View source for 20240087333.TECHNIQUES FOR IDENTIFYING OCCLUDED OBJECTS USING A NEURAL NETWORK simplified abstract (nvidia corporation)

=TECHNIQUES FOR IDENTIFYING OCCLUDED OBJECTS USING A NEURAL NETWORK=


==Organization Name==

[[:Category:nvidia corporation|nvidia corporation]]


[[Category:nvidia corporation]]

==Inventor(s)==

[[:Category:Siva Kumar Sastry Hari of Sunnyvale CA (US)|Siva Kumar Sastry Hari of Sunnyvale CA (US)]][[Category:Siva Kumar Sastry Hari of Sunnyvale CA (US)]]

[[:Category:Jason Lavar Clemons of Leander TX (US)|Jason Lavar Clemons of Leander TX (US)]][[Category:Jason Lavar Clemons of Leander TX (US)]]

[[:Category:Timothy Kohchih Tsai of Santa Clara CA (US)|Timothy Kohchih Tsai of Santa Clara CA (US)]][[Category:Timothy Kohchih Tsai of Santa Clara CA (US)]]

==TECHNIQUES FOR IDENTIFYING OCCLUDED OBJECTS USING A NEURAL NETWORK - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240087333 titled 'TECHNIQUES FOR IDENTIFYING OCCLUDED OBJECTS USING A NEURAL NETWORK

==Simplified Explanation==

The patent application describes techniques for detecting occluded objects within an environment using a neural network trained on training data and ground truth data.

* Training data representing images and ground truth data indicating whether the images are associated with occluded objects are used to train a neural network.
* The neural network is then used to detect occluded objects within an environment, such as while a vehicle is navigating, by processing sensor data and outputting data indicating the presence of occluded objects.
* The neural network may also output additional information associated with the occluded objects.

== Potential Applications ==
This technology could be applied in autonomous vehicles, surveillance systems, and robotics for improved object detection capabilities.

== Problems Solved ==
This technology addresses the challenge of detecting objects that are partially or fully obscured from view within an environment, enhancing safety and efficiency in various applications.

== Benefits ==
The use of neural networks for detecting occluded objects can improve situational awareness, reduce accidents, and enhance decision-making processes in real-time scenarios.

== Potential Commercial Applications ==
Commercial applications of this technology include autonomous driving systems, security systems, and industrial automation for enhanced object detection and recognition capabilities.

== Possible Prior Art ==
Prior art in the field of computer vision and object detection using neural networks may exist, but specific examples are not provided in this patent application.

=== What are the specific training data used to train the neural network in this technology? ===

The specific training data used to train the neural network are images representing occluded objects and ground truth data indicating whether the objects are occluded or not.

=== How does the neural network output additional information associated with the occluded objects? ===

The neural network outputs additional information associated with the occluded objects by analyzing the features of the objects and providing relevant data such as size, shape, and position within the environment.


==Original Abstract Submitted==

in various examples, techniques for detecting occluded objects within an environment are described. for instance, systems and methods may receive training data representing images and ground truth data indicating whether the images are associated with occluded objects or whether the images are not associated with occluded objects. the systems and methods may then train a neural network to detect occluded objects using the training data and the ground truth data. after training, the systems and methods may use the neural network to detect occluded objects within an environment. for instance, while a vehicle is navigating, the vehicle may process sensor data using the neural network. the neural network may then output data indicating whether an object is located within the environment and occluded from view of the vehicle. in some examples, the neural network may further output additional information associated with the occluded object.



[[Category:G06V20/58]]
[[Category:G06V10/774]]
[[Category:G06V10/776]]
[[Category:G06V10/82]]