Innoviz Technologies Ltd.

Guy Zohar

Nir Osiroff

Omer Keilaf

Amit Steinberg

Oren Buskila

Julian Vlaiko

Ronen Eshel

David Elooz

Oren Rosenzweig

Ovadya Menadeva

Sason Sourani

Moshe Medina

Amir Day

Yair Antman

Shahar Levy

Michael Girgel

Smadar David Raly

Yair Alpern

Alon Gan

Oded Yeruhami

Pavel Berman

Hanoch Kremer

Matityahu Shani

Matiyahu Shani

A system includes at least one processor configured to detect, based on point cloud information, portions of a particular object, and determine, based on the detected portions, at least a first portion having a first reflectivity corresponding to a license plate, and at least two additional spaced-apart portions corresponding to locations on the particular object other than a location of the first portion. The at least two additional portions have reflectivity substantially lower than the first reflectivity. The at least one processor is further configured to classify the particular object as a vehicle, based on a spatial relationship and a reflectivity relationship between the first portion and the at least two additional portions.

LIDAR systems and methods for detection and classification of objects

A vehicle-assistance system for classifying objects in a vehicle's surroundings. The system includes: at least one memory configured to store classification information for classifying a plurality of objects; and at least one processor configured to receive a plurality of detection results associated with light detection and ranging system (LIDAR) detection results, each detection result including location information, and further information indicative of at least two of the following detection characteristics: object surface reflectivity; temporal spreading of signal reflected from the object; object surface physical composition; ambient illumination measured at a LIDAR dead time; difference in detection information from a previous frame; and confidence level associated with another detection characteristic. The at least one processor is also configured to: access the classification information; and based on the classification information and the detection results, classify an object in the vehicle's surroundings.

A LIDAR system or a vehicle may include at least one processor configured to perform a method to detect objects in a field of view. The method may include controlling at least one LIDAR light source in a manner enabling light flux of the at least one LIDAR light source to vary over a plurality of scans of a field of view; receiving, from a group of detectors, a plurality of input signals indicative of reflections of light projected from the field of view; detecting a possible existence of an object in the background area based on first input signals associated with a first scanning cycle; detecting a possible existence of the object based on second input signals associated with a second scanning cycle; and aggregating the first and second input signals to detect an existence of the object at an object-existence-certainty level higher than a threshold.

Aggregating data over time to improve image quality

A LIDAR system for use in a vehicle is provided. The LIDAR system may include at least one processor configured to control at least one light source for illuminating a field of view and scan a field of view by controlling movement of at least one deflector at which the at least one light source is directed. The at least one processor may also be configured to receive, from at least one sensor, reflections signals indicative of light reflected from an object in the field of view. The at least one processor may further be configured to detect at least one temporal distortion in the reflections signals, and determine from the at least one temporal distortion an angular orientation of at least a portion of the object.

Detecting angles of objects

The present disclosure provides systems and methods that use LIDAR technology. In one implementation, a LIDAR system includes at least one processor configured to: control activation of at least one light source for illuminating a field of view; receive from at least one sensor a reflection signal associated with an object in the field of view, a time lapse between light leaving the at least one light source and reflection impinging on the least one sensor constituting a time of flight; and alter an amplification parameter associated with the at least one sensor during the time of flight.

Dynamically allocating detection elements to pixels in LIDAR systems

A vehicle-assistance system for classifying objects in a vehicle's surroundings is provided. The system may include at least one memory configured to store classification information for classifying a plurality of objects and at least one processor configured to receive, on a pixel-by-pixel basis, a plurality of measurements associated with LIDAR detection results. The measurements may include at least one of: a presence indication, a surface angle, object surface physical composition, and a reflectivity level. The at least one processor may also be configured to receive, on the pixel-by-pixel basis, at least one confidence level associated with each received measurement, and access the classification information. The at least one processor may further be configured to, based on the classification information and the received measurements with the at least one associated confidence level plurality, identify a of pixels as being associated with a particular object.

Classifying objects with additional measurements

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one deflector to deflect light from a plurality of light sources along a plurality of outbound paths, towards a plurality of regions forming a field of view while the at least one deflector is in a particular instantaneous position; control the at least one deflector such that while the at least one deflector is in the particular instantaneous position, light reflections from the field of view are received on at least one common area of the at least one deflector; and receive from each of a plurality of detectors, at least one signal indicative of light reflections from the at least one common area while the at least one deflector is in the particular instantaneous position.

