A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans
Most studies on map segmentation and recognition are focused on architectural floor plans, while there are very few analyses of shopping mall plans. The objective of the work is to accurately segment and recognize the shopping mall plan, obtaining location and semantic information for each room via...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/7/2510 |
_version_ | 1797437814465363968 |
---|---|
author | Ming Su Wei Shi Dangjun Zhao Dongyang Cheng Junchao Zhang |
author_facet | Ming Su Wei Shi Dangjun Zhao Dongyang Cheng Junchao Zhang |
author_sort | Ming Su |
collection | DOAJ |
description | Most studies on map segmentation and recognition are focused on architectural floor plans, while there are very few analyses of shopping mall plans. The objective of the work is to accurately segment and recognize the shopping mall plan, obtaining location and semantic information for each room via segmentation and recognition. This work can be used in other applications such as indoor robot navigation, building area and location analysis, and three-dimensional reconstruction. First, we identify and match the catalog of a mall floor plan to obtain matching text, and then we use the two-stage region growth method we proposed to segment the preprocessed floor plan. The room number is then obtained by sending each segmented room section to an OCR (optical character recognition) system for identification. Finally, the system retrieves the matching text to match the room number in order to obtain the room name, and outputs the needed room location and semantic information. It is considered a successful detection when a room region can be successfully segmented and identified. The proposed method is evaluated on a dataset including 1340 rooms. Experimental results show that the accuracy of room segmentation is 92.54%, and the accuracy of room recognition is 90.56%. The total detection accuracy is 83.81%. |
first_indexed | 2024-03-09T11:28:04Z |
format | Article |
id | doaj.art-f1c85d9953c24d33a8c5d26e27381d0f |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T11:28:04Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f1c85d9953c24d33a8c5d26e27381d0f2023-11-30T23:59:53ZengMDPI AGSensors1424-82202022-03-01227251010.3390/s22072510A High-Precision Method for Segmentation and Recognition of Shopping Mall PlansMing Su0Wei Shi1Dangjun Zhao2Dongyang Cheng3Junchao Zhang4School of Aeronautics and Astronautics, Central South University, Changsha 410083, ChinaSchool of Aeronautics and Astronautics, Central South University, Changsha 410083, ChinaSchool of Aeronautics and Astronautics, Central South University, Changsha 410083, ChinaSchool of Aeronautics and Astronautics, Central South University, Changsha 410083, ChinaSchool of Aeronautics and Astronautics, Central South University, Changsha 410083, ChinaMost studies on map segmentation and recognition are focused on architectural floor plans, while there are very few analyses of shopping mall plans. The objective of the work is to accurately segment and recognize the shopping mall plan, obtaining location and semantic information for each room via segmentation and recognition. This work can be used in other applications such as indoor robot navigation, building area and location analysis, and three-dimensional reconstruction. First, we identify and match the catalog of a mall floor plan to obtain matching text, and then we use the two-stage region growth method we proposed to segment the preprocessed floor plan. The room number is then obtained by sending each segmented room section to an OCR (optical character recognition) system for identification. Finally, the system retrieves the matching text to match the room number in order to obtain the room name, and outputs the needed room location and semantic information. It is considered a successful detection when a room region can be successfully segmented and identified. The proposed method is evaluated on a dataset including 1340 rooms. Experimental results show that the accuracy of room segmentation is 92.54%, and the accuracy of room recognition is 90.56%. The total detection accuracy is 83.81%.https://www.mdpi.com/1424-8220/22/7/2510two-stage region growingOCRimage segmentationimage recognitionshopping mall plans |
spellingShingle | Ming Su Wei Shi Dangjun Zhao Dongyang Cheng Junchao Zhang A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans Sensors two-stage region growing OCR image segmentation image recognition shopping mall plans |
title | A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans |
title_full | A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans |
title_fullStr | A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans |
title_full_unstemmed | A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans |
title_short | A High-Precision Method for Segmentation and Recognition of Shopping Mall Plans |
title_sort | high precision method for segmentation and recognition of shopping mall plans |
topic | two-stage region growing OCR image segmentation image recognition shopping mall plans |
url | https://www.mdpi.com/1424-8220/22/7/2510 |
work_keys_str_mv | AT mingsu ahighprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT weishi ahighprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT dangjunzhao ahighprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT dongyangcheng ahighprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT junchaozhang ahighprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT mingsu highprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT weishi highprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT dangjunzhao highprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT dongyangcheng highprecisionmethodforsegmentationandrecognitionofshoppingmallplans AT junchaozhang highprecisionmethodforsegmentationandrecognitionofshoppingmallplans |