Merge pull request #458 from ualsg/update

Zicheng's nighttime SVI work

content/data-code/index.md

@@ -15,24 +15,48 @@ summary = "Open stuff"
   columns = "1"
 +++ 
 
-We publish most of our code and data openly.
+We believe in open science, so we publish most of our code and data openly.
 We do that mostly through [our Github account](https://github.com/ualsg).
 
-Please see below for a list of resources and projects, especially lab-grown datasets, which we are happy to share. 
-On this page, we also include similar [outputs led by collaborators](#with-our-friendly-collaborators), in which we were involved.
+Please see below for a list of resources and projects, especially lab-grown datasets, which we are happy to make public. 
+On this page, we also include open [outputs led by collaborators](#with-our-friendly-collaborators), in which we were involved.
 
-On a related note, you may be interested in [our comprehensive survey on open-source software](https://doi.org/10.1016/j.compenvurbsys.2022.101825), published as a review paper in _Computers, Environment and Urban Systems_.
+On a related note, you may be interested in [our comprehensive survey on open-source software](https://doi.org/10.1016/j.compenvurbsys.2022.101825), led by our {{% mention "winston" %}}, published as a review paper in _Computers, Environment and Urban Systems_.
 
-In general, all resources are released under a liberal licence, enabling you unrestricted use as long as you attribute them.
+In general, all resources are released under a liberal licence, enabling unrestricted use as long as you properly attribute them.
 If you use the code and/or the data for presentations and publications, we kindly ask you to cite the related paper(s) and credit our work. 
 We have provided guidelines to do so in each resource.
 
-The usual caveat: while a great deal of effort has been put into each project, they are not free of errors, and we cannot be held responsible for the use of code and/or data and any issues that may arise.
+The usual disclaimer: while a great deal of effort and care has been put into each project, they are not free of errors, and we cannot be held responsible for the use of code and/or data and any issues that may arise.
+All code and data are provided _as is_.
 
 Feel free to contact us for more information, report bugs and errors, or simply to inform us what are you using the data for.
 We would be pleased to learn how others are using our work.
 If you are interested in collaborating with us, please get in touch with the lead developer of each resource listed below.
 
+## Nighttime Street View Imagery
+
+![](nighttime-svi.jpg)
+
+| | |
+| ------------------| ------------------------------ |
+| Short description: | A large set of images collected during nighttime to support our explorations on this latent kind of urban visual data. |
+| Lead developer: | {{% mention "zicheng" %}} |
+| Further reading: | Please read the [paper](https://doi.org/10.1016/j.scs.2024.105862) published in Sustainable Cities and Society |
+| Download: | [<i class="fab fa-github"></i> Github repo](https://github.com/fzc961020/Nighttime-SVI) (also uploaded on Mapillary)|
+| Main data source(s): | Own data collection |
+| Coverage: | Singapore | 
+| Citation: | {{< spoiler text="Click to view the BibTeX entry" >}}
+@article{2024_scs_nightSVI,
+ author = {Fan, Zicheng and Biljecki, Filip},
+ doi = {10.1016/j.scs.2024.105862},
+ journal = {Sustainable Cities and Society},
+ pages = {105862},
+ title = {Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape},
+ volume = {116},
+ year = {2024}
+}
+{{< /spoiler >}}|
 
 ## TreeShadeMapper
 

content/opportunities/application-guide.md

@@ -90,8 +90,10 @@ Some of the expectations from PhD researchers during and at the end of their stu
 + Collaborate and contribute to the scientific community in various ways (i.e. other forms of output such as open data, open-source software, community engagements...).
 + Attain a valuable set of skills, largely domain-agnostic, both hard (e.g. coding, statistics) and soft (e.g. written communication, presenting, project management) that can be applied to a variety of scientific challenges and in various environments.
 
+On a related note, have a look at [this nice illustrated guide to a PhD](https://matt.might.net/articles/phd-school-in-pictures/).
+
 To succeed, a PhD student ideally should:
-+ have ownership of his/her work, have intellectual and scientific curiosity, and be excited and passionate about the topic and field;
++ establish ownership of his/her work, have intellectual and scientific curiosity, be creative, and be excited and passionate about the topic and field;
 + have initiative and be proactive about a variety of aspects related to the research (e.g. take the lead in identifying gaps, think of new ideas, and follow relevant conferences and journals);
 + continuously develop transferrable skills, be on top of the developments in the field and broader domains, and seek means to contribute and advance knowledge;
 + regularly seek opportunities to promote and apply their research;
@@ -112,10 +114,11 @@ But here are some further tips and requirements on our end.
 
