computer-vision-built-environment.html

<!doctype html>
<html lang="en">
  <head>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width, initial-scale=1">
    <meta
      name="description"
      content="Computer Vision for the Built Environment (CEE 147C/247C) — course information, schedule, and resources from the Gradient Spaces Lab at Stanford."
    >
    <title>Computer Vision for the Built Environment | Gradient Spaces Lab</title>
    <meta property="og:title" content="Computer Vision for the Built Environment | Gradient Spaces Lab">
    <meta property="og:description" content="Course information, schedule, and resources for CEE 147C/247C, taught by Iro Armeni.">
    <meta property="og:type" content="website">
    <meta property="og:url" content="https://gradientspaces.github.io/computer-vision-built-environment.html">
    <link rel="canonical" href="https://gradientspaces.github.io/computer-vision-built-environment.html">
    <link rel="icon" type="image/png" href="assets/images/GradientSpacesLogo.png">
    <link rel="apple-touch-icon" href="assets/images/GradientSpacesLogo.png">
    <link rel="stylesheet" href="styles.css?v=20260925">
  </head>
  <body>
    <header class="site-header">
      <a class="brand" href="index.html">Gradient Spaces</a>
      <button class="nav-toggle" type="button" aria-expanded="false" aria-controls="site-nav" title="Open navigation">
        <span class="sr-only">Menu</span>
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
      </button>
      <nav class="site-nav" id="site-nav" aria-label="Main navigation">
        <a href="index.html">Home</a>
        <a href="people.html">People</a>
        <a href="research.html">Research</a>
        <a class="active" href="teaching.html">Teaching</a>
        <a href="events.html">Events</a>
        <a href="gradient-space.html">Gradient Space</a>
        
        <a href="index.html#news">News</a>
        <a href="index.html#connect">Connect</a>
      </nav>
    </header>

    <main>
      <section class="page-hero teaching-hero">
        <div>
          <a class="text-link back-link" href="teaching.html">Back to Teaching</a>
          <p class="eyebrow">Teaching</p>
          <h1>Computer Vision for the Built Environment</h1>
          <p class="lead">
            An introduction to visual machine perception — computer vision and machine learning — for the
            built environment, exploring fundamentals and current research trends in tight reference to
            design, construction, and operation and management.
          </p>
        </div>
      </section>

      <section class="section" aria-labelledby="info-title">
        <div class="section-heading">
          <p class="section-kicker">Overview</p>
          <h2 id="info-title">Course information</h2>
        </div>
        <dl class="info-grid">
          <div class="info-row">
            <dt>Course ID</dt>
            <dd>CEE 147C/247C (Winter 2026)</dd>
          </div>
          <div class="info-row">
            <dt>Instructor</dt>
            <dd>Iro Armeni</dd>
          </div>
          <div class="info-row">
            <dt>Teaching Assistants</dt>
            <dd>Sayan Deb Sarkar, Emily Steiner</dd>
          </div>
          <div class="info-row">
            <dt>Lectures</dt>
            <dd>Wednesdays 1:30–4:20 PM, Y2E2 292A</dd>
          </div>
          <div class="info-row">
            <dt>Credits</dt>
            <dd>3 or 4</dd>
          </div>
          <div class="info-row">
            <dt>Office Hours</dt>
            <dd>Iro Armeni — Tuesdays 1–2 PM, Y2E2 233</dd>
            <dd>Sayan Deb Sarkar / Emily Steiner — Fridays 1–2 PM, Y2E2 278B</dd>
          </div>
          <div class="info-row">
            <dt>Online Material</dt>
            <dd><a class="strong-link" href="https://canvas.stanford.edu/courses/219921">Canvas</a></dd>
          </div>
        </dl>
      </section>

      <section class="section" aria-labelledby="description-title">
        <div class="section-heading">
          <p class="section-kicker">Description</p>
          <h2 id="description-title">Course description</h2>
        </div>
        <div class="body-copy">
          <p>
            The course is an introduction to Visual Machine Perception technology — and specifically Computer
            Vision and Machine Learning (CV-ML) — for the built environment. It explores fundamentals and
            latest trends in this technology both in research and products, in tight reference to design,
            construction, and operation and management. It considers the current and potential impact of this
            technology on achieving sustainability goals, such as those related to reuse, circularity, and
            performance-based lifecycle, as well as the organizational considerations behind development and
            adoption.
          </p>

