Nicheloom visits: 36,470 all-time · 10,879 in the last 7 days

The opportunity tracker for new startups.

Today: 1,488 launches · Niche of the day: giveaway and sweepstakes platforms · See full report →

brandpose

Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Visit website ↗ Source listing ↗

GITHUB · launched Oct 15, 2026 · 123 upvotes (top 11%)

Similar launches

See all 319 similar launches →

Could you build this?

Partial The dashboard and heatmap UI can be vibe-coded by wiring together open-source models. Accurate gaze-to-zone estimation from ordinary security cameras requires camera calibration, depth handling, and validation that is real computer-vision work.

What it would actually take: The pipeline combines YOLO11 person detection, a gaze model such as Gaze-LLE, and Depth Anything V2 for depth, with calibration to map gaze vectors onto store floor zones. Accuracy depends on camera placement, per-site calibration, and validation data, so it needs computer-vision expertise. Deploying it in retail also raises privacy and biometric regulation questions that need legal review.

Competitors

Other products that read as similar to this one : 319 launches clear the similarity bar, closest 8 shown.

Attention rank: #30 of 320 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 349 days after the earliest competitor.

Other launches for this product

More details
External ID
1420107446
Company
n/a
Product
brandpose
Website domain
github.com
Cohort
n/a
Upvotes percentile
0.89
All tags
3d-reconstruction, blender, camera-calibration, cctv, computer-vision, depth-anything, depth-estimation, gaze-estimation, people-tracking, pose-estimation, python, retail-analytics, video-analytics, yolo11
AI summary
customer gaze tracking for physical retail
Manually corrected
No