View source for 20240036186. MULTI-TARGET DETECTION USING CONVEX SPARSITY PRIOR simplified abstract (Numerica Corporation)

=MULTI-TARGET DETECTION USING CONVEX SPARSITY PRIOR=


==Organization Name==

[[:Category:Numerica Corporation|Numerica Corporation]]


[[Category:Numerica Corporation]]

==Inventor(s)==

[[:Category:Jason Kyle Johnson of Fort Collins CO (US)|Jason Kyle Johnson of Fort Collins CO (US)]][[Category:Jason Kyle Johnson of Fort Collins CO (US)]]

[[:Category:Dylan Scott Eustice of Boston MA (US)|Dylan Scott Eustice of Boston MA (US)]][[Category:Dylan Scott Eustice of Boston MA (US)]]

[[:Category:Evan Jackson Everett of Fort Collins CO (US)|Evan Jackson Everett of Fort Collins CO (US)]][[Category:Evan Jackson Everett of Fort Collins CO (US)]]

[[:Category:Shawn Michael Herman of Fort Collins CO (US)|Shawn Michael Herman of Fort Collins CO (US)]][[Category:Shawn Michael Herman of Fort Collins CO (US)]]

==MULTI-TARGET DETECTION USING CONVEX SPARSITY PRIOR - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240036186 titled 'MULTI-TARGET DETECTION USING CONVEX SPARSITY PRIOR

==Simplified Explanation==

The abstract describes a method for detecting the trajectories of targets in the field of view of sensors. The method involves receiving sensor frames, defining allowable target states, specifying potential target trajectories, specifying target signal parameters, specifying a data fidelity objective, specifying sparsity objectives, determining the trajectories of targets, and storing the final trajectories in memory.

* The method receives sensor frames from one or more sensors.
* It defines a space of allowable target states for the sensor frames.
* It specifies a set of potential target trajectories, each with an allowable target state for each sensor frame.
* It specifies target signal parameters for each allowable target state, predicting the expected target signal contribution.
* It specifies a data fidelity objective to quantify how well the target signal parameters match the sensor frames.
* It specifies a sequence of sparsity objectives to penalize the number of detected targets.
* The method determines the trajectories of targets by optimizing the sum of the data fidelity objective and the sparsity objective.
* The final trajectories are stored in memory.

Potential Applications:
* Surveillance systems: This method can be used in surveillance systems to track the trajectories of targets, such as vehicles or individuals, in the field of view of sensors.
* Autonomous vehicles: This method can be applied in autonomous vehicles to detect and track the trajectories of other vehicles or objects in the surroundings.

Problems Solved:
* Target trajectory detection: The method solves the problem of detecting and tracking the trajectories of targets in the field of view of sensors.
* Data fidelity optimization: The method optimizes the target signal parameters to match the sensor frames, improving the accuracy of trajectory detection.
* Sparsity optimization: The method penalizes the number of detected targets, allowing for more efficient and focused trajectory detection.

Benefits:
* Accurate trajectory detection: The method improves the accuracy of detecting and tracking target trajectories in the field of view of sensors.
* Efficient optimization: By specifying target signal parameters and using sparsity objectives, the method optimizes the detection process, reducing computational resources and time.
* Versatile application: The method can be applied in various fields, such as surveillance systems and autonomous vehicles, enhancing their capabilities in target tracking and situational awareness.


==Original Abstract Submitted==

provided is a method for detecting the trajectories of one or more targets in the field of view of one or more sensors, the method comprising: receiving one or more sensor frames corresponding to the one or more sensors; defining a space of allowable target states for the one or more sensor frames; specifying a set of potential target trajectories, each comprising one allowable target state for each of the one or more sensor frames; specifying target signal parameters for each of the allowable target states, such that the target signal parameters predict the expected target signal contribution corresponding to the one or more sensor frames; specifying a data fidelity objective to quantify how well the target signal parameters match the one or more sensor frames; specifying a sequence of one or more sparsity objectives to penalize a number of detected targets; determine the trajectories of one or more targets as follows: obtain values for all the target signal parameters in all the sensor frames, the obtained values being initialized values or previously optimized values, for each sparsity objective of the sequence, starting with the obtained target signal parameters, determine new target signal parameters to optimize the sum of the data fidelity objective and the sparsity objective; and storing the final trajectories in memory.



[[Category:G01S13/58]]
[[Category:G01S13/72]]
[[Category:G01S7/292]]