18125371. METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE simplified abstract (Hyundai Motor Company)
Contents
- 1 METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
METHOD OF PREDICTING A POSITION OF AN OBJECT AT A FUTURE TIME POINT FOR A VEHICLE
Organization Name
Inventor(s)
Jang-Ho Shin of Yongin-si (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.