 The most important tip is to tailor your application and make it specific to our environment.
 PhD applications are examined carefully by the department and college.
-Your application will be given adequate attention, however, generic applications and those without a clear motivation and understanding of the scope of our work, and those that do not demonstrate research affinity, are typically rejected.
+Your application will be given adequate attention, however, generic applications with boilerplate text and those without a clear motivation and understanding of the scope of our work, and those that do not demonstrate research affinity, are typically rejected.
+Your PhD application reflects your ability and skill to find and digest information, which is an instrumental skill for a researcher to possess. 
 
 Therefore, in your application, you need to be clear with your motivation to spend several years in a PhD programme: why do you want to do a PhD, why are you interested in research and in an academic environment, what makes you a strong candidate, what are your career goals, what are your research interests, what are your relevant skills and accomplishments so far, and why do you want to come specifically to NUS and our department and group.
-Each of these points should be accompanied with some evidence or motivation.
+Each of these points should be substantiated with some evidence or motivation.
 
 Prospective candidates who did a bit of research on what we do and those that are able to demonstrate their aptitude for research and motivate their wish to join us in particular have a much better chance getting admitted into the doctoral programme.
 This is most evident from a tailored and research-focused application pertaining to our Lab, university and Singapore.
@@ -229,6 +232,11 @@ PhD programmes at NUS follow the nomenclature of the hosting departments, thus,
 In practice, as far as we know, this will not make or break your chances later in your career. Your work, publications, and attained skills matter the most.
 {{< /spoiler >}}
 
+{{< spoiler text="I am preparing my application but I don't see you listed in the NUS application system. How to apply?" >}}
+This is related to the question above.
+Please select the PhD in Architecture programme in the application portal. 
+{{< /spoiler >}}
+
 
 {{< spoiler text="Can I do a part-time PhD?" >}}
 You can (NUS allows it), but we think you shouldn't.
@@ -323,6 +331,12 @@ However, note that doing a PhD without a scholarship can be difficult and stress
 No, NUS does not provide waivers, sorry, we can't do much about it.
 {{< /spoiler >}}
 
+{{< spoiler text="I didn't receive a reply to my email. Should I send it again?" >}}
+While we appreciate interest, we do not entertain generic emails and applications.
+Research abilities and commitment are key characteristics of a successful PhD researcher.
+If you have not invested time in researching a bit and in preparing your email, it is not good to have an expectation that someone will invest time to reply to you.
+{{< /spoiler >}}
+
 
 {{< spoiler text="Do I need a masters degree to apply for a PhD?" >}}
 Yes, a masters degree is pretty much a hard requirement.

