Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification
Vehicle detection and classification are very important for analysis of vehicle behavior in intelligent transportation system, urban computing, etc. In this paper, an approach based on convolutional neural networks (CNNs) has been applied for vehicle classification. In order to achieve a more accura...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2018/3138278 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549581794050048 |
|---|---|
| author | Yunfei Han Tonghai Jiang Yupeng Ma Chunxiang Xu |
| author_facet | Yunfei Han Tonghai Jiang Yupeng Ma Chunxiang Xu |
| author_sort | Yunfei Han |
| collection | DOAJ |
| description | Vehicle detection and classification are very important for analysis of vehicle behavior in intelligent transportation system, urban computing, etc. In this paper, an approach based on convolutional neural networks (CNNs) has been applied for vehicle classification. In order to achieve a more accurate classification, we removed the unrelated background as much as possible based on a trained object detection model. In addition, an unsupervised pretraining approach has been introduced to better initialize CNNs parameters to enhance the classification performance. Through the data enhancement on manual labeled images, we got 2000 labeled images in each category of motorcycle, transporter, passenger, and others, with 1400 samples for training and 600 samples for testing. Then, we got 17395 unlabeled images for layer-wise unsupervised pretraining convolutional layers. A remarkable accuracy of 93.50% is obtained, demonstrating the high classification potential of our approach. |
| format | Article |
| id | doaj-art-6c9c23815d9a40e9b2e6104b0435582f |
| institution | Kabale University |
| issn | 1687-5680 1687-5699 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj-art-6c9c23815d9a40e9b2e6104b0435582f2025-02-03T06:11:01ZengWileyAdvances in Multimedia1687-56801687-56992018-01-01201810.1155/2018/31382783138278Pretraining Convolutional Neural Networks for Image-Based Vehicle ClassificationYunfei Han0Tonghai Jiang1Yupeng Ma2Chunxiang Xu3The Xinjiang Technical Institute of Physics & Chemistry, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Urumqi 830011, ChinaVehicle detection and classification are very important for analysis of vehicle behavior in intelligent transportation system, urban computing, etc. In this paper, an approach based on convolutional neural networks (CNNs) has been applied for vehicle classification. In order to achieve a more accurate classification, we removed the unrelated background as much as possible based on a trained object detection model. In addition, an unsupervised pretraining approach has been introduced to better initialize CNNs parameters to enhance the classification performance. Through the data enhancement on manual labeled images, we got 2000 labeled images in each category of motorcycle, transporter, passenger, and others, with 1400 samples for training and 600 samples for testing. Then, we got 17395 unlabeled images for layer-wise unsupervised pretraining convolutional layers. A remarkable accuracy of 93.50% is obtained, demonstrating the high classification potential of our approach.http://dx.doi.org/10.1155/2018/3138278 |
| spellingShingle | Yunfei Han Tonghai Jiang Yupeng Ma Chunxiang Xu Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification Advances in Multimedia |
| title | Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification |
| title_full | Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification |
| title_fullStr | Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification |
| title_full_unstemmed | Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification |
| title_short | Pretraining Convolutional Neural Networks for Image-Based Vehicle Classification |
| title_sort | pretraining convolutional neural networks for image based vehicle classification |
| url | http://dx.doi.org/10.1155/2018/3138278 |
| work_keys_str_mv | AT yunfeihan pretrainingconvolutionalneuralnetworksforimagebasedvehicleclassification AT tonghaijiang pretrainingconvolutionalneuralnetworksforimagebasedvehicleclassification AT yupengma pretrainingconvolutionalneuralnetworksforimagebasedvehicleclassification AT chunxiangxu pretrainingconvolutionalneuralnetworksforimagebasedvehicleclassification |