To build an AI-powered retail intelligence platform that delivers real-time shopper analytics, automated inventory visibility, and proactive queue management through on-device AI,enabling retailers to reduce stock-outs, improve customer experience, optimize staffing, and increase operational efficiency while maintaining privacy and minimizing cloud dependency.
Qualcomm Inc · Smart Automation · Hardware
Buildable with a clean demo, but retail vision analytics is a saturated category and the innovation is thin beyond the on-device privacy angle — lean hard into privacy-preserving edge processing as the differentiator, or this reads as a reimplementation of existing retail tools.
What it actually is
Retail stores lose money to stock-outs, long checkout queues and no insight into shopper behaviour, and many Indian stores have poor connectivity. The ask is a smart-camera system running on-device AI that tracks shopper movement and dwell time, detects out-of-stock shelves, and predicts queue congestion before it builds — all locally, for privacy and to work without constant cloud access.
What to build
An edge retail-analytics system using smart cameras with on-device inference to analyse shopper movement and dwell time by store section, detect out-of-stock products and monitor shelf compliance, and predict checkout-queue congestion before it impacts customers, running inference locally for low latency and privacy so no video leaves the store, converting the video into actionable business insights — traffic patterns, dwell heat maps, stock-out alerts, staffing and queue recommendations — on a dashboard for the retailer, functioning reliably even during connectivity outages.
Smallest thing that wins the room
Run the system on store or sample footage and show live shopper dwell heat maps by section, an out-of-stock shelf detected and flagged, and a queue-congestion prediction firing before the checkout line actually backs up — all processed on-device with no video leaving the machine.
How crowded this one gets
A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.
Quieter than 98% of the 226 · #6 of 226 by expected field
Few teams are likely to go here. The best odds on the board come from statements like this.
Why: company-sponsored statements drew the smallest fields of all; hardware halves the field a software statement gets.
This is a guess, not a fact
Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.
The scores
The number is the shorthand. The line under it is the reason.
Acceptance potential
2/5It is buildable and the demo is clean, but retail vision analytics is a saturated commercial category with mature products, the innovation is thin beyond the on-device privacy angle, and a judge will see a competent reimplementation of existing retail-analytics tools rather than something distinctive.
Feasibility
3/5Person detection, tracking, dwell analysis and shelf out-of-stock detection are all standard computer vision runnable on edge hardware, and public retail and shelf datasets exist, but doing all three well plus queue prediction on-device is a broad build, and shelf compliance detection in particular needs product-level recognition that is genuinely finicky.
Innovation scope
2/5Retail vision analytics — footfall, dwell, out-of-stock, queue monitoring — is a mature commercial category with established products, so beyond the on-device and privacy angle there is little genuinely new, and the description bundles the standard feature set.
Clarity
4/5The capabilities are enumerated clearly — shopper analytics, dwell time, out-of-stock detection, shelf compliance, queue prediction — and the on-device and privacy requirements are explicit, so the target is well defined.
Effort
MassiveDetection and tracking, dwell heat mapping, out-of-stock and shelf-compliance recognition, queue prediction and a dashboard, all on-device, is a broad multi-feature build.
Demo-ability
EasyDwell heat maps, a flagged empty shelf and a queue-congestion prediction on store footage are immediately legible business outputs that a retail judge grasps at once.
In its favour
- Green flag: Person detection, tracking and dwell analysis are all standard and runnable on edge hardware with public datasets available
- Green flag: The on-device, no-video-leaves-the-store design is a genuine privacy strength and the one real differentiator
- Green flag: Dwell heat maps and out-of-stock alerts are immediately legible business outputs for a retail judge
- Green flag: Qualcomm's edge-AI platform gives the on-device inference a credible hardware story
Against it
- Red flag: Retail vision analytics is a saturated commercial category, so a competent build looks like existing products and the innovation bar is high
- Red flag: Shelf-compliance and out-of-stock detection need product-level recognition that is genuinely finicky and often the weak feature
- Red flag: Bundling shopper analytics, stock detection and queue prediction invites shallow breadth across all three
- Red flag: The differentiation rests almost entirely on the on-device privacy angle, so without leaning hard into that it is undistinguished
What you will be writing
- On-device person detection + tracking (edge NPU)
- Dwell-time heat mapping
- Shelf out-of-stock / planogram compliance detection
- Queue-length congestion prediction
- Privacy-preserving on-device video (no upload)
- Retail analytics dashboard
- Retail analytics
- Edge computer vision
- Business intelligence
Prior art to read before you start
shopper movement and dwell analytics · out-of-stock shelf detection · queue congestion prediction
Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.