System and method for detecting and tracking an object
Inventors
Jafek, Benjamin • Tumuluru, Samvruta
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12277744-B2
Publication Date
2025-04-15
Expiration Date
Abstract
A method includes receiving a first image that is captured at a first time. The method also includes detecting a location of a first object in the first image. The method also includes determining a region of interest based at least partially upon the location of the first object in the first image. The method also includes receiving a second image that is captured at a second time. The method also includes identifying the region of interest in the second image. The method also includes detecting a location of a second object in a portion of the second image that is outside of the region of interest.
Core Innovation
The invention provides a method for detecting and tracking a first moving object using long-range aircraft object detection with a camera capturing a first image at a first time. A location of the first moving object is detected in the first image, and a region of interest is determined based at least partially upon that location. The region of interest has a probability greater than a predetermined threshold that the first moving object will be located therein at a second time.
After determining the region of interest, a second image is identified as captured by the camera at the second time. The region of interest is identified in the second image, and a location of a second moving object is detected in a portion of the second image outside the region of interest. This partitioning is used to detect a second moving object while avoiding re-detection of the first moving object.
In computing system embodiments, the invention includes hidden Markov model based detection of the first object in the first image and region of interest determination. The computing system then identifies the region of interest in the second image and detects the location of the first object within the region of interest using the hidden Markov model. A location of a second object is detected in a portion of the second image outside the region of interest using the hidden Markov model to avoid re-detection of the first object.
Claims Coverage
The partial content includes three independent claims. Across these claims, the inventive core includes detecting a first moving object in a first image, determining a probability-based region of interest for a second time, and detecting a second moving object only outside that region of interest.
Probability-based region of interest for future object location
Determining a region of interest based at least partially upon the location of the first moving object in the first image, wherein the region of interest has a probability that is greater than a predetermined threshold that the first moving object will be located therein at a second time.
Detect second moving object outside predicted region of interest
Detecting a location of a second moving object in a portion of the second image that is outside of the region of interest.
Aircraft camera image pair with ROI partitioning
Identifying a first image that is captured by a camera on a first aircraft at a first time; detecting a location of a first object in the first image, wherein the first object is moving; determining a region of interest based at least partially upon the location of the first object in the first image, wherein the region of interest has a probability that is greater than a predetermined threshold that the first object will be located therein at a second time; identifying a second image that is captured by the camera on the first aircraft at the second time; identifying the region of interest in the second image; and detecting a location of a second moving object in a portion of the second image that is outside of the region of interest.
Hidden Markov model detection with pixel-limited representation
Detecting a location of a first object in the first image using a hidden Markov model, wherein the first object is a second aircraft in flight, and wherein the first object is represented as five or fewer pixels in the first image.
Hidden Markov model ROI detection and avoided re-detection
Detecting the location of a first object in the region of interest in the second image using the hidden Markov model; and detecting a location of a second object in a portion of the second image that is outside of the region of interest using the hidden Markov model to avoid re-detection of the first object.
The independent claims cover an image-based, probability-threshold region of interest approach that uses a first image to predict where a first moving object will appear in a second image, then detects a second moving object in the portion outside that region to avoid re-detection. Computing-system embodiments further specify hidden Markov model based detection and ROI-based re-detection avoidance.
Stated Advantages
Avoid re-detection of the first object when detecting the second moving object outside the region of interest.
Documented Applications
Long-range aircraft object detection and multi-object tracking using a camera on an aircraft capturing images at a first time and a second time.
Collision avoidance by navigating the first aircraft based at least partially upon predicting trajectory of the first moving object.
Airborne camera/gimbal based implementations for aircraft navigation adjustments based on predicted trajectories.
Interested in licensing this patent?