Company Filing History:
Years Active: 2010-2025
Title: Rohit S Paranjpe: Innovator in Vehicle Perception Technologies
Introduction
Rohit S Paranjpe is a prominent inventor based in Rochester Hills, MI (US). He has made significant contributions to the field of vehicle perception technologies, holding a total of 5 patents. His innovative work focuses on enhancing the capabilities of deep neural networks in understanding and interpreting three-dimensional vehicle environments.
Latest Patents
One of his latest patents is titled "Automatic evaluation of three-dimensional vehicle perception using two-dimensional deep neural networks." This invention involves applying a 3D deep neural network (DNN) to a set of inputs to generate 3D detection results, transforming these results into 2D bounding boxes, and utilizing a 2D DNN to produce 2D detection results. The process includes calculating mean average precision (mAP) values to identify corner cases, ultimately improving the performance of the 3D DNN without the need for costly annotated training datasets.
Another notable patent is "Vehicle perception by adjusting deep neural network confidence values based on k-means clustering." This invention describes a method of obtaining a training dataset represented by histograms, clustering these histograms to determine cluster centers, and applying a DNN to classify objects in input images. The confidence scores from the DNN are adjusted based on distance ratios to enhance the accuracy of vehicle perception.
Career Highlights
Rohit has worked with several notable companies, including FCA US LLC and GM Global Technology Operations, Inc. His experience in these organizations has allowed him to develop and refine his innovative ideas in vehicle perception technologies.
Collaborations
Throughout his career, Rohit has collaborated with talented individuals such as Dalong Li and Fanghui Shi. These partnerships have contributed to the advancement of his research and the successful development of his patents.
Conclusion
Rohit S Paranjpe is a distinguished inventor whose work in vehicle perception technologies has led to significant advancements in the field. His innovative patents demonstrate his commitment to improving the capabilities of deep neural networks in understanding complex environments.