View source for 18125371. METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE simplified abstract (Hyundai Motor Company)

=METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE=


==Organization Name==

[[:Category:Hyundai Motor Company|Hyundai Motor Company]]


[[Category:Hyundai Motor Company]]

==Inventor(s)==

[[:Category:Hyung-Wook Park of Seoul (KR)|Hyung-Wook Park of Seoul (KR)]][[Category:Hyung-Wook Park of Seoul (KR)]]

[[:Category:Jang-Ho Shin of Yongin-si (KR)|Jang-Ho Shin of Yongin-si (KR)]][[Category:Jang-Ho Shin of Yongin-si (KR)]]

[[:Category:Seo-Young Jo of Seoul (KR)|Seo-Young Jo of Seoul (KR)]][[Category:Seo-Young Jo of Seoul (KR)]]

[[:Category:Je-Won Kang of Seoul (KR)|Je-Won Kang of Seoul (KR)]][[Category:Je-Won Kang of Seoul (KR)]]

[[:Category:Jung-Kyung Lee of Seoul (KR)|Jung-Kyung Lee of Seoul (KR)]][[Category:Jung-Kyung Lee of Seoul (KR)]]

==METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18125371 titled 'METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE

==Simplified Explanation==

The method described in the patent application involves predicting the position of an object at a future time point for a vehicle using video image information, semantic segmentation images, mask images, and ego-motion information of the vehicle. This is done by extracting video image information and mask images, predicting a position distribution of the object through deep learning, and calculating the hypotheses as a Gaussian mixture probability distribution.

* Video image information and mask images are extracted from the camera of the vehicle.
* Position distribution of the object is predicted by deriving hypotheses for the object's position at a future time point through deep learning.
* Ego-motion information of the vehicle is used in the prediction process.
* The hypotheses are calculated as a Gaussian mixture probability distribution.

== Potential Applications ==
This technology could be applied in autonomous driving systems, object tracking in surveillance systems, and predictive maintenance in industrial settings.

== Problems Solved ==
This technology helps in predicting the position of objects in real-time, improving safety in autonomous vehicles, enhancing surveillance capabilities, and optimizing maintenance schedules.

== Benefits ==
The benefits of this technology include improved accuracy in predicting object positions, increased efficiency in object tracking, enhanced safety in autonomous vehicles, and cost savings through predictive maintenance.

== Potential Commercial Applications ==
The potential commercial applications of this technology include autonomous vehicles, surveillance systems, industrial automation, and robotics.

== Possible Prior Art ==
One possible prior art for this technology could be the use of deep learning algorithms in object tracking and prediction in various fields such as robotics and computer vision.

=== What are the limitations of this technology in real-world applications? ===

The limitations of this technology in real-world applications may include the need for high-quality video image data, potential inaccuracies in predicting object positions, and the computational resources required for deep learning algorithms.

=== How does this technology compare to existing object tracking and prediction methods? ===

This technology stands out from existing methods by combining video image information, semantic segmentation images, mask images, and ego-motion information to predict object positions with high accuracy and efficiency.


==Original Abstract Submitted==

In a method of predicting a position of an object at a future time point for a vehicle, video image information at a current time point and at a plurality of time points before the current time point acquired through a camera of the vehicle may be extracted as semantic segmentation image. A mask image imaging an attribute and position information of an object present in each of the video images may be extracted. A position distribution of the object may be predicted by deriving a plurality of hypotheses for a position of the object at a future time point through deep learning by receiving video images at the current time point and the time points before the current time point, a plurality of semantic segmentation images, a plurality of mask images, and ego-motion information of the vehicle, and calculating the plurality of hypotheses as a Gaussian mixture probability distribution.



[[Category:G06T7/70]]
[[Category:G01S17/89]]
[[Category:G06T7/12]]
[[Category:G06V10/10]]