Denso Corporation

Denso International America, Inc.

Denso Corpora Tion

Ting-Yu Lai

Miki Sato

Bo Sun

Markos Gerges

Ryo Takaki

Systems, methods, and other embodiments described herein relate to generating depth estimates of an environment depicted in a monocular image. In one embodiment, a method includes identifying semantic features in the monocular image according to a semantic model. The method includes injecting the semantic features into a depth model using pixel-adaptive convolutions. The method includes generating a depth map from the monocular image using the depth model that is guided by the semantic features. The pixel-adaptive convolutions are integrated into a decoder of the depth model. The method includes providing the depth map as the depth estimates for the monocular image.

Systems and methods for adapting a driving assistance system according to the presence of a trailer

System, methods, and other embodiments described herein relate to adapting operation of an assistance system in a subject vehicle according to a presence of a trailer. In one embodiment, a method includes, in response to determining that the trailer causes an occlusion to perception of at least one sensor about a surrounding environment of the subject vehicle, modifying system parameters associated with the assistance system according to the occlusion to adapt how the assistance system operates while the occlusion is present. The method includes controlling the assistance system as a function of the system parameters to improve assistance provided to an occupant of the subject vehicle.

Systems and methods for adapting operation of an assistance system according to the presence of a trailer

System, methods, and other embodiments described herein relate to providing a warning from a subject vehicle to surrounding objects about a collision hazard. In one embodiment, a method includes identifying the surrounding objects of a subject vehicle according to sensor data about a surrounding environment of the subject vehicle. The method includes determining a collision probability indicating a likelihood of collision between a first object and a second object of the surrounding objects. The method includes, in response to the collision probability satisfying a collision threshold, communicating, by the subject vehicle, an alert to at least one of the surrounding objects about the collision hazard associated with the surrounding objects colliding.

Systems and methods for providing warnings to surrounding vehicles to avoid collisions

A vehicle system for estimating a trailer size may include a plurality of sensors arranged on a vehicle and may be configured to detect objects external to the vehicle and provide trailer data indicative of a trailer location behind a vehicle and a memory configured to maintain a virtual grid including a plurality of cells. The system may also include a controller in communication with the sensors and memory and configured to determine, based on the trailer data received within a predefined amount of time, an occupancy frequency for each of the plurality of cells, the occupancy frequency being an incrementation of each time an object was detected within the respective cell; determine a threshold distribution based on the occupancy frequency of each cell; and determine a trailer size based on the cells having an occupancy frequency exceeding the threshold distribution.

Method and system for trailer size estimating and monitoring

A vehicle sensor system for providing data for performance of vehicle features may include a plurality of sensors arranged on a vehicle, each sensor having a sensor profile, a memory configured to maintain the sensor profile, and a controller in communication with the plurality of sensors and memory and configured to receive data from each of the plurality of sensors in order at least one vehicle feature, detect a failure of a first sensor in which the first sensor fails to provide sensor data necessary to provide the vehicle feature, and use sensor data received from the second sensor to provide the vehicle feature in response to the sensor profile of the second sensor including a required attribute of the first sensor.

Multi-sensor management systems for ADAS

A toll road detection and notification system for a vehicle includes a plurality of cameras, a sign recognition unit, and a driver alert system. The plurality of cameras is configured to take images of a vehicle's environment. The sign recognition unit is configured to analyze the images from the plurality of cameras, detect a toll sign, and determine toll information. The driver alert system is configured to receive toll information from the sign recognition unit and notify a driver of the vehicle of the toll information.

Toll road detection and reporting system

Systems, methods, and apparatuses are provided and include a receiver module that is configured to receive at least one radar signal. A control module includes a processor that is configured to execute instruction stored in a nontransitory memory. The control module is configured to generate a Fourier transformation based on the at least one radar signal, and the control module is configured to determine a presence of wave interference based on the Fourier transformation. A primary indicator module is configured to, in response to the control module determining the presence of wave interference, generate an indication. The indication corresponds to the presence of wave interference.

Vehicle function impairment detection

A system and method are provided and include a blind spot monitoring system with a blind spot sensor that monitors a blind spot alert area of a subject vehicle and generates an alert when a secondary vehicle is detected within the blind spot alert area of the subject vehicle. A controller receives at least one of traffic sign data and GPS data, determines whether a current lane of the subject vehicle is merging or is going to merge with a second lane, and expands the blind spot alert area in response to determining that the current lane of the subject vehicle is merging or is going to merge with the second lane.

Methods and systems for blind spot monitoring with adaptive alert zone

A system and method are provided and include a blind spot monitoring system including a blind spot sensor that monitors a blind spot alert area of a subject vehicle and that generates an alert when a secondary vehicle is detected within the blind spot alert area of the subject vehicle. An object detection system detects an adjacent vehicle traveling in an adjacent lane to the subject vehicle. A controller determines whether the subject vehicle has passed the adjacent vehicle and that expands the blind spot alert area in response to determining that the subject vehicle has passed the adjacent vehicle.

A system and method are provided and include a blind spot monitoring system with a blind spot sensor that monitors a focus area within a blind spot detection area of a subject vehicle and that generates an alert when a secondary vehicle is detected within the focus area of the blind spot detection area. A controller receives data corresponding to an amount of traffic at a location of the subject vehicle, determines the level of traffic at the location of the subject vehicle based on the data, and reduces the focus area when the level of traffic is greater than a predetermined threshold.

Methods and systems for blind spot monitoring with dynamic detection range

A system and method are provided and include a rotatable blind spot sensor that monitors a blind spot detection area of a subject vehicle. The rotatable blind spot sensor generates first object data while positioned at a first angle and second object data while positioned at a second angle. A controller receives the first object data and the second object data and determines whether the object is a secondary vehicle located within a blind spot detection area of the subject vehicle. A driver alert system generates an alert in response to the controller determining that the object is the secondary vehicle located within the blind spot detection area of the subject vehicle.

Growing community of inventors

Ann Arbor, MI, United States of America

Ting-Yu Lai