Qualcomm incorporated (20240378911). TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS simplified abstract
Contents
- 1 TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Vehicle Driving Assistance Systems
- 1.13 Original Abstract Submitted
TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS
Organization Name
Inventor(s)
Balaji Shankar Balachandran of San Diego CA (US)
Varun Ravi Kumar of San Diego CA (US)
Senthil Kumar Yogamani of Headford (IE)
TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240378911 titled 'TERRAIN-AWARE OBJECT DETECTION FOR VEHICLE APPLICATIONS
Simplified Explanation
This patent application describes a method for training a machine learning model to identify contact points and ground surface normal vectors using image and position data.
- The method involves receiving image data depicting an object and position data for the object, such as point cloud position information.
- Two sets of labels are determined based on the position data, one set identifying contact points with a ground surface and another identifying normal vectors for the ground surface.
- The machine learning model is then trained based on these labels to determine three-dimensional bounding boxes or normal maps.
Key Features and Innovation
- Training a machine learning model to identify contact points and ground surface normal vectors using image and position data.
- Determining labels based on position data to train the model for accurate identification.
- Generating three-dimensional bounding boxes or normal maps for objects in images.
Potential Applications
This technology can be used in autonomous driving systems, robotics, and augmented reality applications.
Problems Solved
This technology addresses the challenge of accurately identifying contact points and ground surface normal vectors in images.
Benefits
- Improved accuracy in identifying object contact points and ground surface normal vectors.
- Enhanced performance of vehicle driving assistance systems.
Commercial Applications
- Autonomous vehicle technology
- Robotics industry
- Augmented reality applications
Prior Art
Readers can explore prior research in machine learning models for image processing and object detection to understand the background of this technology.
Frequently Updated Research
Stay updated on advancements in machine learning models for image processing and object detection to enhance the capabilities of this technology.
Questions about Vehicle Driving Assistance Systems
How does this technology improve the accuracy of object detection in images?
This technology utilizes machine learning models trained on image and position data to accurately identify contact points and ground surface normal vectors, leading to improved object detection in images.
What are the potential applications of this technology beyond vehicle driving assistance systems?
This technology can also be applied in robotics, augmented reality, and other fields requiring accurate object detection and identification.
Original Abstract Submitted
this disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. in a first aspect, a method is provided to train a machine learning model using image data and position data to identify contact points and ground surface normal vectors. image data is received that depicts an object, and position data for the object is also received, such as point cloud position information for various points along the object's exterior surface. two sets of labels may then be determined based on the position data, with one set identifying where the object contacts a ground surface and another identifying at least one normal vector for the ground surface. the machine learning model may then be trained based on both sets of labels to determine three-dimensional bounding boxes, normal maps, or combinations thereof. other aspects and features are also claimed and described.
