Last week during the geo-spatial week that organized by the International Society for Photogrammetry and Remote Sensing (ISPRS). There exist an International Symposium of Spatial Data Quality (ISSDQ). In that event, a Grass&Green tool is presented during the talk about “TOWARDS RULE-GUIDED CLASSIFICATION FOR VOLUNTEERED GEOGRAPHIC INFORMATION”.

The tool enhance the classification of grassy entity in Openstreetmap. It is a pilot study on the data set of Germany. Please, participate in the study to help into developing a consistent data classifications.

Best,

Visit Grass&Green to improve the classification of grass-related entities. As a start, it now only German data set, however it is a research to generalize the concepts and ensure the feasibility of the methodologies.

The tool and the research would be presented this week in International Symposium of Spatial Data Quality.

Enjoy the tool and improve the data classification

Best

Visit Grass&Green to improve the classification of grass-related entities. As a start, it now only German Dataset, however it is a research to generalize the concepts and ensure the feasibility of the methodologies.

It is very simple QA tool with easy Interface

Login by your OSM account

check the provided recommendation, change them if required and express all the plausibility

Guide and help is provided to introduce all the grass-related classes

That’s all, enjoy it and improve the data quality

Thanks,

Hallo Everyone,

Green is everywhere around us. The most noticeable color on the map is the Green: farms, parks, gardens, forests, meadows, etc. Furthermore, the classification of such of these entities plays a major role in many applications: POI search, ecosystems, climate changes, environmental monitoring, etc. At the same time, these entities on OSM are poorly attract investigations (Mostly have 1-5 versions).

Thus, we target these entities classifications by designing QA tool called Grass&Green. Feature-targeted tools is the powerful solution to manage the data quality. E.g, how many tools investigate the street networks and how it is now looks like (perfect). So, contribute a few of your time in QA tools is required and as much important as contribute new data.

Help us to:

• understand how people perceive and use grassy entities
• enrich VGI data and improve data quality
• help the ecosystem for better environmental analysis

Best

Dear all, After 16 days of publishing Grass&Green, a specific tool for QA of data classification, we got the following contributions.

Thanks for all contributors, however, we still have 1000’s of entities needed to be checked. I could describe simply how does it work?

We have the following assumptions:

• Similar entities should be classified consistently, at least within the same country. For example, In Germany, what people know about “park”, as a place for recreation and amusement, doing sport, grilling, pinking, ..etc. Thus, the one can not called a small piece of grass entity in front or backyard of his home as “park”. It is inconsistency.

• OSM in lots of cities (e.g., urban cities) has a good and acceptable quality.

Hence, we extract the characteristics that describe specific grass-related classes like: forest, meadow, park, garden, and grass. Afterwards, we develop a recommendation system (Grass&Green) for that classes.

The aim of the tool is to improve/enrich the data classification quality of these features. We just have a start and test on Germany DataSet, however, the entire world would be provided in the next phases. So far, contributors confirm our recommendations with 90% full/partial agreement. That’s sounds good.

Please, don’t hesitate to contact us for further details or feedback. Follow our news also on Twitter and Facebook

Best, Ahmed Loai Ali

Dear all, After 16 days of publishing Grass&Green, a specific tool for QA of data classification, we got the following contributions.

Thanks for all contributors, however, we still have 1000’s of entities needed to be checked. I could describe simply how does it work?

We have the following assumptions:

• Similar entities should be classified consistently, at least within the same country. For example, In Germany, what people know about “park”, as a place for recreation and amusement, doing sport, grilling, pinking, ..etc. Thus, the one can not called a small piece of grass entity in front or backyard of his home as “park”. It is inconsistency.

• OSM in lots of cities (e.g., urban cities) has a good and acceptable quality.

Hence, we extract the characteristics that describe specific grass-related classes like: forest, meadow, park, garden, and grass. Afterwards, we develop a recommendation system (Grass&Green) for that classes.

The aim of the tool is to improve/enrich the data classification quality of these features. We just have a start and test on Germany DataSet, however, the entire world would be provided in the next phases. So far, contributors confirm our recommendations with 90% full/partial agreement. That’s sounds good.

