17956518. OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING simplified abstract (Robert Bosch GmbH)
Contents
- 1 OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING - 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
OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING
Organization Name
Inventor(s)
Wenhao Ding of Pittsburgh PA (US)
Ji Eun Kim of Pittsburgh PA (US)
Kevin H. Huang of Pittsburgh PA (US)
Alessandro Oltramari of Pittsburgh PA (US)
OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17956518 titled 'OBJECT TRAJECTORY CLUSTERING WITH HYBRID REASONING FOR MACHINE LEARNING
Simplified Explanation
The patent application describes methods and systems for building a knowledge graph based on event-based ontology of a scene and vehicle trajectory in the scene. Image data and event-based ontology data are received, and a machine-learning model is used to determine the presence of vehicles and their trajectories, which are then clustered to augment the knowledge graph.
- Image data and event-based ontology data are received
- Presence of vehicles and their trajectories are determined using a machine-learning model
- Vehicle trajectories are clustered using a clustering model
- Knowledge graph is augmented based on clustered vehicle trajectories and event-based ontology
Potential Applications
The technology described in the patent application could be applied in various fields such as traffic management, surveillance systems, autonomous vehicles, and smart city infrastructure.
Problems Solved
This technology helps in efficiently analyzing and understanding vehicle movements in a scene, enabling better decision-making in areas such as traffic flow optimization, accident prevention, and security monitoring.
Benefits
Some of the benefits of this technology include improved traffic management, enhanced surveillance capabilities, increased safety on roads, and better utilization of smart city infrastructure.
Potential Commercial Applications
The technology could be commercially applied in industries such as transportation, security, urban planning, and automotive for developing advanced systems for traffic control, surveillance, and autonomous driving.
Possible Prior Art
One possible prior art could be the use of object tracking and clustering techniques in computer vision and machine learning for analyzing vehicle trajectories in a scene.
Unanswered Questions
How does the system handle occlusions in the scene when tracking vehicles?
The patent application does not provide specific details on how the system deals with occlusions in the scene that may obstruct the view of vehicles.
What is the computational complexity of clustering vehicle trajectories in real-time scenarios?
The patent application does not mention the computational complexity of clustering vehicle trajectories, especially in real-time scenarios where efficiency is crucial.
Original Abstract Submitted
Methods and systems of building a knowledge graph based on event-based ontology of a scene and vehicle trajectory in the scene. Image data corresponding to a plurality of scenes captured by one or more cameras is received. Event-based ontology data corresponding to events occurring in the plurality of scenes is received. Via an object-tracking machine-learning model, the system determines (i) a presence of a plurality of vehicles in the image data, and (ii) a plurality of vehicle trajectories, each vehicle trajectory associated with a respective one of the vehicles. Using a clustering model, the vehicle trajectories are clustered. A knowledge graph is augmented based on the clustered vehicle trajectories and the event-based ontology.
