The Use of DCNN for Road Path Detection and Segmentation

Authors

  • Nada Mohammed Murad SMART Lab. Institut Supérieur de Gestion de Tunis (ISG), Université de Tunis, 41 Avenue de la Liberté Bouchoucha, 2000, Tunisia. https://orcid.org/0000-0002-0672-4291
  • Lilia Rejeb SMART Lab. Institut Supérieur de Gestion de Tunis (ISG), Université de Tunis, 41 Avenue de la Liberté Bouchoucha, 2000, Tunisia.
  • Lamjed Ben Said SMART Lab. Institut Supérieur de Gestion de Tunis (ISG), Université de Tunis, 41 Avenue de la Liberté Bouchoucha, 2000, Tunisia.

DOI:

https://doi.org/10.52866/ijcsm.2022.02.01.013

Keywords:

Machine Learning, Deep Learning, Road Paths, Segmentation, Detection, Neural Network, DCNN

Abstract

 In this study, various organizations that have participated in several road path-detecting experiments are analyzed. However, the majority of techniques rely on attributes or form models built by humans to identify sections of the path. In this paper, a suggestion was made regarding a road path recognition structure that is dependent on a deep convolutional neural network. A tiny neural network has been developed to perform feature extraction to a massive collection of photographs to extract the suitable path feature. The parameters obtained from the model of the route classification network are utilized in the process of establishing the parameters of the layers that constitute the path detection network. The deep convolutional path discovery network’s production is pixel-based and focuses on the identification of path types and positions. To train it, a detection failure job is provided. Failure in path classification and regression are the two components that make up a planned detection failure function. Instead of laborious postprocessing, a straightforward solution to the problem of route marking can be found using observed path pixels in conjunction with a consensus of random examples. According to the findings of the experiments, the classification precision of the network for classifying every kind is higher than 98.3%. The simulation that was trained using the suggested detection failure function is capable of achieving an accuracy of detection that is 85.5% over a total of 30 distinct scenarios on the road.

Downloads

Download data is not yet available.

Downloads

Published

2022-06-15

How to Cite

[1]
N. M. Murad, L. . Rejeb, and L. . Ben Said, “The Use of DCNN for Road Path Detection and Segmentation”, Iraqi Journal For Computer Science and Mathematics, vol. 3, no. 2, pp. 119–127, Jun. 2022.
CITATION
DOI: 10.52866/ijcsm.2022.02.01.013
Published: 2022-06-15

Issue

Section

Articles