US-12626505-B2 - Computer implemented method for attribution of land use/land cover, a tool for building a transport network map and a navigation device

US12626505B2US 12626505 B2US12626505 B2US 12626505B2US-12626505-B2

Abstract

The present disclosure relates to a computer implemented method ( 100 ) for attribution of Land Use/Land Cover, LULC, said method comprising the steps of: providing (S 1 ) a plurality of images covering a transport network part, identifying (S 2 ) objects in at least a subset of said plurality of images, identifying (S 4 ) transport routes at least in said at least one satellite image of the plurality of images, and determining (S 5 ) characteristics of said transport network part based on the identified objects at said identified (S 4 ) transport routes.

Inventors

Thomas Beckman
Gustav TAPPER

Assignees

VANTOR SWEDEN AB

Dates

Publication Date: 20260512
Application Date: 20221216
Priority Date: 20221101

Claims (12)

1 . A method comprising: providing a plurality of co-registered images comprising at least one satellite image, the co-registered images covering a transport network part; identifying multiple moving objects in at least a subset of the plurality of images; determining, by a computing device, velocities of the multiple identified moving objects, from the plurality of co-registered images; identifying, by the computing device, a transport route routes at least in the at least one satellite image of the plurality of images, the transport route including the transport network part; and determining, by the computing device, one or more characteristics of the transport network part based on the velocities of the multiple identified moving objects along the identified transport route, wherein the one or more characteristics include: i) a speed limit for the transport network part, ii) whether there is a duty to give way at the transport network part, and/or iii) whether the transport network part includes a tunnel or a viaduct.
2 . The method of claim 1 , wherein determining the one or more characteristics of the transport network part further comprises determining a number of parallel lanes or tracks in the identified transport route based on locations of multiple moving objects on the transport route in a direction across the extension of the transport route.
3 . The method of claim 1 , wherein at least some of the images used for identification of multiple moving objects are obtained using at least one first sensor and at least one second sensor, wherein there is a time difference between capture using the at least one first sensor and the at least one second sensor.
4 . The method of claim 3 , wherein identifying the multiple moving objects is based on the time difference and displacements of the multiple moving objects in the image originating from capture using the at least one first sensor and capture using the at least one second sensor.
5 . The method of claim 4 , further comprising determining an orientation of one or more of the multiple moving objects based on the detected displacements; and wherein the characteristics of the transport network part is determined based on the determined orientation of the moving objects.
6 . The method of claim 5 , wherein determining the velocities of the multiple moving objects is based on the time difference and displacements of the multiple moving objects in the image originating from capture using the at least one first sensor and capture using the at least one second sensor.
7 . The method of claim 1 , wherein determining the one or more characteristics of the transport network part is based on the velocities of the multiple moving objects at different portions of the plurality of images.
8 . The method of claim 1 , wherein at least a part of the obtained images are geo-referenced.
9 . The method of claim 1 , wherein the multiple moving objects are vehicles, which include land-based vehicles or marine vehicles.
10 . The method of claim 1 , wherein the transport network part includes a level crossing; and wherein determining the one or more characteristics includes determining there is a duty to give way for the transport route at the level crossing.
11 . A system comprising: a memory storage; and a processing unit coupled to the memory storage, wherein the processing unit is operative to: provide a plurality of co-registered images comprising at least one satellite image, the co-registered images covering a transport network part, identify multiple moving objects in at least a subset of the plurality of images, determine velocities of the multiple identified moving objects, from the plurality of co-registered images; identify a transport route at least in the at least one satellite image of the plurality of images, the transport route including the transport network part; and determine characteristics of the transport network part based on the velocities of the multiple identified moving objects along the identified transport route, wherein the one or more characteristics include i) a speed limit for the transport network part, ii) whether there is a duty to give way at the transport network part, and/or iii) whether the transport network part includes a tunnel or a viaduct.
12 . A non-transitory computer-readable medium that stores a set of instructions which when executed perform a method executed by the set of instructions comprising: providing a plurality of co-registered images comprising at least one satellite image, the co-registered images covering a transport network part; identifying multiple moving objects in at least a subset of the plurality of images; determine velocities of the multiple identified moving objects, from the plurality of co-registered images; identifying a transport route at least in the at least one satellite image of the plurality of images, the transport route including the transport network part; and determining one or more characteristics of the transport network part based on the velocities of the multiple identified moving objects along the identified transport route, wherein the one or more characteristics include i) a speed limit for the transport network part, ii) whether there is a duty to give way at the transport network part, and/or iii) whether the transport network part includes a tunnel or a viaduct.

