logo

For the Inventor, By the Inventor

Troy, MI, United States of America

Dalong Li

USPTO Granted Patents = 11 

Average Co-Inventor Count = 2.5

ph-index = 2

Forward Citations = 13(Granted Patents)


Company Filing History:

goldMedal11 out of 1,306 
 
Fca US LLC
 patents

Years Active: 2020-2025

Loading Chart...
11 patents (USPTO):Explore Patents
1. 12283112 - Automatic evaluation of three-dimensional vehicle perception using two-dimensional deep neural networks (2025-04-21),
2. 12198440 - Vehicle perception by adjusting deep neural network confidence valves based on k-means clustering (2025-01-14),
3. 11972612 - Techniques to automatically verify object detection, classification, and depth for automated driving systems (2024-04-30),
4. 11820393 - Functionally safe rationalization check for autonomous vehicle machine learning algorithms (2023-11-21),
5. 11702085 - Vehicle center of gravity height detection and vehicle mass detection using light detection and ranging point cloud data (2023-07-18),
6. 11594040 - Multiple resolution deep neural networks for vehicle autonomous driving systems (2023-02-28),
7. 11543531 - Semi-automatic LIDAR annotation system for autonomous driving (2023-01-03),
8. 11460544 - Traffic sign detection from filtered birdview projection of LIDAR point clouds (2022-10-04),
9. 10983215 - Tracking objects in LIDAR point clouds with enhanced template matching (2021-04-20),
10. 10929986 - Techniques for using a simple neural network model and standard camera for image detection in autonomous driving (2021-02-23),
11. 10823855 - Traffic recognition and adaptive ground removal based on LIDAR point cloud statistics (2020-11-03),

Title: The Innovative Contributions of Dalong Li

Introduction

Dalong Li is a prominent inventor based in Troy, MI (US), known for his significant contributions to vehicle perception technologies. With a total of 11 patents to his name, he has made remarkable strides in the field of deep neural networks and their applications in automotive systems.

Latest Patents

One of Dalong Li's latest patents is titled "Automatic evaluation of three-dimensional vehicle perception using two-dimensional deep neural networks." This invention focuses on enhancing vehicle perception techniques by applying a 3D deep neural network (DNN) to generate 3D detection results. The process involves transforming 3D objects into 2D bounding boxes and utilizing a 2D DNN to produce 2D detection results. By calculating mean average precision (mAP) values, the system identifies corner cases to improve the performance of the 3D DNN without relying on costly annotated training datasets.

Another notable patent is "Vehicle perception by adjusting deep neural network confidence values based on k-means clustering." This innovation involves obtaining a training dataset represented by histograms corresponding to training images. By applying K-means clustering, the system determines cluster centers and adjusts confidence scores based on distance ratios. This method enhances the accuracy of detected objects in input images, showcasing Dalong Li's commitment to advancing vehicle perception technologies.

Career Highlights

Dalong Li is currently employed at FCA US LLC, where he continues to develop innovative solutions in the automotive industry. His work focuses on integrating advanced deep learning techniques to improve vehicle safety and perception capabilities.

Collaborations

Throughout his career, Dalong Li has collaborated with notable colleagues, including Stephen W. Horton and Neil R. Garbacik. These partnerships have contributed to the successful development of cutting-edge technologies in the field.

Conclusion

Dalong Li's contributions to vehicle perception and deep neural networks exemplify his dedication to innovation in the automotive sector. His patents reflect a commitment to enhancing safety and efficiency in vehicle technologies, making him a significant figure in the industry.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…