Case study
Real-Time Animal Identification in Live Safari Streams
- Client: WildEarth
- Industry: Wildlife AI & Streaming Analytics
- AI capability: Computer Vision
The challenge
Live streams move, and the same animal keeps coming back
Live safari streams present unique challenges like moving cameras, varying lighting, and frequent occlusions. The system had to detect and identify animal species in real-time from live RTSP feeds while implementing tracking logic to avoid duplicate counting of the same animal across multiple frames as it moves through the scene.
What we built
Detection, species ID and event tracking on a live feed
Tracking decides what counts as a new sighting.
Live frame
1/4Frames are pulled from the live RTSP feed at high frequency and searched for animals.
A live safari feed moves: the camera pans, the light changes and animals disappear behind bushes. The pipeline identifies what is on screen and decides whether it is a new sighting or one it has already reported.
Live stream ingestion
Frames are processed straight from the broadcast RTSP feeds, not from recordings.RTSPDetection and species ID
Deep learning models handle moving cameras, night footage and partly hidden animals.Event tracking
A custom tracking layer turns many frames into one sighting, and checks stored images for animals seen before.Viewer notifications
Sightings reach the companion app, which turns watching a stream into a game.
The delivered pipeline
Detect, track, classify, store, then check whether the animal has been seen before. 
Night footage from the live broadcast, detected at 96% confidence.
The impact
Viewers get told the moment something appears
- Species identified in real time
- Repeat frames collapsed into one sighting
- Notifications in the companion app
WildEarth now offers a gamified, interactive experience where viewers can receive real-time notifications of wildlife sightings. This has significantly boosted viewer engagement and provided a novel way for audiences to connect with nature during live broadcasts.
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