Performance evaluation for vision-based vehicle classification using Convolutional Neural Network
Vision-based vehicle classification is a very challenging task due to vehicle pose and angle variations, weather conditions, lighting qual ity, and limited number of available datasets for training. It can be applied for driver assistance system and autonomous veh icles. This paper conducted a perfo...
| Published in: | International Journal of Engineering and Technology(UAE) |
|---|---|
| Main Author: | |
| Format: | Article |
| Language: | English |
| Published: |
Science Publishing Corporation Inc
2018
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067270894&doi=10.14419%2fijet.v7i3.15.17507&partnerID=40&md5=5e8b44f252b78df47d85b844e074de25 |
| id |
2-s2.0-85067270894 |
|---|---|
| spelling |
2-s2.0-85067270894 Safiyah R.D.; Rahim Z.A.; Syafiq S.; Ibrahim Z.; Sabri N. Performance evaluation for vision-based vehicle classification using Convolutional Neural Network 2018 International Journal of Engineering and Technology(UAE) 7 3 10.14419/ijet.v7i3.15.17507 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067270894&doi=10.14419%2fijet.v7i3.15.17507&partnerID=40&md5=5e8b44f252b78df47d85b844e074de25 Vision-based vehicle classification is a very challenging task due to vehicle pose and angle variations, weather conditions, lighting qual ity, and limited number of available datasets for training. It can be applied for driver assistance system and autonomous veh icles. This paper conducted a performance evaluation for this task based on three Convolutional Neural Network (CNN) models, which are simple CNN, and pretrained CNN models that are AlexNet and GoogleNet. A dataset of more than 7000 images from the Image Processing Group (IPG) has been used for training and testing and the results indicate that AlexNet achieves the best classification result that is 65.09%. This result is obtained because of the variations of the quality of the images. © 2018 Authors. Science Publishing Corporation Inc 2227524X English Article All Open Access; Bronze Open Access |
| author |
Safiyah R.D.; Rahim Z.A.; Syafiq S.; Ibrahim Z.; Sabri N. |
| spellingShingle |
Safiyah R.D.; Rahim Z.A.; Syafiq S.; Ibrahim Z.; Sabri N. Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| author_facet |
Safiyah R.D.; Rahim Z.A.; Syafiq S.; Ibrahim Z.; Sabri N. |
| author_sort |
Safiyah R.D.; Rahim Z.A.; Syafiq S.; Ibrahim Z.; Sabri N. |
| title |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| title_short |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| title_full |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| title_fullStr |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| title_full_unstemmed |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| title_sort |
Performance evaluation for vision-based vehicle classification using Convolutional Neural Network |
| publishDate |
2018 |
| container_title |
International Journal of Engineering and Technology(UAE) |
| container_volume |
7 |
| container_issue |
3 |
| doi_str_mv |
10.14419/ijet.v7i3.15.17507 |
| url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067270894&doi=10.14419%2fijet.v7i3.15.17507&partnerID=40&md5=5e8b44f252b78df47d85b844e074de25 |
| description |
Vision-based vehicle classification is a very challenging task due to vehicle pose and angle variations, weather conditions, lighting qual ity, and limited number of available datasets for training. It can be applied for driver assistance system and autonomous veh icles. This paper conducted a performance evaluation for this task based on three Convolutional Neural Network (CNN) models, which are simple CNN, and pretrained CNN models that are AlexNet and GoogleNet. A dataset of more than 7000 images from the Image Processing Group (IPG) has been used for training and testing and the results indicate that AlexNet achieves the best classification result that is 65.09%. This result is obtained because of the variations of the quality of the images. © 2018 Authors. |
| publisher |
Science Publishing Corporation Inc |
| issn |
2227524X |
| language |
English |
| format |
Article |
| accesstype |
All Open Access; Bronze Open Access |
| record_format |
scopus |
| collection |
Scopus |
| _version_ |
1809678160377151488 |