Please, don’t hesitate to contact us for further details or feedback. Follow our news also on Twitter and Facebook

Best, Ahmed Loai Ali

I just would like to thank the contributors and the power of crowds. more than 800 entities checked about 100 users, more than 150 visits to the system. 90% agreement with recommendations and still more entities need your opinions

This entity was classified as ‘park’ by Grass&Green it is confirmed classified as ‘park’

This entity was classified as ‘park’ by Grass&Green it is classified as ‘garden’

Visit http://opensciencemap.org/quality/ and contribute to improve the classification of grass-related features.

Best, Ahmed loai ali

Dear all,

After 12 days of Grass&Green in place. We have around 100 users and contributed in about 500 entities with 90% agreement with our recommendations. However, there is still exist 1000’s of entities to be checked. So, we ask for daily contributions to improve the classification of grass-related features. It is just the start, we would feed the system with more categories of entities later on e.g.: water-related features and other natural features. Here is the interface of the system. Just visit http://opensciencemap.org/quality/ and login by your osm account and contribute to improve the classification quality.

Thanks for all former contributors and useful comments. I appreciate your feedback

Best, Ahmed Loai Ali

After 5 days Grass&Green contributors agree or partial agree to our recommendation by 91.5 %. Dear OSM users hurry and participate in the contribution to the tool. It is a research project. The project has many objectives: 1) develop an appropriate classification of entities to support more use;2) guide the participants towards better understanding of the class;3) enrich the OSM data; 4) correct the miss classified data.

Do you could tag the following image as a park? Absolutely, This tag is inappropriate and the appropriate tag should be grass.

Now. Help us and improve grass-related entities tags. These entities are used in various applications.The inappropriate tags make them of limited use.

Dear OSM users,

Grass&Green is a new tool to improve the quality of data from classification perspective.The project aims to: 1) develop an appropriate classification of entities to support more use;2) guide the participants towards better understanding of the class;3) enrich the OSM data; 4) correct the miss classified data.

The given entities in the previous figure. Is is a park? could it be classified as a garden? what is the best classification of that entity? While in the next figure is the entity is a park or forest? could it classified as meadow?

The tool is part of a research at Bremen University by Ahmed Loai Ali. The research argues that the appropriate classification of entities comes from the inherent characteristics of the entities and its geographical context. For example, when an area covered by grass and contains amusements and leisure properties then it is recommended to be classified as park, garden, recreation,..etc. Whereas when an identical entity contains nothing and full will woody plants, then it would be better to classify it as forest. While in other situation when a grass entity located between roundabouts and besides highways and aims to decoration purpose it could be classified as grass. When the entity used for agriculture then its field, farm, ..etc. For further details you could read our research publications.

The tool that we develop focus currently on German data only, and we still analysis the classification within the city boundaries. So, It represents a way to improve our research and our research plan still have more items.

The tool is online under http://opensciencemap.org/quality/. We need to understand how participants see the classification of grass-related entities. We need to check if participants could really able to classify these type of entities correctly from only satellite images and local knowledge. To which extent is our generated recommendations matches with participants’ opinion.

Hence, It is a kindly call for participants. Let’s improve our data sets, Let’s understand various conceptual perspectives. I would appreciate your participation. Your comments and feedback and more than welcome.

Dear OSM users,

Grass&Green is a research project aims to improve the classification of grass-related entities. Actually, the main aim are to 1) develop an appropriate classification of entities to support more use;2) guide the participants towards better understanding of the class;3) enrich the OSM data; 4) correct the miss classified data.

The research is done at Bremen University by Ahmed Loai Ali. The research argues that the appropriate classification of entities comes from the inherent characteristics of the entities and its geographical context. For example, when an area covered by grass and contains amusements and leisure properties then it is recommended to be classified as park, garden, recreation,..etc. Whereas when an identical entity contains nothing and full will woody plants, then it would be better to classify it as forest. While in other situation when a grass entity located between roundabouts and besides highways and aims to decoration purpose it could be classified as grass. When the entity used for agriculture then its field, farm, ..etc. For further details you could read our research publications.

The tool that we develop focus currently on German data only, and we still analysis the classification within the city boundaries. So, It represents a way to improve our research and our research plan still have more items.

The tool is online under http://opensciencemap.org/quality/. We need to understand how participants see the classification of grass-related entities. We need to check if participants could really able to classify these type of entities correctly from only satellite images and local knowledge. To which extent is our generated recommendations matches with participants’ opinion.

Hence, It is a kindly call for participants. Let’s improve our data sets, Let’s understand various conceptual perspectives. I would appreciate your participation. Your comments and feedback and more than welcome.

Best,

Ahmed Loai Ali