Immervision, Inc.

6115187 Canada, Inc.

Pascale Nini

Jocelyn Parent

Pierre Konen

Patrice Roulet

Simon Thibault

Xiaojun Du

Valentin Bataille

Jhinseok Lee

Hu Zhang

Xavier Dallaire

Marie-Eve Gosselin

Alessandro Gasparini

Viacheslav Natashyn

Julie Buquet

Valentin Batalle

A stereoscopic vision system uses at least two cameras having different parameters to image a scene and create stereoscopic views. The different parameters of the two cameras can be intrinsic or extrinsic, including, for example, the distortion profile of the lens in the cameras, the field of view of the lens, the orientation of the cameras, the positions of the cameras, the color spectrum of the cameras, the frame rate of the cameras, the exposure time of the cameras, the gain of the cameras, the aperture size of the lenses, or the like. An image processing apparatus is then used to process the images from the at least two different cameras to provide optimal stereoscopic vision to a display.

Wide-angle stereoscopic vision with cameras having different parameters

A miniature wide-angle imaging lens has a miniaturization ratio, of a total track length from the center of a first surface to a focal plane by an image circle diameter, with a value less than 3.0. The imaging lens includes, starting from an object side of the lens, a first group of at least three optical elements, a second group including an aperture stop and an optical element immediately in front of or behind the aperture stop, and a third group of at least two optical elements.

Miniature wide-angle imaging lens

A method for training and using a convolutional neural network with images having on-purpose distortion is disclosed. By distorting on-purpose the image to create zone of interest with higher number of pixels, the resulting output from the neural network is improved. The distorted images are created using an imager device either comprising an optical system specifically designed to output distorted images or comprising software or hardware image distortion manipulation algorithm to create the distorted images from normal images. Also described is a method for training the neural network using a distorted image generator from various existing datasets.

Using imager with on-purpose controlled distortion for inference or training of an artificial intelligence neural network

An optical apparatus captures images of a wide-angle scene with a single camera having a continuous panomorph zoom distortion profile. When combined with a processing unit, the hybrid zoom system creates an output image with constant resolution while allowing continuous adjustment in the magnification and field of view of the image without interpolation like a digital zoom system or without any moving parts like an optical zoom system.

Constant resolution continuous hybrid zoom system

Systems and methods in accordance with the invention allow automatic recording, sharing, and communicating of different parameters associated with images and their imager to define a specific system behavior of a display device or an algorithm unit. Examples of information include imager parameters, environment parameters, image processing and enhancement parameters, coordinates of a section of wide-angle scene image content, display parameters, defined user experience, defined system behavior or any information to be recorded, shared, and communicated. To avoid loss of information, the information is encoded directly in the picture using a marker. This way, the information is robustly transferred from the imager to the display unit. According to the information, the final image can be automatically corrected and enhanced before display, different associated parameters can be displayed on final image or be used with another output. The end user experience or system behavior can thus be defined and be reproduced.

Automated definition of system behavior or user experience by recording, sharing, and processing information associated with wide-angle image

The present invention is a system for assembling panoramic images of a scene captured by a panoramic image capture device having a decoding unit configured to read image content data from the image capture device, an information reading unit configured to extract device parameters about the capture device, and an image processing unit configured to assemble an output image using the image content data and the device parameters.

Method to capture, store, distribute, share, stream and display panoramic image or video

Automated identification of panoramic imagers for appropriate and efficient panoramic image distortion processing system

An image distortion transformation method for transforming an original image by an imager having an original distortion profile to a transformed image optimized for a distortion processing unit includes inputting the original image from the imager into the transformation unit, inputting an original image distortion profile into the original distortion profile memory of the transformation unit, and inputting a target distortion profile into the target distortion profile memory of the transformation unit. The target distortion profile is different from the original distortion profile. The method further includes transforming the original image into a transformed image by transforming the distortion profile of the original image from the original image distortion profile to the target image distortion profile, and outputting the transformed image from the transformation unit.

Image distortion transformation method and apparatus

The present invention is a system for capturing and assembling panoramic image data having a panoramic image capture device with image assembly parameters and configured to capture image content data, an encoding device coupled to the panoramic image capture device and configured to combine the image content data and the image assembly parameters into a panoramic image file, and a decoding device configured to receive the panoramic image file and assemble, based on the image assembly parameters, at least a portion of the image content data into an output image.

The present invention relate to an optical apparatus to capture images of a wide-angle scene with a single camera having a continuous panomorph zoom distortion profile. When combined with a processing unit, the hybrid zoom system creates an output image with constant resolution while allowing continuous adjustment in the magnification and field of view of the image without interpolation like a digital zoom system or without any moving parts like an optical zoom system.

Growing community of inventors

Montreal, Canada

Pascale Nini