Worum es bei uns geht

Hi,
I have taken on a new role in my company that is focused on understanding different types of sensors (mainly Radar, LiDAR and Camera) and how they can work together to make autonomous driving better and safer in the future. Koito and North American Lighting (NAL) are industry leaders supplying exterior automotive lighting to OEMs worldwide. If you are interested in sharing ideas about sensors or have an idea you would like to develop please feel free to join. I will try and host these once a month. Refreshments and food will be provided.

Thank you and see you there!

Bevorstehende Events (1)

Challenges in Flash LiDar Data Processing:Harnessing image processing algorithms

Please join us for our next meetup taking place on Sept 25th at Plug and Play. 6-6:30pm - Networking 6:30-7:30pm - Technical Presentation 7:30-8pm - Networking Discussion topic: The autonomous driving era requires an accurate, real-time solution for depth map generation. These requirements push the current hardware to its limits. One of the leading solutions is based on a time of flight (TOF) camera, also known as flash LiDAR. To successfully integrate flash LiDar in automotive applications, several limitations must be addressed. For example, “infinity points” that exceed the maximum camera distance will appear as pure noise. In addition, due to the physics of the solution, depth maps may contain strong discontinuous artifacts, that should be detected and distinguished from the true depth signals. Finally, a robust and generic confidence value should be defined. In this talk, we will present a comprehensive review of these challenges. We will present some current state of the art methods for LiDar data processing. These algorithms include analytical and numerical methods to define the confidence of each pixel, providing insight into the depth map, and distinguishing between real distance values and erroneous ones. Classification of different noise types will also be discussed, as well as its usage to enhance the scene analysis. About the Speaker Moshe Safran is the CEO of RSIP Vision USA. He has for more than ten years served in various roles within RSIP Vision before rising to the role of VP of Research and Development in 2016, providing new ways for the company to solve complex AI technology challenges. In his new role as CEO of RSIP Vision USA, Moshe will take on the additional role of head of business development for the United States and Canada. Moshe is currently leading multiple RSIP teams simultaneously in multiple locations, while also overseeing customer communication, project management, providing professional guidance in algorithm development, planning, and execution of new projects, along with the recruitment, training and management of new employees. Moshe joined RSIP Vision in 2008 as an algorithm developer before serving almost eight years as the algorithm team leader and research scientist. At RSIP Vision he has led the implementation of a wide variety of computer vision projects, ranging from developing a patented algorithm for 3D reconstruction of heart chambers using parametric modeling, to semiconductor precise measurements, deep learning, microscopy, precise agriculture and more. As head of R&D and team leader Moshe has spearheaded and managed a fourfold growth of the RSIP algorithm development group. He earned his BSc degree in physics (Summa Cum Laude) from The Hebrew University of Jerusalem, after which he spent three years in a computational neuroscience Ph.D. program, researching the fly visual system and medical image processing.

Fotos (104)