron microscopy, and Raman spectroscopy. Among the eight combinations of CNTs and detergents (two types of CNTs and four detergents, including sodium dodecyl sulfate (SDS) as the standard), SWNTs/MWNTs were well dispersed in all combinations except the combination of the MWNTs and the bamboo detergent. The stability of the suspensions prepared with coconut detergents was better than that prepared with SDS. Because the efficiency of the bamboo detergents against the MWNTs differed significantly from that against the SWNTs, the natural detergent might be useful for separating CNTs. Our results revealed that the use of the “green” detergents had the advantage of dispersing CNTs as well as SDS.

scholarly journals Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1104
Author(s):  
Siti Raihanah Abdani ◽  
Mohd Asyraf Zulkifley ◽  
Nuraisyah Hani Zulkifley
Keyword(s):  
Screening Tool ◽  
Jaccard Index ◽  
Dense Network ◽  
Multi Scale ◽  
Spatial Pyramid Pooling ◽  
Severity Levels ◽  
Set Up ◽  
Channel Variation ◽  
Mobile Phone Camera ◽  
Sunlight Radiation

Pterygium is an eye condition that is prevalent among workers that are frequently exposed to sunlight radiation. However, most of them are not aware of this condition, which motivates many volunteers to set up health awareness booths to give them free health screening. As a result, a screening tool that can be operated on various platforms is needed to support the automated pterygium assessment. One of the crucial functions of this assessment is to extract the infected regions, which directly correlates with the severity levels. Hence, Group-PPM-Net is proposed by integrating a spatial pyramid pooling module (PPM) and group convolution to the deep learning segmentation network. The system uses a standard mobile phone camera input, which is then fed to a modified encoder-decoder convolutional neural network, inspired by a Fully Convolutional Dense Network that consists of a total of 11 dense blocks. A PPM is integrated into the network because of its multi-scale capability, which is useful for multi-scale tissue extraction. The shape of the tissues remains relatively constant, but the size will differ according to the severity levels. Moreover, group and shuffle convolution modules are also integrated at the decoder side of Group-PPM-Net by placing them at the starting layer of each dense block. The addition of these modules allows better correlation among the filters in each group, while the shuffle process increases channel variation that the filters can learn from. The results show that the proposed method obtains mean accuracy, mean intersection over union, Hausdorff distance, and Jaccard index performances of 0.9330, 0.8640, 11.5474, and 0.7966, respectively.

Attitude reconstruction from strap-down rate gyros using power series

2021 ◽  
pp. 1-19
Author(s):  
Habib Ghanbarpourasl
Keyword(s):  
Power Series ◽  
Taylor Series ◽  
Direction Cosine ◽  
Analytical Description ◽  
Double Precision ◽  
Angular Velocity Vector ◽  
Higher Order Terms ◽  
Direction Cosine Matrix ◽  
The Stability ◽  
Better Than

Abstract This paper introduces a power series based method for attitude reconstruction from triad orthogonal strap-down gyros. The method is implemented and validated using quaternions and direction cosine matrix in single and double precision implementation forms. It is supposed that data from gyros are sampled with high frequency and a fitted polynomial is used for an analytical description of the angular velocity vector. The method is compared with the well-known Taylor series approach, and the stability of the coefficients’ norm in higher-order terms for both methods is analysed. It is shown that the norm of quaternions’ derivatives in the Taylor series is bigger than the equivalent terms coefficients in the power series. In the proposed method, more terms can be used in the power series before the saturation of the coefficients and the error of the proposed method is less than that for other methods. The numerical results show that the application of the proposed method with quaternions performs better than other methods. The method is robust with respect to the noise of the sensors and has a low computational load compared with other methods.

