NVIDIA Corporation (20240282118). OBJECT DETECTION USING POLYGONS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS simplified abstract
Contents
OBJECT DETECTION USING POLYGONS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Organization Name
Inventor(s)
Yang Zheng of Thousand Oak CA (US)
Trung Pham of Santa Clara CA (US)
Minwoo Park of Saratoga CA (US)
OBJECT DETECTION USING POLYGONS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240282118 titled 'OBJECT DETECTION USING POLYGONS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
- Simplified Explanation:**
The patent application discusses the use of object detectors to regress bounding polygons for detected objects in systems that require object awareness, identification, avoidance, and localization. The object detector determines regression data to represent regressed polygons associated with detected objects and generates bounding shapes based on this data.
- Key Features and Innovation:**
- Object detectors regress bounding polygons for detected objects.
- Regression data includes regressed angles and lengths of vectors for different vertices of the regressed polygon.
- Bounding shapes are generated for detected objects based on regression data.
- Object detector can be trained by deforming a regressed polygon to match a ground truth polygon.
- Potential Applications:**
This technology can be applied in autonomous or semi-autonomous driving systems, surveillance systems, robotics, and other applications requiring object detection and localization.
- Problems Solved:**
This technology addresses the need for accurate object detection, identification, avoidance, and localization in various systems.
- Benefits:**
- Improved object awareness and identification.
- Enhanced object avoidance capabilities.
- Accurate object localization.
- Training efficiency through polygon deformation.
- Commercial Applications:**
Title: Advanced Object Detection and Localization Technology This technology can be utilized in the automotive industry for autonomous driving systems, in security systems for surveillance purposes, in robotics for object manipulation, and in various industries requiring precise object detection and localization.
- Prior Art:**
Prior art related to this technology may include research papers, patents, and publications on object detection, regression algorithms, and training methodologies for object detectors.
- Frequently Updated Research:**
Researchers are constantly working on improving object detection algorithms, regression techniques, and training methods for object detectors to enhance accuracy and efficiency.
- Questions about Object Detection and Localization:**
1. How does this technology improve object detection accuracy compared to traditional methods? 2. What are the potential challenges in implementing this technology in real-world applications?
Original Abstract Submitted
in various examples, one or more object detectors may regress bounding polygons for detected objects in systems (e.g., autonomous or semi-autonomous driving systems and applications) that provide object awareness, object identification, object avoidance, and/or object localization. the object detector may determine regression data representing a regressed polygon associated with a given shape of a detected object represented by classification data determined from a scene. the object detector may determine regression data for different regressed angles between different pairs of successive vertices of the regressed polygon and regressed lengths of vectors from a regressed geometric center of the regressed polygon to vertices of the regressed polygon. the object detector may generate, based at least in part on the regression data, a bounding shape for a detected object in the scene. in some embodiments, the object detector may be trained by deforming a regressed polygon to match a ground truth polygon.
