Case study
Find My Ball: Real-Time AI Golf Ball Detection on Mobile Devices
- Client: FMB
- Industry: Sports AI & Mobile Computer Vision
- AI capability: Computer Vision
- On-device inference time
- <30ms
- Detection recall
- 92%
The challenge
A golf ball in long grass is a handful of pixels
Detecting golf balls in natural environments like tall grass or leaf piles is difficult due to the small object size and cluttered backgrounds. Additionally, the system needed to perform real-time detection entirely on-device without cloud dependency to ensure low latency and continuous availability during gameplay on various course terrains.
What we built
A small-object detector that runs on the phone
Fine-tuned for clutter, then quantized for iPhone hardware.
Add your ball
Four photos of the ball and its markings.
1/4The golfer photographs their own ball, including its markings, so the app knows what to look for.
A golf ball in long grass is a small object on a cluttered background, and there is no signal to rely on halfway down a fairway. The model runs on the phone itself.
Tuned for small objects
A YOLO detector fine-tuned on balls in grass, leaves and shadow, where the target is a few pixels wide.YOLOQuantized for mobile
Quantization and CoreML conversion keep frame rates high on iPhone hardware.QuantizationCoreMLNo cloud round trip
Inference happens on the handset, so there is no latency and no dependency on course coverage.Shipped on the App Store
Running in the live Find My Ball app for golfers.
The impact
Balls found without holding up the group
- Under 30ms inference on device
- 92% detection recall
- Works with no connection
The solution enables golfers to locate lost balls instantly, improving pace of play and enhancing the overall golfing experience. It serves as a prime example of how edge AI can power intelligent, real-time mobile applications in challenging physical environments.
Keep exploring
Related case studies
Real Estate & PropTechComputer VisionAI Property Image Intelligence for Listing Optimization & Compliance
PropTech founders and real estate leaders understand that property photos are the most critical asset in closing deals. PropTexx needed an automated way to enforce strict listing compliance and extract valuable insights from millions of unstructured real estate images without slow manual review.
- Property features tagged automatically
- 50+
- Compliance violation types detected
- 15+
Retail & E-commerceComputer VisionSneaker Visual Retrieval System
AlwaysLegit needed a way for their team at expos to instantly identify shoes from photos and match them against a massive 150K+ SKU database, often in challenging real-world lighting and backgrounds.
- SKUs searchable from a single photo
- 150K+
- Retrieval time per query
- <1s
Sports & MediaComputer VisionSoccer Match Analytics & Insights
The aim of this project is to give soccer analytics of matches being played. The goal is to build an AI tool that takes as input a video of a soccer match and then analyzes each player and extracts different analytics. This included: 1. Player and ball detection, 2. Player and ball tracking, 3. Player re-identification, 4. Field detection, 5. Event detection including passes, intercepts, goals etc.
Multi-stage CV pipeline. Real-time event detection. Player re-identification.
Read the case study
Book a strategy session
Talk to an AI engineer about your project
Tell us what you want to automate. The first call is a 30-minute working session with an engineer, not a sales pitch.
- Send the form, it takes 2 minutes
- We reply within 1 business day, under NDA if you need it
- A 30-minute call to scope feasibility and next steps