Multifunctional integrated system-on-chip for old people nursing
A system-on-chip, multi-functional technology, applied in the field of multi-functional integrated system-on-chip, which can solve the problems of low accuracy, high cost, and scattered functions
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0116] This embodiment describes the composition, connection relationship, working process and advantages of the system of the present invention. The terms used are explained in Table 1 below:
[0117] Explanation of terms in the multifunctional integrated system-on-chip for elderly care described in Table 1
[0118]
[0119]
[0120] During specific implementation, the embedded system on chip is a PYNQ-Z2 development board; the external hardware module is an FPGA external hardware module; the schematic diagram of each module is as follows figure 1 , the hardware connection relationship such as Figure 5 . gesture recognition systems such as figure 2 Shown; when the support vector memory is implemented, by figure 2 The implementation of SV ROMn in the bias memory is implemented by figure 2 Bias ROM implementation in .
[0121] The implementation process of gesture recognition is as follows:
[0122] 1) Take pictures of the 10 gestures of the numbers "1" - "10"...
Embodiment 2
[0140] During specific implementation, the embedded system-on-chip is a PYNQ-Z2 development board; the external hardware module is an FPGA external hardware module, and the vegetable feeding system is as follows: image 3 shown. The implementation process of the vegetable feeding system is as follows:
[0141] (1) Write a python crawler code, and read 200 pictures of 4 types of dishes that need to be classified from Baidu pictures;
[0142] (2) Write an image processing function to compress the images of the four types of dishes that need to be classified into 32*32 images, and then generate a csv file. The csv file contains the storage address and label of each image;
[0143] (3) Use the pytorch official neural network programming template to import the data to be trained from the csv file, define the neural network according to the network definition method in the above invention content, and call the visdom function library to write the accuracy observation program;
[...
Embodiment 3
[0152] During specific implementation, the embedded system-on-chip is a PYNQ-Z2 development board; the external hardware module is an FPGA external hardware module; the fall rescue system is as follows: Figure 4 As shown, in the specific implementation, the binocular stereo matching operation is allocated to the PL end, which is 2 times faster than the PS end implementation. The implementation process of the fall rescue system is as follows:
[0153] a. Hold a binocular camera and shoot 21 sets of left and right synchronized images from all angles of the calibration chessboard. Use the calibration toolbox stereoCameraCalibrator in MATLAB to perform stereo calibration on the left and right cameras to obtain the external and internal parameters of the camera, and the calibration error Controlled at 0.18;
[0154] b. Use the parameters obtained by camera calibration to correct, so that the distortion caused by the reprojection of the left and right images is the smallest, and t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com