AI Object Recognition via Image Normalization and Virtual Regeneration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional trail and surveillance cameras generate numerous false positives due to motion from inanimate objects like leaves or animate objects not of interest, overwhelming users with irrelevant footage, and fail to early detect chronic diseases in animal populations, such as Chronic Wasting Disease, which hampers effective monitoring and containment efforts.
Innovation Solution
An AI-powered system that detects objects within content streams, normalizes images, and virtually regenerates objects to optimize recognition, allowing for species identification, health assessment, and alerting mechanisms based on predefined criteria, thereby filtering out irrelevant data and providing timely disease detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all captured footage is provided to the end user, then complete monitoring data is available, but the user must scour through a plurality of potentially irrelevant frames
Solution Approach 1:
The system extracts and isolates only the relevant frames containing target objects from the complete footage stream. The AI engine analyzes each frame to identify frames with objects of interest, separating them from irrelevant frames (such as those containing only leaves, limbs, or background motion). This extraction process delivers complete monitoring data while eliminating the need to review irrelevant content.
2Productivity
If conventional object detection is used, then all moving objects are detected, but false positives from inanimate objects like leaves or limbs are generated
Solution Approach 1:
The system applies different analysis criteria to different regions and objects within the footage. Instead of treating all moving objects uniformly, the AI engine evaluates local characteristics such as object shape, size, texture, and motion patterns to determine relevance. This allows the system to maintain high detection coverage while filtering out false positives by applying quality-based discrimination to specific local features of detected objects.
3Reliability
If early detection of diseased animals is implemented, then disease spread can be contained, but more sophisticated analysis is required
Solution Approach 1:
The AI engine serves as an intermediary between the captured footage and the disease detection process. It automatically performs sophisticated analysis by comparing detected objects against learned profiles of healthy and diseased animals. The system extracts relevant features from images, performs classification, and generates alerts when disease indicators are detected, thereby enabling early disease detection without requiring complex manual analysis procedures.
Data Source
AI summary
The present disclosure provides a method for target identification and scoring, the method comprising: detecting an object within one or more frames of a content stream; deriving one or more images of the object from the content stream; normalizing the one or more images; processing the normalized one or more images to determine a species of the object; identifying an Artificial Intelligence (“AI”) module corresponding to the species of the object; virtually regenerating the object based on the following: the species of the object, the normalized one or more images, and one or more of the following: physical orientation of the object, time of object detection, and illumination of the object; providing the regenerated object to the AI module configured to perform object recognition; receiving an identification of the object from the AI module; and updating an object profile with object identification data.