On Guard Security Assistant Version 1.7.3.3

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

This version fixes:

1. MQTT Message publishing.
2. A step forward on parking detection and not identifying moving vehicles as parked.

On Guard Security Assistant Version 1.7.3.2

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

This version fixes problems where cars in motion were determined to be parked and were therefore ignored. In addition the determination of which cars are in fact parked should be better, but there is still work to be done there.

On Guard Security Assistant Version 1.7.3

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

This release contains bug fixes as follows:

1. Deleted areas were not staying deleted.
2. Deleted objects to find were not staying deleted.
3. URLs for motion stopped events were not being displayed for editing.

On Guard Security Assistant Version 1.7.2

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

This release contains bug fixes only.

On Guard Security Assistant Version 1.7.1

This release:

1. Fixes an issue with the registration point moving around during execution.
2. Fixes an issue where the Live Camera resolution was not saved correctly.
3. Adds the capability to selectively keep motion pictures when doing an Old Picture Cleanup. In addition, you can select to do either just the current camera or all cameras.

On Guard Security Assistant Version 1.6.2

This release adds the capability to add a custom SQL connection string. This allows users with an existing SQL database to point to the correct instance of the database.

On Guard Security Assistant Version 1.6.1.2

This release adds the ability to define more than one DeepStack AI server. It also incorporates all changes from the last pre-release 1.5.2. Updated version label.

On Guard Security Assistant Version 1.5.2.2

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

NOTE: Due to changes in the stored data, user camera and area definitions from all prior versions are no longer compatible with this version. You must enter the camera data again, and you must re-define your areas.

Changes in this release:
The user interface and engine for recognizing DeepStack objects has changed. You can now recognize/check for any object DeepStack recognizes. In addition, there are two recognition groups. One is for “* Any Vehicle” and one is for “* Any Mammal”. Thus, you can recognize any vehicle type and any mammal with just two entries.

The storage of all user changeable settings is now in the Windows Registry. This will allow for easier upgrades in future versions. For the most part you should (in the future) not need to re-define your settings.

You can now optionally notify Blue Iris that you want pictures “Confirmed” and/or “Flagged”.

You can now add a delay before any URL/Http notification.

This release involves some fairly major changes internally so it is being marked as a "pre-release". Please report any bugs!

The "Release" will now include only the setup executable and manual. If you want the source code please download that separately.

On Guard Security Assistant Version 1.4.7.3

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

NOTE: Due to changes in the stored data, user camera and area definitions from versions before 1.4.1 are no longer compatible with this version. For those updating from a "Release" prior to that version the settings data file locations have changed. You must enter the camera data again, and you must re-define your areas.

This version includes:

1. Re-adds the Test Images menu item that was accidentally removed in 1.4.7.2 when resolving scaling issues.
2. Cleans up a few memory leaks. These are believed to be minor, but might be a problem in very busy cameras.

On Guard Security Assistant Version 1.4.7.2

This project uses Blue Iris or any IP/network camera capable of producing .jpg still images as a security camera image source. It uses DeepStack as an AI to intelligently identify objects. It allows the user to monitor as many cameras as desired. It allows the user to visually create multiple areas that are of security interest, including the types of objects that are of interest in each area. It optionally triggers recording via Blue Iris and/or sends notification emails to the user. It supports notification via MQTT with user defined (or predefined) topics and payloads.

Note that while On Guard can be used with almost any IP/network camera cameras without Blue Iris, some functionality will be lost. For instance, you will not be able to use the pan/tilt/zoom or the Snapshot and Continuous video features. There are too many variations in the camera command layout between manufacturers and models.

NOTE: Due to changes in the stored data, user camera and area definitions from versions before 1.4.1 are no longer compatible with this version. For those updating from a "Release" prior to that version the settings data file locations have changed. You must enter the camera data again, and you must re-define your areas.

This version includes:

1. Several bug fixes.
2. The ability to delete the log file from the help menu.
3. The ability to set a flag for detailed logging from the help menu. This allows the user to determine why the real time images were accepted or rejected as “interesting”.
4. Revises the logic for detecting and ignoring parked vehicles and vehicles that have multiple definitions (truck, car, etc.). It boosts the confidence level for these vehicles further.
5. Some minor user interface improvements.

6. There have been changes in the OnGuard-ReadMe.docx file.  Among these changes are a detailed description on how use IFTTT with On Guard to turn on/off smart devices.
   

7. Fixed issue with screen scaling - things not fitting into the window(s) (1.4.7.2)