{"title":"从低成本GNSS设备密集轨迹中提取道路","authors":"Bruno de Moura Morceli, A. Poz","doi":"10.1080/17489725.2023.2216670","DOIUrl":null,"url":null,"abstract":"ABSTRACT This paper proposes a method for road centerline extraction from dense Global Navigation Satellite System (GNSS) trajectories, collected by using low-cost GNSS-devices, i.e. smartphones. The proposed method basically consists in generating a frequency image by tracking the GNSS trajectories and then by applying the Steger line detector to the generated image to extract the road centerlines. The main motivation of using the Steger algorithm is its capability to detect lines with sub-pixel accuracy. To evaluate the obtained results, reference road centerlines are manually extracted from a georeferenced orthomosaic. The experiments performed demonstrate the high potential of applying the Steger line detector to frequency images, generated by using dense GPS (Global Positioning System) trajectories. The completeness and correctness values for the accomplished experiments were 98% and 99%, respectively. Additionally, the RMSE (Root Mean Square Error) ranged from 0.63 m to 2.39 m, or approximately 1/16 to 1/4 of the expected accuracy (about 10 m) of a point determined by the Single-Point Positioning (SPP) method, which is the GNSS positioning method usually employed by smartphones. KEY POLICY HIGHLIGHTS In this paper we propose to extract roads by using dense GNSS trajectories based on frequency images. GNSS trajectories were collected from low-cost devices (smartphones). Unlike optical images, trajectory frequency images show only roads, thereby preventing problems such as extracting non-road objects. The experiments showed the high potential of using the Steger line detector for road extraction. Profiles drawn cross-sectionally to the roads actually exhibit behaviour similar to the normal distribution. The results obtained were between 16 times and four times better than the expected accuracy of the GNSS positioning method via the SPP positioning method.","PeriodicalId":44932,"journal":{"name":"Journal of Location Based Services","volume":"17 1","pages":"251 - 270"},"PeriodicalIF":1.2000,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Road extraction from low-cost GNSS-device dense trajectories\",\"authors\":\"Bruno de Moura Morceli, A. Poz\",\"doi\":\"10.1080/17489725.2023.2216670\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT This paper proposes a method for road centerline extraction from dense Global Navigation Satellite System (GNSS) trajectories, collected by using low-cost GNSS-devices, i.e. smartphones. The proposed method basically consists in generating a frequency image by tracking the GNSS trajectories and then by applying the Steger line detector to the generated image to extract the road centerlines. The main motivation of using the Steger algorithm is its capability to detect lines with sub-pixel accuracy. To evaluate the obtained results, reference road centerlines are manually extracted from a georeferenced orthomosaic. The experiments performed demonstrate the high potential of applying the Steger line detector to frequency images, generated by using dense GPS (Global Positioning System) trajectories. The completeness and correctness values for the accomplished experiments were 98% and 99%, respectively. Additionally, the RMSE (Root Mean Square Error) ranged from 0.63 m to 2.39 m, or approximately 1/16 to 1/4 of the expected accuracy (about 10 m) of a point determined by the Single-Point Positioning (SPP) method, which is the GNSS positioning method usually employed by smartphones. KEY POLICY HIGHLIGHTS In this paper we propose to extract roads by using dense GNSS trajectories based on frequency images. GNSS trajectories were collected from low-cost devices (smartphones). Unlike optical images, trajectory frequency images show only roads, thereby preventing problems such as extracting non-road objects. The experiments showed the high potential of using the Steger line detector for road extraction. Profiles drawn cross-sectionally to the roads actually exhibit behaviour similar to the normal distribution. The results obtained were between 16 times and four times better than the expected accuracy of the GNSS positioning method via the SPP positioning method.\",\"PeriodicalId\":44932,\"journal\":{\"name\":\"Journal of Location Based Services\",\"volume\":\"17 1\",\"pages\":\"251 - 270\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2023-05-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Location Based Services\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/17489725.2023.2216670\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"TELECOMMUNICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Location Based Services","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/17489725.2023.2216670","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
Road extraction from low-cost GNSS-device dense trajectories
ABSTRACT This paper proposes a method for road centerline extraction from dense Global Navigation Satellite System (GNSS) trajectories, collected by using low-cost GNSS-devices, i.e. smartphones. The proposed method basically consists in generating a frequency image by tracking the GNSS trajectories and then by applying the Steger line detector to the generated image to extract the road centerlines. The main motivation of using the Steger algorithm is its capability to detect lines with sub-pixel accuracy. To evaluate the obtained results, reference road centerlines are manually extracted from a georeferenced orthomosaic. The experiments performed demonstrate the high potential of applying the Steger line detector to frequency images, generated by using dense GPS (Global Positioning System) trajectories. The completeness and correctness values for the accomplished experiments were 98% and 99%, respectively. Additionally, the RMSE (Root Mean Square Error) ranged from 0.63 m to 2.39 m, or approximately 1/16 to 1/4 of the expected accuracy (about 10 m) of a point determined by the Single-Point Positioning (SPP) method, which is the GNSS positioning method usually employed by smartphones. KEY POLICY HIGHLIGHTS In this paper we propose to extract roads by using dense GNSS trajectories based on frequency images. GNSS trajectories were collected from low-cost devices (smartphones). Unlike optical images, trajectory frequency images show only roads, thereby preventing problems such as extracting non-road objects. The experiments showed the high potential of using the Steger line detector for road extraction. Profiles drawn cross-sectionally to the roads actually exhibit behaviour similar to the normal distribution. The results obtained were between 16 times and four times better than the expected accuracy of the GNSS positioning method via the SPP positioning method.
期刊介绍:
The aim of this interdisciplinary and international journal is to provide a forum for the exchange of original ideas, techniques, designs and experiences in the rapidly growing field of location based services on networked mobile devices. It is intended to interest those who design, implement and deliver location based services in a wide range of contexts. Published research will span the field from location based computing and next-generation interfaces through telecom location architectures to business models and the social implications of this technology. The diversity of content echoes the extended nature of the chain of players required to make location based services a reality.