content/post/2024-10-scs-nighttime-svi/index.md

@@ -0,0 +1,84 @@
+---
+# Documentation: https://sourcethemes.com/academic/docs/managing-content/
+
+title: "New paper: Nighttime Street View Imagery"
+subtitle: "Sustainable Cities and Society publishes our work on a new perspective for sensing urban lighting landscape."
+summary: "Sustainable Cities and Society publishes our work on a new perspective for sensing urban lighting landscape."
+authors: [admin]
+tags: [paper, nighttime, ntl, computer vision, street view]
+categories: []
+date: 2024-10-19T09:43:22+08:00
+lastmod: 2024-10-19T09:43:22+08:00
+featured: false
+draft: false
+show_related: true
+pager: true
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ""
+  focal_point: ""
+  preview_only: false
+
+# Projects (optional).
+#   Associate this post with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+
+---
+
+We are glad to share our new paper:
+
+> Fan Z, Biljecki F (2024): Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape. Sustainable Cities and Society, 116: 105862. [<i class="ai ai-doi-square ai"></i> 10.1016/j.scs.2024.105862](https://doi.org/10.1016/j.scs.2024.105862) [<i class="far fa-file-pdf"></i> PDF](/publication/2024-scs-night-svi/2024-scs-night-svi.pdf)</i> <i class="ai ai-open-access-square ai"></i>
+
+This research was led by {{% mention "zicheng" %}}.
+Congratulations on his first PhD journal publication! :raised_hands: :clap:
+
+The dataset has been released openly at [GitHub](https://github.com/fzc961020/Nighttime-SVI).
+
+![](1.png)
+
+![](2.png)
+
+### Highlights
+
++ Street View Imagery (SVI) is taken almost exclusively during daytime, ignoring the urban nightscape.
++ Elucidation of data collection and usability of such imagery during night.
++ Exploring the profound correspondence between daytime SVI and nighttime SVI.
++ Identifying nighttime SVI as viable complement for Nighttime Lights satellite imagery.
++ Position that nighttime SVI is a latent but valuable urban dataset.
+
+![](3.png)
+
+![](4.png)
+
+
+### Abstract
+
+> Urban lighting reflects nocturnal activities and it is traditionally observed using Nighttime Lights (NTL) satellite imagery. Few studies systematically measure the nightscape from a human perspective. This study brings a new paradigm — urban lighting sensing via Nighttime Street View Imagery (SVI). The paradigm draws on the accomplishments of (daytime) SVI and gives attention to its ignored nighttime counterpart. We put forward this idea by manually collecting 2,831 nighttime SVIs across various urban functional areas in Singapore. We investigated their values by developing a use case for clustering nighttime lighting patterns. To mitigate the scarcity of nighttime SVI, deep learning regression models were trained to predict nighttime brightness based on corresponding daytime SVIs obtained from widely available sources. The results were compared with brightness data derived from satellite imagery, to affirm the novelty and uniqueness of nighttime SVI. As a result, there are 7 lighting patterns within the collected nighttime SVI, distinct in lighted spot features and total brightness. The identified patterns effectively characterize different urban function scenarios. The best trained brightness prediction model performs well in revealing the city-scale lighting landscape. The SVI-predicted brightness shows a distribution similar to the brightness from satellite imagery and complements it in urban areas with complex vertical lighting structures. This study demonstrates the potential of nighttime SVI as a valuable data source for mapping urban lighting and activities, offering advantages over satellite data. The proposed paradigm contributes significantly to cross-modal information mining in urban studies and has potential applications in scenarios such as light pollution mitigation and crime prevention.
+
+![](5.png)
+
+![](6.png)
+
+### Paper 
+
+For more information, please see the [paper](/publication/2024-scs-night-svi/).
+
+[![](page-one.png)](/publication/2024-scs-night-svi/)
+
+BibTeX citation:
+```bibtex
+@article{2024_scs_nightSVI,
+ author = {Fan, Zicheng and Biljecki, Filip},
+ doi = {10.1016/j.scs.2024.105862},
+ journal = {Sustainable Cities and Society},
+ pages = {105862},
+ title = {Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape},
+ volume = {116},
+ year = {2024}
+}
+```

content/publication/2024-scs-night-svi/2024-scs-night-svi.bib

@@ -0,0 +1,9 @@
+@article{2024_scs_nightSVI,
+ author = {Fan, Zicheng and Biljecki, Filip},
+ doi = {10.1016/j.scs.2024.105862},
+ journal = {Sustainable Cities and Society},
+ pages = {105862},
+ title = {Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape},
+ volume = {116},
+ year = {2024}
+}

content/publication/2024-scs-night-svi/cite.bib

@@ -0,0 +1,9 @@
+@article{2024_scs_nightSVI,
+ author = {Fan, Zicheng and Biljecki, Filip},
+ doi = {10.1016/j.scs.2024.105862},
+ journal = {Sustainable Cities and Society},
+ pages = {105862},
+ title = {Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape},
+ volume = {116},
+ year = {2024}
+}

