WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • Oct 16, 2021

Computer Vision from the Edge to the Cloud done easy

Flo Pachinger

Stop wasting bandwidth on constant video feeds. Transform edge cameras into proactive IoT endpoints that trigger heavy-lifting cloud vision APIs only when actionable events occur.

Pause
Mute Enter Fullscreen
#1 about 6 min

Practical applications and use cases for computer vision

Real-world scenarios demonstrate how cameras act as digital sensors for retail, public safety, and smart cities.

#2 about 3 min

Components and architecture of computer vision systems

The core technical pipeline involves capturing video, storing footage, processing logic via inference, and displaying results on a dashboard.

#3 about 3 min

Capabilities and features of cloud-managed IP cameras

Modern cloud-deployed cameras offer built-in edge processing for object detection, audio analytics, and illuminance measurement.

#4 about 2 min

Developer interfaces for interacting with camera hardware

Event-driven integrations leverage communication protocols like MQTT, webhooks, and REST APIs alongside real-time RTSP streams.

#5 about 2 min

Configuring priority detection zones in live camera feeds

Defining targeted tracking areas within a live video stream enables specific MQTT event triggers.

#6 about 2 min

Processing camera events with a Python subscriber script

A custom Python script connects to an MQTT broker to listen for event payloads and automatically capture snapshots.

#7 about 2 min

Simulating lux drops and ambient fire alarm events

Covering the physical sensor and playing a siren video validate the camera's real-time detection mechanisms.

#8 about 2 min

Extracting metadata via external face detection APIs

Uploading captured snapshots to cloud services yields structured JSON responses containing bounding boxes and demographic estimates.

#9 about 5 min

Architectural workflow of edge triggers to cloud inference

Running edge inference exclusively on predefined physical actions saves significant compute resources compared to constant cloud streaming.

#10 about 4 min

Comparing computer vision platforms across cloud providers

Evaluating AWS, Azure, and Google Cloud reveals differing availability of out-of-the-box machine learning models and API pricing tiers.

#11 about 4 min

Exploring community projects for specialized hardware pipelines

Advanced edge use cases combine serverless architectures with third-party tools to recognize masks, read license plates, and monitor entryways.

#12 about 2 min

Core advantages of hybrid edge and cloud systems

Combining localized hardware triggers with powerful cloud AI offers a scalable and secure approach to processing visual data.

#13 about 17 min

Implementing object thresholds and custom training models

Filtering out unwanted detection objects and preparing custom training datasets enable specialized object recognition in unique environments.

Matching moments

3:21 min

Reducing cloud dependency with on-device edge AI models

Precious Osaro Precious Osaro · WWC Europe 2026

37 sec

Deploying edge computing applications across target industries

Antonio Tavera Antonio Tavera · WWC 2025

2:26 min

Cost and latency pressures pushing AI to the edge

Moe Sani Moe Sani · WWC Europe 2026

3:36 min

Deploying intelligent edge filters to onboard vehicular modules

Nico Schmidt · LIVE

5:51 min

Deploying machine learning models at the edge for conservation

Sohan Maheshwar · LIVE

3:58 min

Controlling hardware cameras and analyzing visual frames

Marc Rousavy Marc Rousavy · WWC 2025

More from WeAreDevelopers LIVE

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail
5:43
5 days ago

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail
1:08:30
5 days ago

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail
1:10:26
12 days ago

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail
1:02:34
19 days ago

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail
1:07:59
26 days ago

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail
5:55
about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Point. Ask. Answer. Building Vision into AI Live on Stage.

Kavya Sri Chennoju

Staff AI Engineer at Arm

Kavya Sri Chennoju
Open session

World Congress 2026 North America

Trust, But Verify: Continuous GPU Validation at Scale

Kyle Bell

VP of AI @ TensorWave

Kyle Bell
Open session

World Congress 2026 North America

Microservice Cognitive Index for Deploy Diagnosis and Change Impact

Sachin Gupta

Member of Technical Staff 2 at eBay

Sachin Gupta
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey

Related videos

Edge Orchestration for the Physical World: Connecting Cameras, Sensors, and Devices with MQTT thumbnail
5:51
WWC Europe 2026 • about 1 month ago

Edge Orchestration for the Physical World: Connecting Cameras, Sensors, and Devices with MQTT

Irina Terekhova

From Code to Motion: Building an Autonomous Hat-Hunting Robot with Kubernetes & ML thumbnail
30:58
WWC 2025 • 12 months ago

From Code to Motion: Building an Autonomous Hat-Hunting Robot with Kubernetes & ML

Daniel Brintzinger

Focoos AI: Building the Future of Computer Vision thumbnail
4:18
WWC 2025 • 12 months ago

Focoos AI: Building the Future of Computer Vision

Antonio Tavera

Trends, Challenges and Best Practices for AI at the Edge thumbnail
29:50
WWC 2023 • almost 3 years ago

Trends, Challenges and Best Practices for AI at the Edge

Ekaterina Sirazitdinova

Leverage Cloud Computing Benefits with Serverless Multi-Cloud ML thumbnail
39:58
LIVE • over 5 years ago

Leverage Cloud Computing Benefits with Serverless Multi-Cloud ML

Linda Mohamed

From Perception to Autonomy: Building Agentic Edge AI Robots with ROS 2 thumbnail
25:50
WWC Europe 2026 • about 1 month ago

From Perception to Autonomy: Building Agentic Edge AI Robots with ROS 2

Moe Sani

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.