Volkswagen Ag

Audi Ag

Porsche Ag

Dr. Ing. H.c. F. Porsche Aktiengesellschaft

Posrche Ag

Jerramy Lee Gipson

Lutz Junge

Edmund Dawes Zink

Douglas Allen Hauger

Nikhil J George

Anh Vu

Martin Hempel

Luis Marcial Hernandez Gonzalez

Allen Khorasani

Nils Kuepper

Joerg Christian Wolf

Stefan T Hilligardt

Qiang Liu

Philipp Nils Kuepper

Andreas Busse

Nils Küpper

A system, methodologies and components utilizing a random access scanning LiDAR sensor for object detection for use in autonomous and driver assisted transportation vehicles, wherein calculated expected potential range changes determined based on emission of range determining laser pulses are used to schedule subsequent emission of range determining laser pulses such that laser pulse generation and ray sample generation for individual rays with a larger expected potential range change is performed more frequently than laser pulse generation and ray sample generation for individual rays with a smaller expected potential change so as to provide compressive active range scanning.

System, method, and components providing compressive active range sampling

A system for point cloud data compression including a LiDAR sensor and a compression circuit. The compression circuit receives data for rays from the LiDAR sensor, wherein the data is arranged in cells which map to corresponding rays, and each cell includes a range value. The compression circuit constructs a frame for the received data and, for each cell, determines a velocity associated with the range value for the cell, determines whether to compress the frame with respect to the cell based upon the velocity; and selectively compresses the frame with respect to the cell accordingly. Also disclosed is a system including a device and a server which optionally are co-located. The device gathers data about an environment which is used to generate a point cloud.

System, method, and components utilizing live point cloud compression

Technologies and techniques for dynamic fixed pattern correction for an image sensor. A current image and a previous image received in the image sensor is stored and a bias and gain is computed for the current image, wherein the computing includes processing the current image together with a current local average value, the previous image, and a previous local average value. A gain correction value and a bias correction value is generated based on the computing, and the gain correction value and bias correction value are combined with the current image to generate a corrected image. A Bayer image is generated, based on the generated corrected image.

Fixed pattern correction for Bayer pattern imager under low light conditions

Approaches, techniques, and mechanisms are disclosed for range data compression. According to one embodiment, a current range data frame for a current time point is generated. Each current range data cell in the current range data frame includes current ranges representing points in a point cloud in a 3D space for the current time point. Accumulated prior ranges in an accumulated prior range buffer are propagated from a prior time point to the current time point. Current ranges in the current range data frame are compared with the propagated accumulated prior ranges to determine range differences between the current ranges and the propagated accumulated prior ranges. A proper subset of current ranges in the set of current ranges is identified based on the range difference. The proper subset of current ranges is included in a range data signal excluding other current ranges not in the proper subset.

Live point cloud compression with egomotion propagation

A system and method for safe decontamination of a vehicle cabin while passengers can be present are disclosed that uses and/or has at least one data storage, at least one processor, at least one infrared ('IR') sensor, and at least one ultraviolet (“UV”) emitter having a beam steering module. At least one contaminated area in the vehicle cabin is tracked using IR sensor data from the IR sensor. It is determined if there's a direct line of sight between the UV emitter and the at least one contaminated area. If so, UV emitter is activated to target the at least one contaminated area and blocking UV illumination on non-contaminated areas of the vehicle cabin and areas temporarily covered by a passenger.

In-vehicle decontamination

A system, components, and methodologies are provided for image data processing and subsequent use to detect and/or identify objects and object movement in such image data to enable assistance, automation, control and/or documentation regarding transportation vehicle movement. An affine contour filter provides the ability to extract precise sub-pixel roots of contours that represent boundaries of blobs in an image that undergoes small affine changes such as translation, rotation and scale. Thereby lateral contour tracking may be performed wherein movement of an object may be tracked within the field of view of a camera by aligning the contours associated with the object in space-time. As a result, the size and shape of the object to be tracked need not be specified ahead of time.

Object tracking using contour filters and scalers

A system and methodologies for neuromorphic (NM) vision simulate conventional analog NM system functionality and generate digital NM image data that facilitate improved object detection, classification, and tracking.

System and method for 1D root association providing sparsity guarantee in image data

A system and methodologies for neuromorphic vision simulate conventional analog NM system functionality and generate digital NM image data that facilitate improved object detection, classification, and tracking.

Vector engine and methodologies using digital neuromorphic (NM) data

Digital neuromorphic (NM) sensor array, detector, engine and methodologies

A system and methodologies for neuromorphic vision simulate conventional analog NM system functionality and generate digital NM image data that facilitate improved object detection, classification, and tracking so as to detect and predict movement of a vehicle occupant.

Growing community of inventors

Willits, CA, United States of America

Jerramy Lee Gipson