Pre-Flood Monitoring
Last updated
Last updated
The Nodeflux Pre-Flood Monitoring System empowers users to proactively monitor for potential flooding events by identifying the presence of puddles on roadways. This solution leverages advanced Large Vision Models and Visual Transformers integrated directly within the Nodeflux Visionaire platform. The analytics system automatically detects road conditions, classifying them in real-time as either "normal dry road" or "waterlogged road" based on real-time inferences.
Nodeflux Pre-flood Monitoring is primarily intended for use in smart city surveillance applications. It functions by monitoring for the potential occurrence of floods through puddle detection and aids in mitigating or preventing potential risks or threats associated with future flood events.
Disclaimer: In a sense of large vision models and visual transformers technology, the performance of this analytic might slightly differ in your environment, depending on several variables such as camera specs, camera height, camera angle, weather conditions, etc. We highly recommend you to test our analytics and run benchmarks on your own images, with ground truth or your quality expectations prepared beforehand. Please contact us for more info.
Visionaire Pre-Flood Monitoring utilizes a combination of other services:
Postgres - For database,
Docker Snapshot - For object classification related,
Visionaire Docker Stream (must be v4.57.4 and above) - For video stream processing,
Visionaire Dashboard (Optional) - Built-in dashboard for visualization.
Since Nodeflux Pre-Flood Moniotring utilizes the snapshot platform, an additional docker-compose.yml file needs to be deployed alongside the other aforementioned services. The following outlines the installation process for deploying the docker-compose.yml file specific to the Open Vocabulary Image Classification (OVIC) pipeline of snapshot platform:
When you are assigning this analytics into the stream through the dashboard, you should configure some parameters setting below as you need:
dump_interval
How frequent you want the stream as a frame snapshot to get the inference result. Unit in second
address
The IP address and its port where the OVIC snapshot service is deployed
dump_confidence
The value of minimum confidence threshold so that the inference result should be dumped as the event. Unit ranged between 0.1 to 1