Description

This application claims benefit of European Application No. 22204915.7, filed Nov. 1, 2022, which application is incorporated herein by reference. To the extent appropriate, a claim of priority is made to the above disclosed application. TECHNICAL FIELD The present disclosure relates to a computer-implemented method for attribution of land use/land cover, a tool for building a transport network map and a navigation device. More specifically, the disclosure relates to a computer-implemented method for attribution of land use/land cover, a tool for building a transport network map and a navigation device as defined in the introductory parts of the independent claims. BACKGROUND ART A fast growing market both in civilian and military business is geographical information systems. Knowledge about geographical conditions forms a fundamental decision support to companies, authorities and in the military. The geographical information can comprise digital maps having superposed information layers such as infrastructure, terrain type and different types of objects. A concept used in this regard is Land Use/Land Cover, LULC, classification or attribution. LULC, classification refers to categorization or classification of human activities and natural elements on the landscape within a specific time frame based on established scientific and statistical methods of analysis of appropriate source materials. Another type of known classification is described in EP3035237 A1. This document relates to classification of terrain type using a plurality of overlapping aerial images. SUMMARY OF THE INVENTION An object of the invention is to obtain more information from LULC attribution. According to a first aspect there is provided a computer implemented method for attribution of Land Use/Land Cover, LULC, the method comprising the steps of: providing a plurality of co-registered images comprising at least one satellite image, said co-registered images covering a transport network part, identifying objects in at least a subset of the plurality of images, identifying transport routes, such as roads or railways or water based transport routes, at least in said at least one satellite image of the plurality of images, and determining characteristics of the transport network part based on the identified objects. Thus, the method allows for combination of the technology of attribution of Land Use/Land Cover, LULC, with transport network information to determine characteristics of the transport network part. In particular new satellite images may be obtained often, for example on a daily basis or more frequently or less frequently depending on the orbital characteristics of the satellite(s) or number of satellites. It is thereby possible to provide an up-to-date determination of the characteristics of the transport network part. Thus, at least the steps of identifying objects in at least a subset of the plurality of images and determining characteristics of the transport network part based on the identified objects can be updated frequently, while the step of identifying transport routes, such as roads or railways or water-based transport routes, at least in said at least one satellite image of the plurality of images can be made once or be updated less frequently. Characteristically, the identified objects are vehicles. The vehicles may be land-based vehicles such as cars and/or trains and/or marine vehicles such as ships. The marine vehicles are characteristically vehicles operating on the sea/lake/river surface. According to some embodiments, the determination of the characteristics of said transport network part being based on a count of the identified objects at the respective identified transport route. The count of, for example, vehicles present along a road is a good measure of the characteristics of the road. If the obtained images are from different times of the day, even further characteristics can be found as the variation of number of vehicles during a day and/or the count or variation for different days of the week and/or the count or variation for different seasons may be provided. According to some embodiments, the determination of characteristics of said transport network part comprises determining the characteristics for each identified transport route. According to some embodiments, the determination of the characteristics of the transport network part comprises determining a number of parallel lanes or tracks in each identified transport route based on the locations of the objects on the transport route in a direction across the extension of the transport route. As is clear from the above it may be possible to determine of the number of parallel lanes or tracks only based on the positions of identified objects in the transport route in a direction across the extension of the transport route. It is not necessary to use other information even if of course complementary information obtainable from the images can be used,