View source for 18071255. ADAPTIVE IMAGE CLASSIFICATION simplified abstract (GM Cruise Holdings LLC)

=ADAPTIVE IMAGE CLASSIFICATION=


==Organization Name==

[[:Category:GM Cruise Holdings LLC|GM Cruise Holdings LLC]]


[[Category:GM Cruise Holdings LLC]]

==Inventor(s)==

[[:Category:Victor Wang of San Diego CA (US)|Victor Wang of San Diego CA (US)]][[Category:Victor Wang of San Diego CA (US)]]

[[:Category:Yumin Shen of Fremont CA (US)|Yumin Shen of Fremont CA (US)]][[Category:Yumin Shen of Fremont CA (US)]]

[[:Category:Zayra Lobo of Sunnyvale CA (US)|Zayra Lobo of Sunnyvale CA (US)]][[Category:Zayra Lobo of Sunnyvale CA (US)]]

==ADAPTIVE IMAGE CLASSIFICATION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18071255 titled 'ADAPTIVE IMAGE CLASSIFICATION

==Simplified Explanation==

The patent application describes a technology for image classification using a two-stage classifier, trained by raw data captured by sensors associated with an autonomous vehicle (AV).

* The first stage of the classifier is trained using raw AV data captured at varying values of capture parameters.
* The second stage of the classifier consists of image calibration classifiers trained by second raw AV data at varying values of image calibration parameters.

== Potential Applications ==
This technology can be applied in various industries such as autonomous driving, surveillance, and image recognition systems.

== Problems Solved ==
1. Efficient image classification: The two-stage classifier improves the accuracy and efficiency of image classification tasks.
2. Adaptability to different environments: By training the classifier with varying sensor data, it can adapt to different environmental conditions.

== Benefits ==
1. Improved accuracy: The two-stage classifier enhances the accuracy of image classification by utilizing raw sensor data.
2. Faster processing: The technology allows for quick and efficient image classification, which is crucial in real-time applications.

== Potential Commercial Applications ==
"Image Classification Technology for Autonomous Vehicles" can be utilized in autonomous driving systems, security surveillance systems, and industrial automation processes.

== Possible Prior Art ==
One possible prior art could be the use of machine learning algorithms for image classification in autonomous vehicles. However, the specific approach of training a two-stage classifier using raw sensor data may be a novel aspect of this technology.

=== Unanswered Questions ===

=== How does this technology compare to existing image classification methods in terms of accuracy and efficiency? ===
This article does not provide a direct comparison with existing image classification methods, so it is unclear how this technology stacks up against current solutions.

=== What are the potential limitations or challenges of implementing this technology in real-world applications? ===
The article does not address any potential limitations or challenges that may arise when implementing this technology in practical scenarios.


==Original Abstract Submitted==

Aspects of the subject technology relate to systems, methods, and computer-readable media for image classification through a two-stage classifier. Raw image data of an image gathered by a sensor associated with an AV during operation of the AV is accessed. A first stage of a two-stage classifier is applied. The first stage is trained by first raw AV data captured at varying values of one or more capture parameters associated with one or more sensors of the AV in capturing the first raw AV data. A second stage of the two-stage classifier is applied to the raw image data to generate a final classification output. The second stage of the two-stage classifier if formed by a plurality of image calibration classifiers that are trained by second raw AV data at varying values of one or more image calibration parameters.



[[Category:G06V10/764]]
[[Category:G06V10/774]]
[[Category:G06V20/56]]