A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions
Recognizing the patterns of road junctions in a road network plays a crucial role in various applications. Owing to the diversity and complexity of morphologies of road junctions, traditional methods that rely heavily on manual settings of features and rules are often problematic. In recent years, s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/10/523 |
| _version_ | 1797472812274810880 |
|---|---|
| author | Min Yang Lingya Cheng Minjun Cao Xiongfeng Yan |
| author_facet | Min Yang Lingya Cheng Minjun Cao Xiongfeng Yan |
| author_sort | Min Yang |
| collection | DOAJ |
| description | Recognizing the patterns of road junctions in a road network plays a crucial role in various applications. Owing to the diversity and complexity of morphologies of road junctions, traditional methods that rely heavily on manual settings of features and rules are often problematic. In recent years, several studies have employed convolutional neural networks (CNNs) to classify complex junctions. These methods usually convert vector-based junctions into raster representations with a predefined sampling area coverage. However, a fixed sampling area coverage cannot ensure the integrity and clarity of each junction, which inevitably leads to misclassification. To overcome this drawback, this study proposes a stacking ensemble learning method for classifying the patterns of complex road junctions. In this method, each junction is first converted into raster images with multiple area coverages. Subsequently, several CNN-based base-classifiers are trained using raster images, and they output the probabilities of the junction belonging to different patterns. Finally, a meta-classifier based on random forest is used to combine the outputs of the base-classifiers and learn to arrive at the final classification. Experimental results show that the proposed method can improve the classification accuracy for complex road junctions compared to existing CNN-based classifiers that are trained using raster representations of junctions with a fixed sampling area coverage. |
| first_indexed | 2024-03-09T20:07:26Z |
| format | Article |
| id | doaj.art-1ac20bcf04e84a009e7749675201df0f |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T20:07:26Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-1ac20bcf04e84a009e7749675201df0f2023-11-24T00:27:31ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-10-01111052310.3390/ijgi11100523A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road JunctionsMin Yang0Lingya Cheng1Minjun Cao2Xiongfeng Yan3School of Resource and Environmental Sciences, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaCollege of Surveying and Geo-Informatics, Tongji University, 1239 Siping Road, Shanghai 200092, ChinaRecognizing the patterns of road junctions in a road network plays a crucial role in various applications. Owing to the diversity and complexity of morphologies of road junctions, traditional methods that rely heavily on manual settings of features and rules are often problematic. In recent years, several studies have employed convolutional neural networks (CNNs) to classify complex junctions. These methods usually convert vector-based junctions into raster representations with a predefined sampling area coverage. However, a fixed sampling area coverage cannot ensure the integrity and clarity of each junction, which inevitably leads to misclassification. To overcome this drawback, this study proposes a stacking ensemble learning method for classifying the patterns of complex road junctions. In this method, each junction is first converted into raster images with multiple area coverages. Subsequently, several CNN-based base-classifiers are trained using raster images, and they output the probabilities of the junction belonging to different patterns. Finally, a meta-classifier based on random forest is used to combine the outputs of the base-classifiers and learn to arrive at the final classification. Experimental results show that the proposed method can improve the classification accuracy for complex road junctions compared to existing CNN-based classifiers that are trained using raster representations of junctions with a fixed sampling area coverage.https://www.mdpi.com/2220-9964/11/10/523complex road junctionpattern classificationconvolutional neural networkstacking ensemblearea coverage |
| spellingShingle | Min Yang Lingya Cheng Minjun Cao Xiongfeng Yan A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions ISPRS International Journal of Geo-Information complex road junction pattern classification convolutional neural network stacking ensemble area coverage |
| title | A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions |
| title_full | A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions |
| title_fullStr | A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions |
| title_full_unstemmed | A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions |
| title_short | A Stacking Ensemble Learning Method to Classify the Patterns of Complex Road Junctions |
| title_sort | stacking ensemble learning method to classify the patterns of complex road junctions |
| topic | complex road junction pattern classification convolutional neural network stacking ensemble area coverage |
| url | https://www.mdpi.com/2220-9964/11/10/523 |
| work_keys_str_mv | AT minyang astackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT lingyacheng astackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT minjuncao astackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT xiongfengyan astackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT minyang stackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT lingyacheng stackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT minjuncao stackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions AT xiongfengyan stackingensemblelearningmethodtoclassifythepatternsofcomplexroadjunctions |