Ahmad Fauzan Kadmin
Universiti Teknikal Malaysia Melaka

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Implementation of Algorithm for Vehicle Anti-Collision Alert System in FPGA Aiman Zakwan Jidin; Lim Siau Li; Ahmad Fauzan Kadmin
International Journal of Electrical and Computer Engineering (IJECE) Vol 7, No 2: April 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (434.116 KB) | DOI: 10.11591/ijece.v7i2.pp775-783

Abstract

Vehicle safety has becoming one of the important issues nowadays, due to the fact the number of road accidents, which cause injuries, deaths and also damages, keeps on increasing. One of the main factors which contribute to these accidents are human's lack of awareness and also carelessness. This paper presents the development and implementation of an algorithm to be utilized for vehicle anti-collision alert system, which may be useful to reduce the occurrence of accidents. This algorithm, which is to be deployed with the front sensors of the vehicle, is capable of alerting any occurrence of sudden slowing or static vehicles ahead, by sensing the rate of distance change. Furthermore, it also triggers an alert if the driver is breaching the safe distance from the vehicle ahead. This algorithm has been successfully implemented in Altera DE0 FPGA and its functionality was validated via hardware experimental tests.
A new function of stereo matching algorithm based on hybrid convolutional neural network Mohd Saad Hamid; Nurulfajar Abd Manap; Rostam Affendi Hamzah; Ahmad Fauzan Kadmin; Shamsul Fakhar Abd Gani; Adi Irwan Herman
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 1: January 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v25.i1.pp223-231

Abstract

This paper proposes a new hybrid method between the learning-based and handcrafted methods for a stereo matching algorithm. The main purpose of the stereo matching algorithm is to produce a disparity map. This map is essential for many applications, including three-dimensional (3D) reconstruction. The raw disparity map computed by a convolutional neural network (CNN) is still prone to errors in the low texture region. The algorithm is set to improve the matching cost computation stage with hybrid CNN-based combined with truncated directional intensity computation. The difference in truncated directional intensity value is employed to decrease radiometric errors. The proposed method’s raw matching cost went through the cost aggregation step using the bilateral filter (BF) to improve accuracy. The winner-take-all (WTA) optimization uses the aggregated cost volume to produce an initial disparity map. Finally, a series of refinement processes enhance the initial disparity map for a more accurate final disparity map. This paper verified the performance of the algorithm using the Middlebury online stereo benchmarking system. The proposed algorithm achieves the objective of generating a more accurate and smooth disparity map with different depths at low texture regions through better matching cost quality.