Parallel scene scanning in LIDAR using a common steerable deflector

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light flux to vary over a scan of a field of view, the field of view including a first portion and a second portion; receive on a pixel-by-pixel basis, signals from at least one sensor; estimate noise in at least some of the signals associated with the first portion of the field of view; alter a sensor sensitivity for reflections associated with the first portion of the field of view; estimate noise in at least some of the signals associated with the second portion of the field of view; and alter a sensor sensitivity for reflections associated with the second portion of the field of view based on the estimation of noise in the second portion of the field of view.

Adaptive noise mitigation for different parts of the field of view

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light flux to vary over scans of a field of view using light from the at least one light source; control at least one light deflector to deflect light from the at least one light source; receive from at least one sensor, reflections signals indicative of light reflected from objects in the field of view; determine, based on the reflections signals of an initial light emission, whether an object is located in an immediate area of the LIDAR system and within a threshold distance from the at least one light deflector, and when no object is detected in the immediate area, control the at least one light source such that an additional light emission is projected toward the immediate area.

Adaptive lidar illumination techniques based on intermediate detection results

A LIDAR system for use in a vehicle may include at least one processor configured to control at least one light source in a manner enabling light flux of at least one light source to vary over scans of a field of view. The processor may also be configured to control at least one light deflector to deflect light from the at least one light source in order to scan the field of view. The processor may also be configured to receive input indicative of a current driving environment of the vehicle, and based on the current driving environment, coordinate the control of the at least one light source with the control of the at least one light deflector to dynamically adjust an instantaneous detection distance by varying an amount of light projected and a spatial light distribution of light across the scan of the field of view.

Dynamic mode of operation based on driving environment

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light flux of light from at least one light source to vary over a scanning cycle of a field of view; receive from at least one sensor reflections signals indicative of light reflected from objects in the field of view; coordinate light flux and scanning in a manner to cause at least three sectors of the field of view to occur in a scanning cycle, a first sector having a first light flux and an associated first detection range, a second sector having a second light flux and an associated second detection range, and a third sector having third light flux and an associated a third detection range; and detect an object in the second sector.

Steerable high energy beam

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: access an optical budget stored in memory, the optical budget being associated with at least one light source and defining an amount of light that is emittable in a predetermined time period by the at least one light source; receive information indicative of a platform condition for the LIDAR system; based on the received information, dynamically apportion the optical budget to a field of view of the LIDAR system based on at least two of: scanning rates, scanning patterns, scanning angles, spatial light distribution, and temporal light distribution; and output signals for controlling the at least one light source in a manner enabling light flux to vary over scanning of the field of view in accordance with the dynamically apportioned optical budget.

Optical budget apportionment in LIDAR

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light intensity to vary over a scan of a field of view using light from the at least one light source; control at least one light deflector to deflect light from the at least one light source; obtain an identification of at least one distinct region of interest in the field of view; and increase light allocation to the at least one distinct region of interest relative to other regions, such that following a first scanning cycle, light intensity in at least one subsequent second scanning cycle at locations associated with the at least one distinct region of interest is higher than light intensity in the first scanning cycle at the locations associated with the at least one distinct region of interest.

Variable flux allocation within a LIDAR FOV to improve detection in a region

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light flux to vary over a scan of a field of view; control projection of at least a first light emission directed toward a first portion of the field of view to determine an absence of objects in the first portion of the field of view at a first distance; when an absence of objects is determined in the first portion of the field of view, control projection of at least a second light emission directed toward the first portion of the field of view; and control projection of at least a third light emission directed toward the first portion of the field of view to determine an existence of an object in the first portion of the field of view.

Incremental flux allocation for LIDAR detection

A LIDAR system is provided. The LIDAR system comprises at least one processor configured to: control at least one light source in a manner enabling light flux to vary over a scan of a field of view using light from the at least one light source; control at least one light deflector to deflect light from the at least one light source; use first detected reflections associated with a scan of a first portion of the field of view to determine an existence of a first object in the first portion at a first distance; determine an absence of objects in a second portion of the field of view at the first distance; alter a light source parameter; and use second detected reflections in the second portion of the field of view to determine an existence of a second object at a second distance greater than the first distance.

Growing community of inventors

Netanya, Israel

Guy Zohar