HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model
Map annotation interpretation is crucial for geographic information extraction and intelligent map analysis. This study addresses the challenges associated with interpreting Chinese map annotations, specifically visual complexity and data scarcity issues, by proposing a hybrid intelligence-based mul...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/204 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587574232743936 |
|---|---|
| author | Jiaxin Ren Wanzeng Liu Jun Chen Xiuli Zhu Ran Li Tingting Zhao Jiadong Zhang Yuan Tao Shunxi Yin Xi Zhai Yunlu Peng Xinpeng Wang |
| author_facet | Jiaxin Ren Wanzeng Liu Jun Chen Xiuli Zhu Ran Li Tingting Zhao Jiadong Zhang Yuan Tao Shunxi Yin Xi Zhai Yunlu Peng Xinpeng Wang |
| author_sort | Jiaxin Ren |
| collection | DOAJ |
| description | Map annotation interpretation is crucial for geographic information extraction and intelligent map analysis. This study addresses the challenges associated with interpreting Chinese map annotations, specifically visual complexity and data scarcity issues, by proposing a hybrid intelligence-based multi-source unstructured Chinese map annotation interpretation method (HI-CMAIM). Firstly, leveraging expert knowledge in an innovative way, we constructed a high-quality expert knowledge-based map annotation dataset (EKMAD), which significantly enhanced data diversity and accuracy. Furthermore, an improved annotation detection model (CMA-DB) and an improved annotation recognition model (CMA-CRNN) were designed based on the characteristics of map annotations, both incorporating expert knowledge. A two-stage transfer learning strategy was employed to tackle the issue of limited training samples. Experimental results demonstrated the superiority of HI-CMAIM over existing algorithms. In the detection task, CMA-DB achieved an 8.54% improvement in Hmean (from 87.73% to 96.27%) compared to the DB algorithm. In the recognition task, CMA-CRNN achieved a 15.54% improvement in accuracy (from 79.77% to 95.31%) and a 4-fold reduction in NED (from 0.1026 to 0.0242), confirming the effectiveness and advancement of the proposed method. This research not only provides a novel approach and data support for Chinese map annotation interpretation but also fills the gap of high-quality, diverse datasets. It holds practical application value in fields such as geographic information systems and cartography, significantly contributing to the advancement of intelligent map interpretation. |
| format | Article |
| id | doaj-art-6a86b539726c402ab9c2722ebb94f445 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-6a86b539726c402ab9c2722ebb94f4452025-01-24T13:47:43ZengMDPI AGRemote Sensing2072-42922025-01-0117220410.3390/rs17020204HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation ModelJiaxin Ren0Wanzeng Liu1Jun Chen2Xiuli Zhu3Ran Li4Tingting Zhao5Jiadong Zhang6Yuan Tao7Shunxi Yin8Xi Zhai9Yunlu Peng10Xinpeng Wang11School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaNational Geomatics Center of China, Beijing 100830, ChinaMap annotation interpretation is crucial for geographic information extraction and intelligent map analysis. This study addresses the challenges associated with interpreting Chinese map annotations, specifically visual complexity and data scarcity issues, by proposing a hybrid intelligence-based multi-source unstructured Chinese map annotation interpretation method (HI-CMAIM). Firstly, leveraging expert knowledge in an innovative way, we constructed a high-quality expert knowledge-based map annotation dataset (EKMAD), which significantly enhanced data diversity and accuracy. Furthermore, an improved annotation detection model (CMA-DB) and an improved annotation recognition model (CMA-CRNN) were designed based on the characteristics of map annotations, both incorporating expert knowledge. A two-stage transfer learning strategy was employed to tackle the issue of limited training samples. Experimental results demonstrated the superiority of HI-CMAIM over existing algorithms. In the detection task, CMA-DB achieved an 8.54% improvement in Hmean (from 87.73% to 96.27%) compared to the DB algorithm. In the recognition task, CMA-CRNN achieved a 15.54% improvement in accuracy (from 79.77% to 95.31%) and a 4-fold reduction in NED (from 0.1026 to 0.0242), confirming the effectiveness and advancement of the proposed method. This research not only provides a novel approach and data support for Chinese map annotation interpretation but also fills the gap of high-quality, diverse datasets. It holds practical application value in fields such as geographic information systems and cartography, significantly contributing to the advancement of intelligent map interpretation.https://www.mdpi.com/2072-4292/17/2/204intelligentized surveying and mappinghybrid intelligenceunstructured mapsChinese recognitionannotation interpretationexpert knowledge |
| spellingShingle | Jiaxin Ren Wanzeng Liu Jun Chen Xiuli Zhu Ran Li Tingting Zhao Jiadong Zhang Yuan Tao Shunxi Yin Xi Zhai Yunlu Peng Xinpeng Wang HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model Remote Sensing intelligentized surveying and mapping hybrid intelligence unstructured maps Chinese recognition annotation interpretation expert knowledge |
| title | HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model |
| title_full | HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model |
| title_fullStr | HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model |
| title_full_unstemmed | HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model |
| title_short | HI-CMAIM: Hybrid Intelligence-Based Multi-Source Unstructured Chinese Map Annotation Interpretation Model |
| title_sort | hi cmaim hybrid intelligence based multi source unstructured chinese map annotation interpretation model |
| topic | intelligentized surveying and mapping hybrid intelligence unstructured maps Chinese recognition annotation interpretation expert knowledge |
| url | https://www.mdpi.com/2072-4292/17/2/204 |
| work_keys_str_mv | AT jiaxinren hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT wanzengliu hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT junchen hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT xiulizhu hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT ranli hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT tingtingzhao hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT jiadongzhang hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT yuantao hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT shunxiyin hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT xizhai hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT yunlupeng hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel AT xinpengwang hicmaimhybridintelligencebasedmultisourceunstructuredchinesemapannotationinterpretationmodel |