Nvidia corporation (20240192320). OBJECT DETECTION AND DETECTION CONFIDENCE SUITABLE FOR AUTONOMOUS DRIVING simplified abstract

OBJECT DETECTION AND DETECTION CONFIDENCE SUITABLE FOR AUTONOMOUS DRIVING

Organization Name

nvidia corporation

Inventor(s)

Tommi Koivisto of Uusimaa (FI)

Pekka Janis of Uusimaa (FI)

Tero Kuosmanen of Uusimaa (FI)

Timo Roman of Uusimaa (FI)

Sriya Sarathy of Santa Clara CA (US)

William Zhang of Los Altos CA (US)

Nizar Assaf of Santa Clara CA (US)

Colin Tracey of Santa Clara CA (US)

OBJECT DETECTION AND DETECTION CONFIDENCE SUITABLE FOR AUTONOMOUS DRIVING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240192320 titled 'OBJECT DETECTION AND DETECTION CONFIDENCE SUITABLE FOR AUTONOMOUS DRIVING

• • Simplified Explanation:**

The patent application discusses a method for determining object data in a field of view, generating clusters of detected objects, and using machine learning models to compute confidence scores for the clusters.

• • Key Features and Innovation:**
• Determining object data representative of locations of detected objects in a field of view.
• Generating clusters of detected objects based on locations and features.
• Using features of clusters as inputs to machine learning models.
• Receiving confidence scores from machine learning models based on inputs.
• Determining ground truth data for training object detectors.

• • Potential Applications:**

This technology can be applied in various fields such as surveillance, autonomous vehicles, robotics, and image recognition systems.

• • Problems Solved:**

The technology addresses the challenges of accurately detecting and classifying objects in a field of view, as well as providing ground truth data for training object detectors.

• • Benefits:**
• Improved accuracy in detecting and classifying objects.
• Efficient training of object detectors using ground truth data.
• Enhanced performance of machine learning models in object recognition tasks.

• • Commercial Applications:**

Potential commercial uses include security systems, traffic management, industrial automation, and retail analytics. The technology can have significant market implications in improving efficiency and accuracy in various industries.

• • Prior Art:**

Prior art related to this technology may include research papers, patents, and academic studies on object detection, clustering algorithms, and machine learning models for image recognition tasks.

• • Frequently Updated Research:**

Researchers are constantly exploring new algorithms and techniques to enhance object detection and clustering in computer vision applications. Stay updated on advancements in machine learning models and image processing techniques for improved object recognition.

• • Questions about Object Detection Technology:**

1. What are the key challenges in object detection technology? 2. How does this technology improve the accuracy of object detection in various applications?

Original Abstract Submitted

in various examples, detected object data representative of locations of detected objects in a field of view may be determined. one or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). a confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.