Ambarella International LP

Ambarella, Inc.

Shimon Pertsel

Alexander Fink

Patrick Martin

Greg Hedman

Christopher N Day

Didier LeGall

Cheng-Yu Huang

Moshe Doron

Pier Paolo Porta

Udit Budhia

An apparatus comprising a plurality of capture devices and a processor. The plurality of capture devices may each be configured to generate a video signal in response to captured images. The processor may be configured to (i) receive the video signals from at least two of the capture devices, (ii) perform a video stitching operation on the video signals, (iii) generate a stitched video based on the video stitching operation and (iv) calculate image stabilization data for the stitched video based on (A) the stitched video signal and (B) motion information. Video data from one of the video signals is used to perform image stabilization for another of the video signals based on the image stabilization data.

Image stabilization for a multi-sensor camera

An apparatus includes a capture device and a processor. The capture device may be configured to generate pixel data corresponding to an exterior view from a vehicle. The processor may be configured to perform operations on video frames generated from the pixel data to detect a moving object in the video frames, determine a predicted path of the moving object, determine a probability of the moving object colliding with the vehicle based on the predicted path, determine whether the vehicle is stationary and generate a control signal if the vehicle is stationary and the probability is greater than a pre-determined threshold. The control signal may be configured to enable a response to alert a person in control of the moving object.

Automatic collision detection, warning, avoidance and prevention in parked cars

An apparatus comprising an interface and a processor. The interface may be configured to receive data about an interior of a vehicle. The processor may be configured to process the data, determine a number of occupants in the vehicle in response to an analysis of the data and generate a counter signal comprising the number of the occupants in the vehicle. The counter signal may be generated in a format compatible with a toll interface of a toll tag. The toll tag may be implemented in the vehicle. The toll tag may be configured to generate a readable occupant count in response to the counter signal. The readable occupant count may be configured to be scanned by an automatic roadway system.

Toll collection and carpool lane automation using in-vehicle computer vision and radar

An apparatus includes a capture device and a processor. The capture device may be configured to generate a plurality of video frames corresponding to users of a vehicle. The processor may be configured to perform operations to detect objects in the video frames, detect users of the vehicle based on the objects detected in the video frames, determine a comfort profile for the users and select a reaction to adjust vehicle components according to the comfort profile of the detected users. The comfort profile may be determined in response to characteristics of the users. The characteristics of the users may be determined by performing the operations on each of the users.

Determining comfort settings in vehicles using computer vision

An apparatus includes an interface and a processor. The interface may be configured to receive video frames comprising at least one of a vehicle or an outdoor environment near the vehicle and a correction signal. The processor may be configured to perform video operations on the video frames to detect objects, predict a state of the vehicle based on the objects detected in the video frames and generate the correction signal. The correction signal may be configured to apply a corrective measure based on the predicted state of the vehicle. The state of the vehicle may be predicted when the vehicle is parked in the outdoor environment. The state of the vehicle may comprise factors that prevent driving the vehicle.

Using camera data to manage a vehicle parked outside in cold climates

An apparatus including an interface and a processor. The interface may be configured to receive pixel data of an area external to a vehicle. The processor may be configured to generate video frames from the pixel data, perform computer vision operations on the video frames to detect objects in the video frames and determine characteristics of the objects, analyze the characteristics of the objects to determine a visually observable status of the objects, perform a comparison of the visually observable status to a remote command and send the remote command if the comparison determines that the visually observable status does not match the remote command. The remote command may be configured to control the visually observable status of the objects.

Vision based, in-vehicle, remote command assist

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data of an exterior environment of a vehicle. The processor may be configured to process the pixel data arranged as video frames, perform computer vision operations to detect objects in the video frames, extract characteristics about the objects detected, determine driving conditions in response to an analysis of the characteristics and generate a control signal. The control signal may be configured to perform a gear shift. The driving conditions may be used to predict a future drivetrain configuration of the vehicle. The gear shift may be performed if a comparison of the future drivetrain configuration with a current drivetrain configuration of the vehicle meets a threshold condition. The gear shift may not be performed if the comparison does not meet the threshold condition.

Efficient automatic gear shift using computer vision

An apparatus including a capture device and a processor. The capture device may be configured to generate pixel data corresponding to an exterior view from a vehicle. The processor may be configured to generate video frames from the pixel data, perform computer vision operations on the video frames to detect objects in the video frames and determine characteristics of the objects, detect a change in orientation of the vehicle at a first time, analyze the characteristics of the objects at a second time to determine a cause of the change in orientation of the vehicle and generate annotations for the video frames that comprise the objects determined to have caused the change in orientation of the vehicle. The second time may be earlier than the first time.

Generating training data for speed bump detection

An apparatus includes a capture device and a processor. The capture device may be configured to generate a plurality of video frames. The processor may be configured to perform operations to detect objects in the video frames, detect users based on the objects detected in the video frames, determine a comfort profile for the users and select a reaction to adjust vehicle components according to the comfort profile of the detected users. The comfort profile may be determined in response to characteristics of the users. The characteristics of the users may be determined by performing the operations on each of the users. The operations detect the objects by performing feature extraction based on weight values for each of a plurality of visual features that are associated with the objects extracted from the video frames. The weight values are determined by the processor analyzing training data prior to the feature extraction.

An apparatus including an interface and a processor. The interface may be configured to receive first video frames of a first field of view captured by a first capture device and second video frames of a second field of view captured by a second capture device. The first capture device and the second capture device may have a symmetrical orientation with respect to a vehicle. The fields of view may have an overlapping region. The processor may be configured to select the capture devices to operate as a stereo pair of cameras based on the symmetrical orientation, receive the video frames from the interface, detect an object located in the overlapping region, perform a comparison operation on the object based on the symmetrical orientation with respect to the video frames and determine a distance of the object from the vehicle in response to the comparison operation.

Oncoming car detection using lateral emirror cameras

An apparatus including cameras and a processor. The cameras may generate pixel data of an exterior view from a vehicle. The processor may generate video frames from each of the cameras, perform computer vision operations on the video frames to detect an object, determine a predicted path of the object with respect to the vehicle, predict an approach side of the vehicle of the object based on the predicted path, and generate a notification in response to the predicted path. A first of the cameras may be on the approach side of the vehicle. The object may not be in a field of view captured by the first camera. The object may be detected in the video frames captured by a second of the cameras that may not be on the approach side of the vehicle. The notification may be generated before the object may be in the field of view.

Using the image from a rear view camera in a three-camera electronic mirror system to provide early detection of on-coming cyclists in a bike lane

An apparatus comprising a sensor and a processor. The sensor may be configured to generate a first video signal based on a targeted view from a vehicle. The processor may be configured to (A) receive the first video signal, (B) generate a second video signal and (C) present the second video signal to a display. The second video signal presents a series of video frames configured to fit a shape of the display. The processor selects among a plurality of fields of view for the video frames based on a decision by the processor.

Electronic side-mirror with multiple fields of view

An apparatus includes a first capture device, a second capture device and a processor. The first capture device may generate a first plurality of video frames corresponding to an interior view of a vehicle. The second capture device may generate a second plurality of video frames corresponding to an area outside of the vehicle. The processor may be configured to perform operations to detect objects in the video frames, detect occupants of the vehicle based on the objects detected in the first video frames, determine whether a potential collision is unavoidable based on the objects detected in the second video frames and select a reaction if the potential collision is unavoidable. The reaction may be selected to protect occupants determined to be vulnerable based on characteristics of the occupants. The characteristics may be determined by performing the operations on each of the occupants.

Growing community of inventors

Mountain View, CA, United States of America

Shimon Pertsel