Optimizing Blue Iris Surveillance with AI

Table of Contents

1. Introduction to AI or Artificial Intelligence on Blue Iris
2. Installing Code Project AI on the Same Computer as Blue Iris
3. Running Code Project AI Locally or on a Server
4. Understanding the Role of Models in Code Project AI
5. Setting Up Blue Iris to Send Images to Code Project AI
6. Configuring AI Settings in Blue Iris
7. Adjusting Confidence Levels and Real-Time Image Frequency
8. The Impact of System Resources on Running Code Project AI
9. Monitoring Code Project AI with the AI Dashboard
10. Troubleshooting Common Issues with Code Project AI and Blue Iris

Introduction to AI or Artificial Intelligence on Blue Iris

Artificial Intelligence (AI) has become an integral part of many surveillance systems, including Blue Iris. Blue Iris offers the ability to incorporate AI capabilities through the use of tools like Code Project AI or DeepStack. By utilizing AI, Blue Iris can detect objects such as humans, dogs, cars, and boats, reducing false positives and providing more accurate notifications. In this article, we will explore how to install and configure Code Project AI on the same computer as Blue Iris, as well as the option of running Code Project AI on a separate server.

Installing Code Project AI on the Same Computer as Blue Iris

To install Code Project AI on the same computer as Blue Iris, You can visit the Code Project AI Website and download the latest version. Once downloaded, you can extract the files and run the installer. The installation process may take some time as it pulls down the necessary models for object detection. It is worth noting that running Code Project AI locally on the same computer as Blue Iris may Consume system resources, so it is essential to consider the CPU and GPU utilization of your device.

Running Code Project AI Locally or on a Server

While it is common to run Code Project AI on the same computer as Blue Iris, it is not a requirement. Code Project AI can also be run on a separate server or even in the cloud using a Docker image or a cloud instance. Running Code Project AI on a different device can help distribute the CPU and GPU load and prevent congestion on the Blue Iris machine. However, it is important to ensure that the Blue Iris server can connect to the Code Project AI server for seamless communication.

Understanding the Role of Models in Code Project AI

Code Project AI utilizes models to accurately detect objects in images. These models are trained using a vast dataset of images that represent different objects such as people, dogs, cats, buses, etc. When an image is sent from Blue Iris to Code Project AI for analysis, the model compares it with the Patterns it has learned to determine the presence of an object. The availability and quality of these models are crucial for accurate object detection, and Code Project AI continuously updates and improves them.

Setting Up Blue Iris to Send Images to Code Project AI

To enable Code Project AI in Blue Iris, you need to specify the location of the AI server in the global settings. If Code Project AI is running on the same computer, you can use the local host IP address (typically 127.0.0.1) and the default port. It is also recommended to enable the automatic start and stop of Code Project AI with Blue Iris. However, if you choose to run Code Project AI on a separate device, you will need to enter the IP address and port of that device.

Configuring AI Settings in Blue Iris

In the AI settings of Blue Iris, you can fine-tune various parameters to optimize the detection process. These include the minimum confidence level, real-time image frequency, and object detection options. The minimum confidence level determines the threshold at which Code Project AI considers an object detected. Adjusting this value allows you to prioritize accuracy or minimize false positives. The real-time image frequency controls the rate at which Blue Iris sends images to Code Project AI for analysis, directly impacting resource consumption.

Adjusting Confidence Levels and Real-Time Image Frequency

Finding the right balance between confidence levels and real-time image frequency is crucial for accurate object detection and resource management. The confidence level is a measure of Code Project AI's certainty in detecting an object. Higher confidence levels reduce false positives but may also increase the likelihood of false negatives. The real-time image frequency determines how frequently Blue Iris sends images for analysis. Higher frequencies provide more precise detection but also consume more system resources.

The Impact of System Resources on Running Code Project AI

Running Code Project AI requires significant CPU and GPU resources, especially when processing a large number of images. It is essential to consider your device's capabilities and usage before running Code Project AI on the same computer as Blue Iris. High CPU or GPU utilization may affect the overall performance and responsiveness of your system. If your CPU or GPU is already heavily utilized, it may be better to run Code Project AI on a separate server or in the cloud to distribute the workload.

Monitoring Code Project AI with the AI Dashboard

Code Project AI provides an AI dashboard that allows you to monitor the object detection process. The dashboard displays the objects requested by Blue Iris and the corresponding images being analyzed. It also provides information about CPU or GPU usage, allowing you to gauge the resource consumption. The AI dashboard is a valuable tool for troubleshooting and ensuring that Code Project AI is functioning correctly.

Troubleshooting Common Issues with Code Project AI and Blue Iris

When using Code Project AI with Blue Iris, you may encounter certain challenges or performance issues. Some common issues include false positives, incorrect object detection, or high CPU/GPU utilization. To troubleshoot these problems, it is recommended to adjust the confidence levels, real-time image frequency, and object detection settings. Monitoring the system resources using the task manager can also help identify any bottlenecks or limitations that may be affecting the performance of Code Project AI.