Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction
Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/7/1848 |
| _version_ | 1797607109407277056 |
|---|---|
| author | Ding Yu Aihua Li Jinrui Li Yan Xu Yinping Long |
| author_facet | Ding Yu Aihua Li Jinrui Li Yan Xu Yinping Long |
| author_sort | Ding Yu |
| collection | DOAJ |
| description | Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary accuracy. It is insufficient for determining mapping accuracy. Furthermore, traditional remote sensing mapping methods struggle to match the inflection points encountered in artificial intelligence contour extraction. In order to address these issues, we propose the mean inflection point distance (MPD) as a new segmentation evaluation method. MPD can accurately calculate error values and solve the problem of multiple inflection points, which traditional remote sensing mapping cannot match. We tested three algorithms on the Vaihingen dataset: Mask R-CNN, Swin Transformer, and PointRend. The results show that MPD is highly sensitive to mapping accuracy, can calculate error values accurately, and is applicable for different scales of mapping accuracy while maintaining high visual consistency. This study helps to assess the accuracy of automatic mapping using remote sensing artificial intelligence. |
| first_indexed | 2024-03-11T05:25:40Z |
| format | Article |
| id | doaj.art-4416a82807ea43e4859c4af0069a1a36 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:25:40Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4416a82807ea43e4859c4af0069a1a362023-11-17T17:29:50ZengMDPI AGRemote Sensing2072-42922023-03-01157184810.3390/rs15071848Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building ExtractionDing Yu0Aihua Li1Jinrui Li2Yan Xu3Yinping Long4Xi’an Research Institute of High Technology, Xi’an 710025, ChinaXi’an Research Institute of High Technology, Xi’an 710025, ChinaHubei Key Laboratory of Petroleum Geochemistry and Environment, Yangtze University, Wuhan 430100, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan 430100, ChinaCollege of Resources and Environment, Chengdu University of Information Technology, Chengdu 610225, ChinaMapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary accuracy. It is insufficient for determining mapping accuracy. Furthermore, traditional remote sensing mapping methods struggle to match the inflection points encountered in artificial intelligence contour extraction. In order to address these issues, we propose the mean inflection point distance (MPD) as a new segmentation evaluation method. MPD can accurately calculate error values and solve the problem of multiple inflection points, which traditional remote sensing mapping cannot match. We tested three algorithms on the Vaihingen dataset: Mask R-CNN, Swin Transformer, and PointRend. The results show that MPD is highly sensitive to mapping accuracy, can calculate error values accurately, and is applicable for different scales of mapping accuracy while maintaining high visual consistency. This study helps to assess the accuracy of automatic mapping using remote sensing artificial intelligence.https://www.mdpi.com/2072-4292/15/7/1848segmentation evaluationdeep learningmean inflection point |
| spellingShingle | Ding Yu Aihua Li Jinrui Li Yan Xu Yinping Long Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction Remote Sensing segmentation evaluation deep learning mean inflection point |
| title | Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction |
| title_full | Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction |
| title_fullStr | Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction |
| title_full_unstemmed | Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction |
| title_short | Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction |
| title_sort | mean inflection point distance artificial intelligence mapping accuracy evaluation index an experimental case study of building extraction |
| topic | segmentation evaluation deep learning mean inflection point |
| url | https://www.mdpi.com/2072-4292/15/7/1848 |
| work_keys_str_mv | AT dingyu meaninflectionpointdistanceartificialintelligencemappingaccuracyevaluationindexanexperimentalcasestudyofbuildingextraction AT aihuali meaninflectionpointdistanceartificialintelligencemappingaccuracyevaluationindexanexperimentalcasestudyofbuildingextraction AT jinruili meaninflectionpointdistanceartificialintelligencemappingaccuracyevaluationindexanexperimentalcasestudyofbuildingextraction AT yanxu meaninflectionpointdistanceartificialintelligencemappingaccuracyevaluationindexanexperimentalcasestudyofbuildingextraction AT yinpinglong meaninflectionpointdistanceartificialintelligencemappingaccuracyevaluationindexanexperimentalcasestudyofbuildingextraction |