├── expected_outputs
    ├── count.png
    ├── blurriness.png
    ├── num-months.png
    ├── num-years.png
    ├── first-avail.png
    ├── most-recent.png
    ├── time-elapsed.png
    ├── spatial-coverage.png
    └── spatial-continuity.png
└── README.md


/expected_outputs/count.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/count.png


--------------------------------------------------------------------------------
/expected_outputs/blurriness.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/blurriness.png


--------------------------------------------------------------------------------
/expected_outputs/num-months.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/num-months.png


--------------------------------------------------------------------------------
/expected_outputs/num-years.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/num-years.png


--------------------------------------------------------------------------------
/expected_outputs/first-avail.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/first-avail.png


--------------------------------------------------------------------------------
/expected_outputs/most-recent.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/most-recent.png


--------------------------------------------------------------------------------
/expected_outputs/time-elapsed.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/time-elapsed.png


--------------------------------------------------------------------------------
/expected_outputs/spatial-coverage.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/spatial-coverage.png


--------------------------------------------------------------------------------
/expected_outputs/spatial-continuity.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ualsg/SVI-Quality-Checker/HEAD/expected_outputs/spatial-continuity.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # Street View Imagery Quality Checker
  2 | 
  3 | ## Introduction
  4 | It is crucial to understand the quality of a street view imagery (SVI) dataset to assess its ’fitness for purpose’. In this repository, we present: (1) a Jupyter notebook to quickly assess the quality of a SVI dataset by **9 quality elements**, each at its relevant **hierarchical levels** - image, street, or grid; (2) a sample dataset for running the notebook.
  5 | 
  6 | ### Quality elements
  7 | A total of 9 quality elements are evaluated in the notebook with their spatial variations visualised:
  8 | * Spatial coverage
  9 | * Spatial continuity
 10 | * Count
 11 | * Age of the most recent coverage
 12 | * Age of the first available coverage
 13 | * Number of years covered
 14 | * Number of months covered
 15 | * Time elapsed between coverage
 16 | * Image blurriness
 17 | 
 18 | ### Sample dataset
 19 | For demonstration, we provide a set of Mapillary SVI data from a 2 km x 2 km area in Kowloon, Hong Kong for running the notebook. This includes:
 20 | * A metadata file, obtained from the [Mapillary API](https://www.mapillary.com/developer/api-documentation)
 21 | * A zip file of sample images, obtained from [Mapillary](https://www.mapillary.com/)
 22 | 
 23 | Apart from the SVI data, we also provide a raster file that enables the grid-based analysis, obtained from [WorldPop](https://www.worldpop.org/).
 24 | 
 25 | All data in the sample dataset was obtained under the [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
 26 | 
 27 | ## Expected outputs
 28 | 
 29 | The expected output for each quality element, if the sample dataset is used:
 30 | 
 31 | 1. Spatial coverage
 32 | <div align=left>
 33 | <img src="expected_outputs/spatial-coverage.png" width="700">
 34 | </div>
 35 | 
 36 | 2. Spatial continuity
 37 | <div align=left>
 38 | <img src="expected_outputs/spatial-continuity.png" width="350">
 39 | </div>
 40 | 
 41 | 3. Count
 42 | <div align=left>
 43 | <img src="expected_outputs/count.png" width="700">
 44 | </div>
 45 | 
 46 | 4. Age of the most recent coverage
 47 | <div align=left>
 48 | <img src="expected_outputs/most-recent.png" width="700">
 49 | </div>
 50 | 
 51 | 5. Age of the first available coverage
 52 | <div align=left>
 53 | <img src="expected_outputs/first-avail.png" width="700">
 54 | </div>
 55 | 
 56 | 6. Number of years covered
 57 | <div align=left>
 58 | <img src="expected_outputs/num-years.png" width="700">
 59 | </div>
 60 | 
 61 | 7. Number of months covered
 62 | <div align=left>
 63 | <img src="expected_outputs/num-months.png" width="700">
 64 | </div>
 65 | 
 66 | 8. Time elapsed between coverage
 67 | <div align=left>
 68 | <img src="expected_outputs/time-elapsed.png" width="700">
 69 | </div>
 70 | 
 71 | 9. Image blurriness
 72 | <div align=left>
 73 | <img src="expected_outputs/blurriness.png" width="350px">
 74 | </div>
 75 | 
 76 | 
 77 | ## Access
 78 | The sample dataset can be downloaded from [Google drive](https://drive.google.com/file/d/1UtAKOO5cgtqEQ7e4T4RiFkETmnLKO4El/view?usp=sharing).
 79 | 
 80 | ## Reference, citation, and documentation
 81 | 
 82 | A [paper](https://doi.org/10.1016/j.jag.2022.103094) about the work was published in the _International Journal of Applied Earth Observation and Geoinformation_ and it is available open access.
 83 | 
 84 | If you use this work in a scientific context, please cite this article.
 85 | 
 86 | Hou Y, Biljecki F (2022): A comprehensive framework for evaluating the quality of street view imagery. International Journal of Applied Earth Observation and Geoinformation, 115: 103094. doi:10.1016/j.jag.2022.103094
 87 | 
 88 | ```
 89 | @article{2022_jag_svi_quality, 
 90 |   year = {2022}, 
 91 |   title = {{A comprehensive framework for evaluating the quality of street view imagery}}, 
 92 |   author = {Hou, Yujun and Biljecki, Filip}, 
 93 |   journal = {International Journal of Applied Earth Observation and Geoinformation}, 
 94 |   doi = {10.1016/j.jag.2022.103094}, 
 95 |   pages = {103094}, 
 96 |   volume = {115}
 97 | }
 98 | ```
 99 | 
100 | ## License
101 | This dataset is released under the [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
102 | 
103 | ## Contact
104 | Feel free to contact [Yujun Hou](https://ual.sg/authors/yujun/) or [Filip Biljecki](https://ual.sg/authors/filip/) should you have any questions.
105 | For more information, please visit [Urban Analytics Lab](https://ual.sg/), National University of Singapore.
106 | 
107 | ## Acknowledgements
108 | We appreciate the valuable contributions of the VGI community.
109 | 
110 | We thank our colleagues at the NUS Urban Analytics Lab for the discussions.
111 | 
112 | This research is part of the project Large-scale 3D Geospatial Data for Urban Analytics, which is supported by the National University of Singapore under the Start Up Grant R-295-000-171-133.
113 | 


--------------------------------------------------------------------------------