Design of Airborne Multi-Scale Wide-Field-of-View and High-Resolution Imaging System

2021 ◽  
Vol 41 (2) ◽  
pp. 0208002
Author(s):  
李江勇 Li Jiangyong ◽  
冯位欣 Feng Weixin ◽  
刘飞 Liu Fei ◽  
魏雅喆 Wei Yazhe ◽  
邵晓鹏 Shao Xiaopeng
Keyword(s):  
High Resolution ◽  
Imaging System ◽  
Field Of View ◽  
Wide Field ◽  
High Resolution Imaging ◽  
Multi Scale ◽  
Wide Field Of View ◽  
Resolution Imaging

Magnetorheological fluid based on amorphous Fe-Si-B alloy magnetic particles

2021 ◽  
pp. 1045389X2110643
Author(s):  
Chuncheng Yang ◽  
Zhong Liu ◽  
Xiangyu Pei ◽  
Cuiling Jin ◽  
Mengchun Yu ◽  
...  
Keyword(s):  
Magnetic Field ◽  
Field Strength ◽  
Rheological Property ◽  
Magnetic Particles ◽  
Annealing Treatment ◽  
Magnetorheological Fluid ◽  
The Stability ◽  
The Magnetic Field ◽  
Amorphous Particle ◽  
Better Than

Magnetorheological fluids (MRFs) based on amorphous Fe-Si-B alloy magnetic particles were prepared. The influence of annealing treatment on stability and rheological property of MRFs was investigated. The saturation magnetization ( Ms) of amorphous Fe-Si-B particles after annealing at 550°C is 131.5 emu/g, which is higher than that of amorphous Fe-Si-B particles without annealing. Moreover, the stability of MRF with annealed amorphous Fe-Si-B particles is better than that of MRF without annealed amorphous Fe-Si-B particles. Stearic acid at 3 wt% was added to the MRF2 to enhance the fluid stability to greater than 90%. In addition, the rheological properties demonstrate that the prepared amorphous particle MRF shows relatively strong magnetic responsiveness, especially when the magnetic field strength reaches 365 kA/m. As the magnetic field intensified, the yield stress increased dramatically and followed the Herschel-Bulkley model.

scholarly journals Analysis of dengue model with fractal-fractional Caputo–Fabrizio operator

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Fatmawati ◽  
Muhammad Altaf Khan ◽  
Cicik Alfiniyah ◽  
Ebraheem Alzahrani
Keyword(s):  
Statistical Data ◽  
Dengue Infection ◽  
Fractional Operator ◽  
Novel Approach ◽  
Reduction Number ◽  
Best Fitting ◽  
The Stability ◽  
Parameter Values ◽  
Graphical Illustration ◽  
Stability Results

AbstractIn this work, we study the dengue dynamics with fractal-factional Caputo–Fabrizio operator. We employ real statistical data of dengue infection cases of East Java, Indonesia, from 2018 and parameterize the dengue model. The estimated basic reduction number for this dataset is $\mathcal{R}_{0}\approx2.2020$ R 0 ≈ 2.2020 . We briefly show the stability results of the model for the case when the basic reproduction number is $\mathcal{R}_{0} <1$ R 0 < 1 . We apply the fractal-fractional operator in the framework of Caputo–Fabrizio to the model and present its numerical solution by using a novel approach. The parameter values estimated for the model are used to compare with fractal-fractional operator, and we suggest that the fractal-fractional operator provides the best fitting for real cases of dengue infection when varying the values of both operators’ orders. We suggest some more graphical illustration for the model variables with various orders of fractal and fractional.

Durability of BFRP and Hybrid FRP Sheets under Freeze-Thaw Cycling

2010 ◽  
Vol 163-167 ◽  
pp. 3297-3300 ◽  
Author(s):  
Jia Wei Shi ◽  
Hong Zhu ◽  
Zhi Shen Wu ◽  
Gang Wu
Keyword(s):  
Mechanical Properties ◽  
Test Data ◽  
Mechanical Characteristics ◽  
Test Results ◽  
Freeze Thaw ◽  
Frp Composites ◽  
Test Parameters ◽  
The Stability ◽  
Better Than

Coupon tests were conducted to investigate the mechanical characteristics of basalt FRP (BFRP) sheet, basalt-carbon hybrid FRP sheets and the corresponding epoxy rein under the effect of freeze-thaw cycling. FRP sheets and epoxy rein coupons were subjected to up to 200 and 250 freeze-thaw cycles respectively. Test parameters included the number of freeze-thaw cycles and the types of FRP composites. Test results show that (1) BFRP sheet perform better than CFRP or GFRP sheets under high freeze-thaw cycles; (2) exposed hybrid FRP sheets not only show very little loss in mechanical properties, but also contribute to the stability of test data; (3) mechanical properties of rein epoxy decrease significantly with increasing freeze-thaw cycles.

Sign in / Sign up

Export Citation Format

Share Document