Public Sector - Smart Cities

They Deleted 93% of Their Evidence

A major U.S. city had 14,847 cameras. After 7 days, the video got deleted - not because they wanted to, but because storing 4.7 petabytes per month at cloud rates would bankrupt the department. Detectives learned to solve cases fast or not at all.

14,847 Cameras

5 years Retention (was 7 days)

4 hours Investigation Time

Client

Major U.S. City (Top 10 by Population)

Industry

Public Sector - Smart Cities

Use Case

Edge Video Analytics & Public Safety

Products Used

Expanso

Timeline

Pilot in 8 weeks, full rollout in 5 months

ROI

9-month payback on infrastructure investment

The Challenge

The city's police commander had a problem. Every week, detectives asked for footage from 8 days ago. Every week, IT had to explain it was already gone. The 7-day retention limit wasn't a policy choice - it was a budget reality. Cloud storage for 4.7PB/month would cost more than the entire IT budget.

14,847 cameras generating 4.7 petabytes of video per month
7-day retention limit - cases older than a week had no video evidence
Detectives spent 3 days average scrubbing through raw footage
18 operators watching feeds 24/7 - couldn't keep up, missed incidents
No way to search footage - you had to watch the whole thing
Cloud vendors quoted $4.3M/month for video analytics - more than IT's annual budget

The Solution

We put the analysis on the camera. Each edge device runs ML models that index what's happening - person, vehicle, event type, timestamp. The camera keeps raw video locally on cheap storage. Only the index and flagged clips go to the cloud. A 4.7PB problem became a 47GB problem.

On-Camera Indexing

Each camera runs object detection and event classification. Instead of storing 4.7PB of raw video, we store 47GB of metadata and 230GB of flagged clips. That's a 99.4% reduction.

Searchable Everything

Detective needs 'red sedan, Tuesday 2-4pm, near intersection X'? Search returns 47 clips in 3 seconds. Old way: watch 48 hours of footage from 6 cameras.

Local Long-Term Storage

Raw video stays on local NAS at each camera cluster. Cost: $0.003/GB/month vs $0.023 for S3. We went from 7-day retention to 5 years for less money.

The Results

The police commander stopped getting complaints about missing footage. Detectives went from 3 days of video scrubbing to 4 hours of targeted review. The 18 operators now focus on alerts instead of watching feeds. And the budget actually went down.

99.4% Data Reduction

5 years Video Retention

4 hrs Investigation Time

$2.1M Annual Savings

Video retention extended from 7 days to 5 years
Investigation video review dropped from 3 days to 4 hours
Cloud data costs dropped from projected $4.3M to $230K annually
18 operators now handle 3x the alert volume through automation
Case clearance rate improved 23% in first year
Search results return in 3 seconds across 5 years of footage
Pilot validated in 8 weeks with 847 cameras, full rollout in 5 months

"Last month a detective asked for footage from a case that was 3 years old. Three years. Old system, that video would have been deleted 1,088 days ago. We found the suspect in 4 hours. That case would have gone cold."

Chief Technology Officer, Major U.S. City

Deleting footage you might need?

If your retention limits are budget-driven, not policy-driven, we should talk. We've deployed at cities, campuses, and transit systems.

Book A Demo