          <h3 class="course-detail-subhead">About</h3>
          <p>
            In recent years, a lot of discussion has been sparked in AEC (Architecture, Engineering, and
            Construction) on CV-ML for the built environment. Despite advancements in this interdisciplinary
            field, fundamental questions remain about adopting and adapting CV-ML technology — this course
            equips students with the rudimentary knowledge of how this technology works and the essential
            points to consider when applying it to this specific domain.
          </p>
          <p>
            The growing availability of sensors that collect visual data on commodity hardware, combined with
            the off-the-shelf, generalization, and zero-shot capabilities of large multimodal models, is
            creating pressure to identify how new technology can increase efficiency and decrease risk in this
            trillion-dollar industry. Cautious, well-thought steps are needed for such technologies to thrive
            in an industry that has historically shown inertia toward technological adoption, while still
            driving sustainability goals.
          </p>
          <p>The course unfolds in two interwoven storylines:</p>
          <ul>
            <li>
              The first introduces fundamentals in computer vision and machine learning technology as building
              blocks for developing related applications, discussed with respect to the latest developments
              (e.g., diffusion and large language neural models) and their impact on the final solution.
            </li>
            <li>
              The second consists of AEC processes — architectural design, construction, and operation and
              management — which drive the application of the technological storyline.
            </li>
          </ul>
          <p>
            Students will see the importance of accounting for application requirements when designing a
            CV-ML system, as well as their impact on the underlying building blocks. Guest speakers from both
            the CV-ML and AEC domains complement the lectures.
          </p>

          <h3 class="course-detail-subhead">Learning goals</h3>
          <p>
            By the end of the course, students will develop computational thinking related to visual machine
            perception applications for the built environment and the AEC domain. Specifically, they will:
          </p>
          <ul>
            <li>Gain a fundamental understanding of how this technology works and its impact on AEC and the built environment through example applications.</li>
            <li>Be able to identify limitations, pitfalls, and bottlenecks in these applications.</li>
            <li>Critically think through solutions for the above issues.</li>
            <li>Acquire hands-on experience creatively designing an application given a base system, through in-class demos and at-home assignments.</li>
            <li>Use this course as a stepping-stone or entry point to CV-ML–intensive courses offered in CEE and CS.</li>
          </ul>

          <h3 class="course-detail-subhead">Prerequisites / notice</h3>
          <p>
            The course does not require any background in CV-ML, computer science, coding, or the AEC domain.
            It is designed for students of any background, while still engaging advanced students in these
            topics. Students will engage with and even implement their own code, tightly supported by
            tutorials and assignments.
          </p>

          <h3 class="course-detail-subhead">Performance evaluation</h3>
          <p>
            Grading combines tutorials, assignments, and a final project. Tutorials engage students more
            deeply in algorithmic and application aspects and are evaluated on understanding of the presented
            material. Assignments require critical thinking, research into prior work, and/or hands-on
            interaction with a pre-existing system or codebase. The final project asks students to creatively
            design and develop an application based on course material; there is no final exam. Students may
            be evaluated with a letter grade or credit/no credit.
          </p>
          <p>
            Grading weights: 42% assignments (6% each), 6% tutorials (1% each), and 52% final project (10%
            proposal, 12% midterm, 30% final submission). Course project reviews are assigned to a team member
            other than the student's TA to reduce bias, with feedback from project supervisors and the
            assigned TA feeding into a final grading discussion. All members of a team receive the same grade
            unless there is clear evidence of unequal participation.
          </p>
          <p>
            Late submission policy: students have a total of 3 late days across the course. Each day used
            reduces that deliverable's grade by 15%, compounding for consecutive days (e.g., two late days:
            grade × 0.85 × 0.85). In case of genuine emergencies, contact the teaching team — some
            documentation may be requested. Late project reports incur the same penalty for all team members.
            No late submissions are accepted for project presentations.
          </p>
        </div>
      </section>

      <section class="section" aria-labelledby="schedule-title">
        <div class="section-heading">
          <p class="section-kicker">Schedule</p>
          <h2 id="schedule-title">Lectures, assignments &amp; deadlines</h2>
        </div>

