(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Tracking system using neural network

Tracking system using neural network / Chong Chee Moi
Pengguna kerusi roda mungkin menghadapi kesukaran untuk membawa bagasi mereka semasa melakukan perjalanan. Penyelesaian yang dicadangkan telah diperkenalkan demi mengatasi masalah yang dinyatakan. Pengikut kereta yang mengunakan sensor visual telah dicadangkan demi memudahkan mobiliti kerusi roda apabila membawa bagasi. Kereta itu akan menjejaki dan mengikuti kerusi roda dalam jarak yang sesuai. Kamera berfungsi sebagai input untuk membiarkan kereta dapat mengesan dan mengikuti kerusi roda. Sensor Visi (Pixy CMUcam5) telah digunakan untuk mengesan corak warna yang telah ditetapkan. Sensor berasaskan visual mengumpul maklumat papan corak warna yang terletak di belakang kerusi roda dan mengumbulkan maklumat-maklumat yang diperlukan. Maklumat yang dikumpulkan akan dilatihkan dengan rangkaian neural demi mendapatkan maklumat kedudukan relatif, seperti jarak dan sudut condong. Nilai MSE yang diperoleh ialah 0.14007. Rangkaian neural akan dilaksanakan ke dalam FPGA. Pelaksanaan rangkaian neural pada FPGA boleh dilakukan melalui konfigurasi perisian dan perkakasan. Nilai ralat untuk jarak keluaran kurang daripada 0.8000 manakala nilai ralat untuk sudut keluaran kurang dari 0.3000 semasa simulasi. _______________________________________________________________________________________________________ Wheelchair users might face difficulty to carry their luggage when traveling. A proposed solution is introduced based on the problem stated. A visual-based sensor cart follower is proposed to ease the mobility of a wheelchair in carrying their luggage. The cart will track and follow the wheelchair in a suitable distance. A Camera acts as input to let cart able to track and follow the wheelchair, Vision sensor (Pixy CMUcam5) is used to detect the predefined colour pattern in this project. The visually based sensor gathered the information of the colour pattern board which situated behind the wheelchair and translate the gathered information into relative position information, such as distance and skew angle which helps the cart in following the wheelchair. This translation can be done in the neural network. The Mean Squared Error (MSE) value obtained is 0.14007. The neural network can be implemented in the Field Gate Programmable Array (FPGA). The implementation of the neural network on the FPGA can be done through software and hardware configuration. The error value in predict the distance is less than 0.8000 while the error value in predict the skew angle is less than 0.3000.
Contributor(s):
Chong Chee Moi - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875008682
Language:
English
Subject Keywords:
Wheelchair; luggage; mobility
First presented to the public:
6/1/2019
Original Publication Date:
3/4/2020
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 89
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2020-03-04 15:21:34.577
Date Last Updated
2020-12-14 13:21:22.666
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Tracking system using neural network1 2020-03-04 15:21:34.577