-
Notifications
You must be signed in to change notification settings - Fork 96
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Dynamic masking #38
Closed
Closed
Dynamic masking #38
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
classObject
pushed a commit
to classObject/bi-aidetection
that referenced
this pull request
Sep 24, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
EDIT: Changes have been merged with VorlonCD's updates found here: https://github.com/VorlonCD/bi-aidetection
We are now collaborating on changes.
Summary of key changes
New feature: Create dynamic masks for objects that are detected in the same location. (e.g. your neighbors car that parks in random spots on the street)
Integrated NLog for system wide logging. Allows for customizable logging levels (trace, debug, info, warn, error, off), custom formatting, archiving, and much more. Open source, industry tested, well documented and feature rich. https://nlog-project.org/
JSON based configuration for camera settings. Automatic migration of existing v1.67 .txt config to JSON config.
UI enhancements, updated namespace from WindowsFormApp2 to AITool, disabled camera settings if no cameras are added.
Details
Object Masking Settings:
Clear Object History - Saves a list of all objects detected in the image after each DeepStack call. Each time an object is seen in the same location, increment the counter. When the count reaches the “Create mask after” count, delete object from history and move it to the masked object list . This setting determines how long to store the object’s history before deleting it. If stored for too long you may get false positives.
Create mask after - The number of times an object needs to be seen in object history before creating a mask.
Remove mask after - The number of times an object is not detected by DeepStack before removing the mask
Object variance % - Objects found by DeepStack can vary slightly in location after each call. Percent variance is the percent change allowed in the object’s position between calls to be considered a match.
Change log levels at runtime. Customizable project config file "Nlog.config" See website for all the features. https://nlog-project.org
Camera settings are saved and retrieved from JSON files. Object to JSON mapping using Newtonsoft.
Automatically migrates existing .txt config files to JSON on the first run of the program.