        <h3 class="course-detail-subhead">Lectures</h3>
        <div class="table-wrap">
          <table class="data-table">
            <thead>
              <tr><th>Date</th><th>Lecture</th></tr>
            </thead>
            <tbody>
              <tr><td>January 7</td><td>Lecture 1. Introduction<br>Tutorial A. Google Colab Demo</td></tr>
              <tr><td>January 14</td><td>Lecture 2. Drawing lines, surfaces, and primitives in visual data<br>Tutorial B. Point Cloud Manipulation</td></tr>
              <tr><td>January 21</td><td>Lecture 3. As-is geometric model: From pixels to 3D reconstruction<br><em>No tutorial (Project Proposal Presentation)</em></td></tr>
              <tr><td>January 28</td><td>Lecture 4. Making sense of visual data: Segmentation and clustering<br>Tutorial C. 3D Reconstruction</td></tr>
              <tr><td>February 4</td><td>Lecture 5. What is this that I see?: Visual data classification<br>Tutorial D. Deep Feature Clustering</td></tr>
              <tr><td>February 11</td><td>Lecture 6. Toward a "digital-twin": Detection and Semantic Segmentation<br>Tutorial E. Classification and Detection</td></tr>
              <tr><td>February 18</td><td>Lecture 7. The machine designer: Generating new visual data<br><em>No tutorial (Midterm Project Presentation)</em></td></tr>
              <tr><td>February 25</td><td>Lecture 8a. Keeping track of mobile elements in construction sites: Object and people tracking<br>Lecture 8b. Construction worker productivity and safety: Activity recognition<br>Tutorial F. Object Tracking &amp; Activity Recognition</td></tr>
              <tr><td>March 4</td><td>Lecture 9. The machine worker: Human-Robot Interaction<br>Tutorial G. Diffusion Models for Image Generation and Editing</td></tr>
              <tr><td>March 11</td><td><em>Final Project Presentation</em></td></tr>
            </tbody>
          </table>
        </div>

        <h3 class="course-detail-subhead">Assignment list</h3>
        <div class="table-wrap">
          <table class="data-table">
            <thead>
              <tr><th>Name</th><th>Topic</th></tr>
            </thead>
            <tbody>
              <tr><td>Assignment 1</td><td>Edge Detection, Crack Segmentation</td></tr>
              <tr><td>Assignment 2</td><td>Image Registration, 3D Reconstruction from Images</td></tr>
              <tr><td>Assignment 3</td><td>Image Clustering, 3D Point Cloud Clustering</td></tr>
              <tr><td>Assignment 4</td><td>Image Classification, 3D Object Classification</td></tr>
              <tr><td>Assignment 5</td><td>Object Detection (images and video of a construction site), Facade Material Classification, 3D Point Cloud Instance Segmentation</td></tr>
              <tr><td>Assignment 6</td><td>Early Design Generation</td></tr>
              <tr><td>Assignment 7</td><td>Tracking, Activity Recognition</td></tr>
            </tbody>
          </table>
        </div>

        <h3 class="course-detail-subhead">Deadlines</h3>
        <div class="table-wrap">
          <table class="data-table">
            <thead>
              <tr><th>Deadline</th><th>Description</th></tr>
            </thead>
            <tbody>
              <tr><td>January 20</td><td>Project proposal report and slides due; Assignment 1 due</td></tr>
              <tr><td>January 21</td><td>Project proposal presentation, in class</td></tr>
              <tr><td>January 27</td><td>Assignment 2 due</td></tr>
              <tr><td>February 3</td><td>Assignment 3 due</td></tr>
              <tr><td>February 10</td><td>Assignment 4 due</td></tr>
              <tr><td>February 17</td><td>Midterm project report and slides due; Assignment 5 due</td></tr>
              <tr><td>February 18</td><td>Midterm project presentation, in class</td></tr>
              <tr><td>February 24</td><td>Assignment 6 due</td></tr>
              <tr><td>March 3</td><td>Assignment 7 due</td></tr>
              <tr><td>March 11</td><td>Final project slides due (1:30 PM); final project presentations, in class</td></tr>
              <tr><td>March 17</td><td>Final project report due</td></tr>
            </tbody>
          </table>
        </div>
        <p class="detail-line">All deadlines are due by 11:59 PM on the specified date, unless indicated otherwise.</p>
      </section>