content/publication/2024-scs-night-svi/index.md

@@ -0,0 +1,72 @@
+---
+title: 'Nighttime Street View Imagery: A new perspective for sensing urban lighting
+  landscape'
+
+# Authors
+# A YAML list of author names
+# If you created a profile for a user (e.g. the default `admin` user at `content/authors/admin/`), 
+# write the username (folder name) here, and it will be replaced with their full name and linked to their profile.
+authors:
+- zicheng
+- filip
+
+# Author notes (such as 'Equal Contribution')
+# A YAML list of notes for each author in the above `authors` list
+author_notes: []
+
+date: '2024-10-18'
+
+# Date to publish webpage (NOT necessarily Bibtex publication's date).
+publishDate: '2024-10-19T01:10:14.923086Z'
+
+# Publication type.
+# A single CSL publication type but formatted as a YAML list (for Hugo requirements).
+publication_types:
+- article-journal
+
+# Publication name and optional abbreviated publication name.
+publication: '*Sustainable Cities and Society*'
+publication_short: ''
+
+doi: 10.1016/j.scs.2024.105862
+
+abstract: 'Urban lighting reflects nocturnal activities and it is traditionally observed using Nighttime Lights (NTL) satellite imagery. Few studies systematically measure the nightscape from a human perspective. This study brings a new paradigm — urban lighting sensing via Nighttime Street View Imagery (SVI). The paradigm draws on the accomplishments of (daytime) SVI and gives attention to its ignored nighttime counterpart. We put forward this idea by manually collecting 2,831 nighttime SVIs across various urban functional areas in Singapore. We investigated their values by developing a use case for clustering nighttime lighting patterns. To mitigate the scarcity of nighttime SVI, deep learning regression models were trained to predict nighttime brightness based on corresponding daytime SVIs obtained from widely available sources. The results were compared with brightness data derived from satellite imagery, to affirm the novelty and uniqueness of nighttime SVI. As a result, there are 7 lighting patterns within the collected nighttime SVI, distinct in lighted spot features and total brightness. The identified patterns effectively characterize different urban function scenarios. The best trained brightness prediction model performs well in revealing the city-scale lighting landscape. The SVI-predicted brightness shows a distribution similar to the brightness from satellite imagery and complements it in urban areas with complex vertical lighting structures. This study demonstrates the potential of nighttime SVI as a valuable data source for mapping urban lighting and activities, offering advantages over satellite data. The proposed paradigm contributes significantly to cross-modal information mining in urban studies and has potential applications in scenarios such as light pollution mitigation and crime prevention.'
+
+# Summary. An optional shortened abstract.
+summary: ''
+
+tags: []
+
+# Display this page in a list of Featured pages?
+featured: false
+
+# Links
+url_pdf: ''
+url_code: ''
+url_dataset: ''
+url_poster: ''
+url_project: ''
+url_slides: ''
+url_source: ''
+url_video: ''
+
+# Custom links (uncomment lines below)
+# links:
+# - name: Custom Link
+#   url: http://example.org
+
+# Publication image
+# Add an image named `featured.jpg/png` to your page's folder then add a caption below.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects: ['internal-project']` links to `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects: []
+---
+

content/publication/_index.md

@@ -11,7 +11,8 @@ banner:
 ---
 
 These are our publications since the Lab was established in 2019 (earlier publications of the PI of the Lab Dr {{% mention "filip" %}} are available [here](https://filipbiljecki.com/#publications)).
-We strive to publish open access papers whenever possible.
+We strive to publish papers open access whenever possible.
 The PDFs available here are either published as [gold or green open access](https://en.wikipedia.org/wiki/Open_access#Colour_naming_system) (usually postprints).
 For the authoritative publication please visit the publisher's website linked through the DOI of the article.
-For code and data check our [GitHub page](https://github.com/ualsg) or follow the links noted in the publications.
+For code and data check our [data+code page](/data-code/) or follow the links noted in the publications.
+We have also a [GitHub page](https://github.com/ualsg).

publications.bib

@@ -1,13 +1,25 @@
 %% This BibTeX bibliography file was created using BibDesk.
 %% https://bibdesk.sourceforge.io/
 
-%% Created for Filip at 2024-09-15 16:03:13 +0800 
+%% Created for Filip at 2024-10-19 09:09:46 +0800 
 
 
 %% Saved with string encoding Unicode (UTF-8) 
 
 
 
+@article{2024_scs_nightSVI,
+	author = {Fan, Zicheng and Biljecki, Filip},
+	date-added = {2024-10-19 09:09:45 +0800},
+	date-modified = {2024-10-19 09:09:45 +0800},
+	doi = {10.1016/j.scs.2024.105862},
+	journal = {Sustainable Cities and Society},
+	pages = {105862},
+	title = {{Nighttime Street View Imagery}: A new perspective for sensing urban lighting landscape},
+	volume = {116},
+	year = {2024},
+	bdsk-url-1 = {https://doi.org/10.1016/j.scs.2024.105862}}
+
 @article{2024_bae_svf,
 	author = {Fujiwara, Kunihiko and Ito, Koichi and Ignatius, Marcel and Biljecki, Filip},
 	date-added = {2024-09-15 16:03:12 +0800},