Project Info

Locked.AI

Inspiration

We, and many of our peers are constantly afflicted by our generation's diminishing attention span and growing reliance on social media. We came up with Locked.AI to remedy the poor focus that we may face when it comes to long periods of lectures and studying.

What it does

Locked.AI utilizes an artificial intelligence software that tracks eye and head movements to distinguish focused moments from unfocused ones, promptly alerting the user through their mobile device to get them back on track. After a studying session or lecture, Locked will give users a feedback report of how focused they were.

How we built it

We built Locked.AI using Python's OpenCV, mediapipe and Flask libraries for the backend and HTML/CSS for the frontend.

Challenges we ran into

One challenge we faced was being able to properly align the AI models with our goals. For instance, it was difficult perceiving depth with tracking sleepiness. We also ran into trouble detecting focus states as the thresholds required were extremely precise. Another difficulty was communicating between our Flask backend and HTML/CSS frontend. It took some time to figure out how to display our video recording with Javascript.

Accomplishments we're proud of

We are proud of making a finished product with technologies we are new to.

What we learned

We learned new Python technology and how to efficiently collaborate in a team.

What's next

Locked.AI plans to improve their face and eye detection accuracy and host its service on a server.

Analysis

Compare with all teams

View

Metric

kesavanramakrishnan
1

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only

CSSIn code
FlaskIn code
HTMLIn code
JavaScriptIn code
PythonIn code

5 of 5 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

270 KB

Source files

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

Feature verification

5 Verified2 Code-supported2 Claimed only

Built with OpenCV, mediapipe, Flask (Python) and HTML/CSS (frontend)Verified
Built using Python's OpenCV, mediapipe and Flask libraries for backend, HTML/CSS for frontend
Claimed on Devposthigh confidence
- requirements.txt:1 — Lists opencv-python, mediapipe, flask as dependencies
- app.py:1 — Imports Flask, cv2, mediapipe in the backend
- templates/index.html:1 — HTML/CSS frontend template rendered by Flask
Eye/head movement tracking for focus detectionVerified
AI tracks eye and head movements to distinguish focused from unfocused moments
Claimed on Devposthigh confidence
- app.py:161 — focusTrack block computes hori_c/vert_c distances from face landmarks and compares to thresholds (0.77, 0.687) of calibrated baseline to classify Focused/Unfocused
- app.py:98 — mediapipe FaceMesh landmarks used for forehead/chin/cheek points feeding the focus calculation
Live webcam video stream in browser (Flask backend to HTML/CSS/JS frontend)Verified
Flask backend and HTML/CSS frontend communicate to display video recording with Javascript
Claimed on Devposthigh confidence
- app.py:199 — /video_feed route streams generate_frames() as multipart JPEG response
- static/scripts.js:83 — videoStream.src set to the /video_feed endpoint URL to display the stream in an img tag
Post-session feedback reportVerified
After a studying session or lecture, Locked gives users a feedback report of how focused they were
Claimed on Devposthigh confidence
- app.py:205 — /pause_stream endpoint tallies zero/one counts from sleep_data and returns them as a summary
- static/scripts.js:115 — showModal/renderChart displays a Chart.js doughnut chart of Focused vs Unfocused time using the pause_stream response
Sleep/eye-closure detectionVerified
Distinguishes focused vs unfocused moments including detecting dozing off (fatigue) via eye closure
Claimed on Devposthigh confidence
- app.py:148 — normalized_eye_distance compared to baseline_eye_distance*0.70 to detect closed eyes, incrementing closed_eye_counter
- app.py:156 — closed_eye_counter >= sleep_threshold triggers sleeping counter and notification
Mobile device alert via PushoverCode-supported
Promptly alerts the user through their mobile device to get them back on track
Claimed on Devpostmedium confidence
- app.py:26 — send_notification_to_iphone uses PushoverAPI to send a message, called on sleep_threshold trip (line 158)
- app.py:28 — Pushover api_token is hardcoded and user_key is only set via /receive_data; no notification call exists for the 'unfocused' branch, only for sleep, so mobile alerting for unfocused moments specifically is not wired up
Session start/stop controls with focus/sleep tracking optionsCode-supported
Implied by 'studying session' and 'lecture' focus tracking workflow
Claimed on Devpostmedium confidence
- templates/index.html:177 — sessionForm has trackFocus/trackSleep checkboxes and emailInput submitted to backend
- app.py:187 — /receive_data reads data['focus'] and data['sleep'], but line 195 assigns focusTrack from data['sleep'] instead of sleepTrack, a bug that means the sleep toggle doesn't actually control sleepTrack
Diminishing attention span / social media distraction motivationClaimed only
Inspiration narrative about attention span and social media
Claimed on Devposthigh confidence
Hosting the service on a server (future plan)Claimed only
What's next: host its service on a server
Claimed on Devposthigh confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.