A car door opening pre-detection system for a car includes a first detecting module, a second detecting module and a control module. The first detecting module is installed within the car. The first detecting module issues a motion detecting signal according to a result of detecting a motion of a palm. The second detecting module is installed outside the car. When the car is stopped, the second detecting module is enabled to selectively provide a first detection range or a second detection range. The control unit judges whether a car door of the car is about to be opened according to the motion detecting signal. When the car is stopped and the control module judges that the car door is about to be opened, the second detecting module provides the second detection range to detect whether there is a moving object behind the car.

Example blind spot detection systems and methods are described. In one implementation, a primary vehicle detects a secondary vehicle ahead of the primary vehicle in an adjacent lane of traffic. A method determines dimensions of the secondary vehicle and estimates a vehicle class associated with the secondary vehicle based on the dimensions of the secondary vehicle. The method also identifies a side-view mirror location on the secondary vehicle and determines a blind spot associated with the secondary vehicle based on the vehicle class and the side-view mirror location.

A sensing system for a vehicle includes a first sensor at a forward portion of a side of the vehicle such that a principal axis of the first sensor's zone of sensing is rearward and sideward and at an angle relative to the body, and a second sensor at a rearward portion of the side of the vehicle such that a principal axis of the second sensor's zone of sensing is forward and sideward and at an angle relative to the body. Data sensed by the sensors when each sensor senses with at least two zones of sensing are communicated to a control, which determines the presence of one or more objects exterior the vehicle and within the zones of sensing of at least one of the sensors.

A RADAR system and associated methods are used to detect obstacles obscured from view when backing a trailer. An autonomous tractor is equipped with a rear facing RADAR device that has a field-of-view under the trailer and is configured to output RADAR returns from reflections. A controller of the tractor classifies RADAR returns from the RADAR device according to a number of reflections by a dock wall and a trailer face (e.g., a back end of the trailer) of a corresponding RADAR beam. The RADAR returns are correlated based on distance, and distance of a RADAR return from an obstacle is corrected based on the number of reflections. Advantageously, by processing RADAR returns from both direct and reflected RADAR beams, the controller is able to detect obstacles hidden behind the trailer and flag the obstacles as a hazard.

The invention relates to a method for detecting a screening of a sensor device (4) of a motor vehicle (1) by an object (8), in which at least one echo signal, captured by the sensor device (4), that characterizes a spacing between the sensor device (4) and the object (8) is received (S1) by means of a computing device (3), a capture region (E) for the sensor device (4) is determined, and on the basis of the at least one received echo signal it is checked whether the capture region (E) of the sensor device (4) is being screened by the object (8), at least in some regions, wherein the at least one echo signal is assigned by means of the computing device (3) to a discrete spacing value (B1, B2, B3) from a plurality of discrete spacing values (B1, B2, B3), for each of the discrete spacing values (B1, B2, B3) a power value (P) is determined (S2) on the basis of the echo signal, and on the basis of the power values (P) a decision is made by means of a classifier as to whether at least a predetermined proportion of the capture region (E) of the sensor device (4) is being screened (S6) by the object (8).

The disclosure relates to a driver assistance system for a motor vehicle, such as a truck. The driver assistance system includes an environment camera with an image sensor and an optical system. The driver assistance system also includes an imaging unit and a display element in the interior of the motor vehicle. The environment camera, the imaging unit, and the display element form a digital exterior mirror, where the digital exterior mirror is arranged such that at least two visual field regions, namely a first visual field region and a second visual field region, are mapped with different magnifications.

In an apparatus for monitoring an adjacent lane to a lane in which an own vehicle that is a vehicle carrying the apparatus is traveling, a travel trajectory calculation unit calculates a travel trajectory of the own vehicle based on odometry information of the own vehicle. An adjacent lane estimation unit estimates an adjacent-lane region based on the travel trajectory of the own vehicle. An other-vehicle determination unit determines whether or not a target (the other vehicle) is present in the adjacent lane based on a position of the target detected by an other-vehicle detector and the estimated adjacent-lane region.

A method and system for detecting an object in the “blind-spot” of a moving vehicle. The system can be user-installed to retrofit a vehicle, e.g., one that lacks a more complex, factory-installed blind-spot detection system. The invention thus provides an inexpensive and simplified vehicle safety enhancement.

A system for enhancing driver situation awareness and environment perception around a transportation vehicle. The system incorporates a plurality of object detecting sensors. The sensors are arranged for monitoring at least one critical zone around the vehicle. A plurality of addressable light-emitting diodes are operatively associated with the object detecting sensors. The addressable light-emitting diodes are located on the vehicle for visual display to the driver. When a given sensor detects an object in the critical zone, a detection signal is transmitted to a LED controller. Upon receiving the detection signal, the LED controller transmits a control signal to selectively activate only those addressable light-emitting diodes which are associated with the given sensor, such that the activated light-emitting diodes visually communicate to the driver a location of the detected object in the critical zone.

Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.