Tactile Signal Reconstruction Assisted by Video Processing

Because of prior knowledge, a person will deduce the strength of the contact force using only visual input. This research proposes a method for cross-modal signal processing to recover tactile information by using visual input. According to our method, visual information supplements tactile information as an auxiliary source. Our paper starts with a group of photos (GOPs) and uses them as input. Second, to identify regions of in-terest(ROI), we employ the low-rank foreground based attention mechanism (LAM). In order to determine contact force in video frames, we prefer to suggest a linear regression convolutional neural network (LRCNN). Results from experiments support our ability to rebuild sentience. Additionally, simulation results as compared to alternative methods of work, our method can save network costs while also increasing the accuracy of material identification.

[1]  Takahiro Nozaki,et al.  Haptic Data Prediction and Extrapolation for Communication Traffic Reduction of Four-Channel Bilateral Control System , 2021, IEEE Transactions on Industrial Informatics.

[2]  Jianxin Chen,et al.  Cross-Modal Stream Scheduling for eHealth , 2021, IEEE Journal on Selected Areas in Communications.

[3]  Wonjun Hwang,et al.  Sequential Image-Based Attention Network for Inferring Force Estimation Without Haptic Sensor , 2018, IEEE Access.

[4]  Gang Wang,et al.  Progressive Attention Guided Recurrent Network for Salient Object Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Jie Chen,et al.  Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Wonjun Hwang,et al.  Inferring Interaction Force from Visual Information without Using Physical Force Sensors , 2017, Sensors.

[7]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Xiaogang Wang,et al.  Residual Attention Network for Image Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Eman Ahmed,et al.  House Price Estimation from Visual and Textual Features , 2016, IJCCI.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Anil K. Jain,et al.  A background model initialization algorithm for video surveillance , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[14]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[15]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.