      <section class="section" aria-labelledby="projects-title">
        <div class="section-heading">
          <p class="section-kicker">Projects</p>
          <h2 id="projects-title">Student projects</h2>
        </div>
        <div class="body-copy">
          <p>
            Over the quarter, students work on a project related to a topic in Computer Vision for the Built
            Environment in collaboration with a supervisor, in groups of 2–4. A list of project ideas is
            provided, and students are expected to implement and test algorithms, covering aspects such as
            dataset collection, annotation, user testing, and evaluation metrics. Full details are on Canvas.
          </p>
        </div>
        <div class="milestone-grid">
          <article class="milestone-card">
            <h3>Project proposal</h3>
            <p>
              A 1–2 page proposal describing what the project will do and why it matters to the AEC domain,
              including preliminary thoughts on success criteria and evaluation. Teams may present during a
              designated lecture, alongside a submitted presentation file.
            </p>
          </article>
          <article class="milestone-card">
            <h3>Midterm progress check</h3>
            <p>
              A 2-page report identifying current status, problems encountered, and next steps, with an
              in-class presentation and feedback opportunity, alongside a submitted presentation file.
            </p>
          </article>
          <article class="milestone-card">
            <h3>Final project delivery</h3>
            <p>
              A final presentation on the last day of class, along with an 8-page report (tables and figures
              included, references excluded) and the presentation file.
            </p>
          </article>
        </div>
      </section>

      <section class="section" aria-labelledby="resources-title">
        <div class="section-heading">
          <p class="section-kicker">Resources</p>
          <h2 id="resources-title">Book suggestions</h2>
        </div>
        <div class="dataset-list book-list">
          <a class="dataset-card" href="https://link.springer.com/book/10.1007/978-3-031-39675-5">
            <h3>A Circular Built Environment in the Digital Age</h3>
            <p>Editors: De Wolf, C., Çetin, S., &amp; Bocken, N. M.</p>
            <p class="book-publisher">Springer</p>
          </a>
          <a class="dataset-card" href="https://link.springer.com/book/10.1007/978-1-84882-935-0">
            <h3>Computer Vision: Algorithms and Applications</h3>
            <p>Richard Szeliski</p>
            <p class="book-publisher">Springer</p>
          </a>
          <a class="dataset-card" href="http://www.computervisionmodels.com/">
            <h3>Computer Vision: Models, Learning and Inference</h3>
            <p>Simon J.D. Prince</p>
            <p class="book-publisher">Cambridge University Press</p>
          </a>
          <a class="dataset-card" href="https://www.robots.ox.ac.uk/~vgg/hzbook/">
            <h3>Multiple View Geometry in Computer Vision</h3>
            <p>Richard Hartley and Andrew Zisserman</p>
            <p class="book-publisher">Cambridge University Press</p>
          </a>
          <a class="dataset-card" href="https://www.deeplearningbook.org/">
            <h3>Deep Learning</h3>
            <p>Ian Goodfellow, Yoshua Bengio, and Aaron Courville</p>
            <p class="book-publisher">MIT Press</p>
          </a>
        </div>
      </section>
    </main>

    <footer class="site-footer">
      <div class="footer-identity">
        <a href="https://cee.stanford.edu/" aria-label="Stanford Civil and Environmental Engineering">
          <img src="assets/images/stanford-cee-lockup.png" alt="Stanford University — Civil &amp; Environmental Engineering">
        </a>
        <a class="footer-soe-logo" href="https://engineering.stanford.edu/">
          <img src="assets/images/stanford-engineering-logo.png" alt="Stanford Engineering" width="1080" height="101">
        </a>
        <p>Gradient Spaces Research Group</p>
      </div>
      <div class="footer-meta">
        <p>Y2E2, 473 Via Ortega, Stanford, CA 94305</p>
        <p>Site owner: Iro Armeni · iarmeni@stanford.edu</p>
        <p class="footer-accessibility"><a href="https://www.stanford.edu/site/accessibility">Accessibility</a></p>
      </div>
    </footer>

    <script src="script.js?v=20260925"></script>
  </body>
</html>