Inuitive Ltd.

Ady Ecker

Niv Shmueli

Mishel Ivgi

Idan Ram

A method for use in a stereoscopic image generating system, wherein the image generating system comprises a hardware module associated with at least one pair of image capturing devices, at least one memory means and at least one processor, wherein information retrieved from the capturing devices is processed by the at least one processor, which is configured to implement a hardware module stereo algorithm for identifying objects included in the captured scene at a distance that is equal to or greater than a minimal distance defined by the geometry and disparity range of said hardware module, and wherein the at least one processor is further configured to implement a software stereo algorithm adapted to identify objects included in the captured scene at a distance that is less than the minimal distance required for detecting objects by the hardware module stereo algorithm.

Detection of objects located closer than a minimal distance of hardware stereo systems

A method is described for processing data retrieved from two image capturing sensors, by filling missing disparity values of pixels included in holes comprised in the retrieved data. The method comprises: retrieving data by the two image capturing sensors, wherein the retrieved data includes data that relates to at least one pixel for which no disparity related information is provided; arranging the retrieved data in a form of a raster that comprises a plurality of disparity values representing the retrieved data, arranged in rows and columns; identifying boundary pixels included in the retrieved data, wherein the boundary pixels are pixels adjacent to the pixel for which no information is provided; determining which of the holes, should be filled; inserting disparity values of the boundary pixels surrounding holes that should be filled, into a queue implemented in a linear array; repeatedly extracting a pixel from the queue, obtaining its disparity value by interpolating disparity values of its adjacent and remote neighbors, and inserting all its adjacent neighboring pixels for which no disparity values have been provided, into the queue; and adding to the data retrieved, disparity values for all pixels having originally missing values.

Method for filling missing disparity values of pixels comprised in an image

A system configured to operate in an unknown, possibly texture-less environment, with possibly self-similar surfaces, and comprising a plurality of platforms configured to operate as mobile platforms, where each of these platforms comprises an optical depth sensor, and one platform operates as a static platform and comprising at least one optical projector. Upon operating the system, the static platform projects a pattern onto the environment, wherein each of the mobile platforms detects the pattern or a part thereof by its respective optical depth sensor while moving, and wherein information obtained by the optical depth sensors, is used to determine moving instructions for mobile platforms within that environment. Optionally, the system operates so that every time period another mobile platform from among the plurality of platforms, takes the role of operating as the static platform, while the preceding platform returns to operate as a mobile platform.

Self-localizing system operative in an unknown environment

A method and apparatus for generating a three-dimensional depth map, are provided. The method comprising the steps of: (i) illuminating a target by a pattern projector having background intensity or by a combination of a pattern projector which does not have a background intensity operative together with a flood projector; (ii) capturing at least one image that comprises one or more objects present at the illuminated target; (iii) converting the at least one captured image into data; (iv) processing the data received from the conversion of the at least one captured image while filtering out the projected pattern from the processed data; (v) detecting edges of at least one of the one or more objects present at the illuminated target; and (vi) generating a three-dimensional depth map that comprises the at least one of the one or more objects whose edges have been determined.

Method and apparatus for detecting edges in active stereo images

An optical passive stereo assembly for generating a three-dimensional image, the optical assembly comprising: two image capturing devices each mounted within the optical passive stereo assembly in a skewed position to the other with respect to the horizontal plane; a processor configured to: process data retrieved from a plurality of pixels comprised within images captured by the two image capturing devices, and generate a point cloud, being a set of data points in a 3D space retrieved from the tilted coordinate system (X', Y&#x2032;, Z&#x2032;); apply a 2D rotation in the X-Y plane to the point cloud, thereby converting the coordinate system of the resulting point cloud to a conventional cartesian coordinate system (X, Y, Z), to enable generating the three-dimensional image.

Growing community of inventors

Ness Ziona, Israel

Ady Ecker