Talks
Speakers
Events
Topics
Sign in
Home
Talks
Speakers
Events
Topics
Leaderboard
Use
Analytics
Sign in
Suggest modification to this talk
Title
Description
Learn about combining Rails and Python for Computer Vision. We'll be analyzing images of cannabis plants in real-time and deriving insights from changes in leaf area & bud site areas. We'll explore when to use traditional statistical analysis versus ML approaches, as well as other ways CV has been deployed. We’ll cover integrating OpenCV with ActionCable & Sidekiq for broadcasting camera analysis to Rails and creating time-lapse style renderings with graphs. You will gain an understanding of what tools to use and where to start if you’re interested in using ML or CV with your Rails project!
Date
Summarized using AI?
If this talk's summary was generated by AI, please check this box. A "Summarized using AI" badge will be displayed in the summary tab to indicate that the summary was generated using AI.
Show "Summarized using AI" badge on summary page
Summary
Markdown supported
The video titled "Exploring Real-time Computer Vision Using ActionCable," presented by Justin Bowen at RailsConf 2021, delves into integrating Rails with Python for real-time computer vision applications. The primary focus is on analyzing images of cannabis plants, particularly in tracking changes in leaf and bud areas. Bowen articulates that leveraging computer vision (CV) tools can significantly enhance the agricultural process, especially in cannabis cultivation, while also discussing architectural methods for deploying Rails applications that incorporate CV techniques. **Key Points Covered:** - **Introduction to Computer Vision:** Bowen begins with an analogy between Teslas and dairy barns, illustrating how both utilize cameras for insights through CV, notably in Tesla's autopilot features and dairy farm monitoring systems for cow comfort and health. - **Experience with Drones and Agriculture:** Describing his past roles in the drone and agricultural sectors, Bowen emphasizes how his experiences shaped the development of computer vision applications in cannabis cultivation, focusing on biomass tracking and disease detection via image analysis. - **Technical Challenges in Agriculture:** Common issues such as powdery mildew and bud rot significantly impact crop yields. He proposes using CV to monitor plant health by analyzing leaf and bud areas to detect disease early and track growth rates. - **Implementation of Computer Vision Techniques:** Bowen discusses employing OpenCV with ActionCable and Sidekiq to process imagery, enabling real-time data analysis and providing actionable insights to users. He details specific methodologies for measuring healthy versus unhealthy areas in crops through pixel analysis. - **Architecture and Scalability:** The talk explores a scalable architecture for deploying computer vision applications using Rails, alongside Python. He highlights the use of services such as Puma, Redis, and Google Cloud for performance optimization and data management. - **Machine Learning Integration:** Bowen touches on how to incorporate machine learning techniques into Rails applications, including the potential use of neural networks for enhanced detection capabilities. He emphasizes learning by doing and provides resources for further exploration, such as Adrian Rosebrock's work. - **Conclusion and Future Directions:** The talk concludes with encouragement to engage in these technologies while sharing a whimsical note about his cat, underscoring a light-hearted approach to the complex world of computer vision in agriculture. Overall, attendees gain insights into the foundational tools needed for integrating machine learning and computer vision with Rails projects, especially in the context of agricultural applications.
Suggest modifications
Cancel
