Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation
Motivated by applications in topographic map information extraction, our goal was to discover a practical method for scanned topographic map (STM) segmentation. We present an advanced guided watershed transform (AGWT) to generate superpixels on STM. AGWT utilizes the information from both linear and...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/20/3421 |
| _version_ | 1797550601714794496 |
|---|---|
| author | Tiange Liu Qiguang Miao Pengfei Xu Shihui Zhang |
| author_facet | Tiange Liu Qiguang Miao Pengfei Xu Shihui Zhang |
| author_sort | Tiange Liu |
| collection | DOAJ |
| description | Motivated by applications in topographic map information extraction, our goal was to discover a practical method for scanned topographic map (STM) segmentation. We present an advanced guided watershed transform (AGWT) to generate superpixels on STM. AGWT utilizes the information from both linear and area elements to modify detected boundary maps and sequentially achieve superpixels based on the watershed transform. With achieving an average of 0.06 on under-segmentation error, 0.96 on boundary recall, and 0.95 on boundary precision, it has been proven to have strong ability in boundary adherence, with fewer over-segmentation issues. Based on AGWT, a benchmark for STM segmentation based on superpixels and a shallow convolutional neural network (SCNN), termed SSCNN, is proposed. There are several notable ideas behind the proposed approach. Superpixels are employed to overcome the false color and color aliasing problems that exist in STMs. The unification method of random selection facilitates sufficient training data with little manual labeling while keeping the potential color information of each geographic element. Moreover, with the small number of parameters, SCNN can accurately and efficiently classify those unified pixel sequences. The experiments show that SSCNN achieves an overall F1 score of 0.73 on our STM testing dataset. They also show the quality of the segmentation results and the short run time of this approach, which makes it applicable to full-size maps. |
| first_indexed | 2024-03-10T15:31:38Z |
| format | Article |
| id | doaj.art-80b4f175b20d421eab5cbd5305f83379 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:31:38Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-80b4f175b20d421eab5cbd5305f833792023-11-20T17:35:13ZengMDPI AGRemote Sensing2072-42922020-10-011220342110.3390/rs12203421Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map SegmentationTiange Liu0Qiguang Miao1Pengfei Xu2Shihui Zhang3School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710126, ChinaInformation Science and Technology School, Northwest University, Xi’an 710127, ChinaSchool of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaMotivated by applications in topographic map information extraction, our goal was to discover a practical method for scanned topographic map (STM) segmentation. We present an advanced guided watershed transform (AGWT) to generate superpixels on STM. AGWT utilizes the information from both linear and area elements to modify detected boundary maps and sequentially achieve superpixels based on the watershed transform. With achieving an average of 0.06 on under-segmentation error, 0.96 on boundary recall, and 0.95 on boundary precision, it has been proven to have strong ability in boundary adherence, with fewer over-segmentation issues. Based on AGWT, a benchmark for STM segmentation based on superpixels and a shallow convolutional neural network (SCNN), termed SSCNN, is proposed. There are several notable ideas behind the proposed approach. Superpixels are employed to overcome the false color and color aliasing problems that exist in STMs. The unification method of random selection facilitates sufficient training data with little manual labeling while keeping the potential color information of each geographic element. Moreover, with the small number of parameters, SCNN can accurately and efficiently classify those unified pixel sequences. The experiments show that SSCNN achieves an overall F1 score of 0.73 on our STM testing dataset. They also show the quality of the segmentation results and the short run time of this approach, which makes it applicable to full-size maps.https://www.mdpi.com/2072-4292/12/20/3421scanned topographic mapsegmentationsuperpixelshallow convolutional neural networkwatershed transform |
| spellingShingle | Tiange Liu Qiguang Miao Pengfei Xu Shihui Zhang Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation Remote Sensing scanned topographic map segmentation superpixel shallow convolutional neural network watershed transform |
| title | Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation |
| title_full | Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation |
| title_fullStr | Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation |
| title_full_unstemmed | Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation |
| title_short | Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation |
| title_sort | superpixel based shallow convolutional neural network sscnn for scanned topographic map segmentation |
| topic | scanned topographic map segmentation superpixel shallow convolutional neural network watershed transform |
| url | https://www.mdpi.com/2072-4292/12/20/3421 |
| work_keys_str_mv | AT tiangeliu superpixelbasedshallowconvolutionalneuralnetworksscnnforscannedtopographicmapsegmentation AT qiguangmiao superpixelbasedshallowconvolutionalneuralnetworksscnnforscannedtopographicmapsegmentation AT pengfeixu superpixelbasedshallowconvolutionalneuralnetworksscnnforscannedtopographicmapsegmentation AT shihuizhang superpixelbasedshallowconvolutionalneuralnetworksscnnforscannedtopographicmapsegmentation |