A system includes a camera having a field of view, a cleaning apparatus positioned to clean the camera, and a computer communicatively coupled to the camera and the cleaning apparatus. The computer is programmed to detect an obstruction on the camera based on sensing a trajectory of an external light source relative to the field of view in data from the camera, and upon detecting the obstruction, activate the cleaning apparatus.

The present disclosure relates to a method of generating a surround view of a vehicle platoon and a device thereof. A surround view generating device for a vehicle in the vehicle platoon acquires a local surround view of the vehicle and at least one of a truncated local surround view associated with one or more preceding vehicles and a truncated local surround view associated with one or more following vehicles in the vehicle platoon. Further, the surround view generation device generates a surround view of the vehicle platoon using the local surround view of the vehicle, the truncated local surround view associated with the one or more preceding vehicles, and the truncated local surround view associated with the one or more following vehicles. Finally, the surround view generating device navigates the vehicle in the vehicle platoon based on the surround view of the vehicle platoon.

A semiconductor device includes an image data acquisition circuit which acquires a plurality of first captured image data and a plurality of second captured image data at a first time and a second time, an adjustment region determination circuit which detects a target object from the plurality of first captured image data, and determines an adjustment region by estimating a position of the target object at the second time, a color adjustment circuit configured to determine a color adjustment gain based on the adjustment region, and perform color balance adjustment processing on the plurality of second captured image data based on the color adjustment gain, and an image synthesis circuit configured to synthesize the plurality of second captured image data so that overlapping regions included in a plurality of images of the plurality of second captured image data overlap each other.

A vehicular ground illumination light module includes at least one light emitting diode and a freeform optic disposed in front of the emitting diode. The vehicular ground illumination light module, when disposed at a side of a vehicle, and when the light emitting diode is electrically powered so as to emit light through the freeform optic, illuminates a ground region at that side of the vehicle. The illuminated ground region includes an illuminated side ground region at least partially along the side of the vehicle and an illuminated rearward ground region rearward of a rearmost portion of the vehicle. The illuminated ground region is at least in part within the fields of view of a sideward-viewing side camera and a rearward-viewing rear backup camera disposed at the vehicle. A portion of the illuminated side ground region is illuminated with a luminance of at least 10 lux.

Systems and methods to provide visual references to passengers in vehicles to prevent motion sickness. The system can include a controller and one or more projectors and/or displays. The controller can detect movement of a vehicle and project images within the vehicle that comport with the detected movement. The system can include a projector to project images on the interior of the vehicle. The system can include one or more displays to display images inside the vehicle. The controller can receive data from one or more cameras, accelerometers, navigation units, magnetometers, and other components to detect the motion of the vehicle. The system can display visual references on the dashboard, door panels, and other interior surfaces to complete the view of passengers, or provide other visual reference, to prevent motion sickness.

A controller is adapted to receive respective images from a sensors of a first vehicle. The images provide a gapless view along, and within a predetermined perpendicular distance away from, a side of the first vehicle. Movement of a second vehicle along, and within the predetermined perpendicular distance away from, the side of the first vehicle, is detected based on at least one of the images. A position of a front of the second vehicle is predicted based on the movement of the second vehicle. An image sequence is recorded at the position.

A method for self-supervised depth and ego-motion estimation is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes generating a self-occlusion mask by manually segmenting self-occluded areas of images captured by the multi-camera rig of the ego vehicle. The method further includes multiplying the multi-camera photometric loss with the self-occlusion mask to form a self-occlusion masked photometric loss. The method also includes training a depth estimation model and an ego-motion estimation model according to the self-occlusion masked photometric loss. The method further includes predicting a 360 point cloud of a scene surrounding the ego vehicle according to the depth estimation model and the ego-motion estimation model.

In mobile equipment that is configured for remote operation there are the competing interests of minimizing the number and complexity of cameras by using wide-angle cameras, while avoiding the fisheye distortion inherent in wide-angle cameras, which can be disorienting to remote operators. Thus, a method is disclosed that switches between video processing configurations depending on a machine state of the mobile equipment. For example, a first machine state may represent that the mobile equipment is immobile, whereas a second machine state may represent that the mobile equipment is mobile. In the first machine state, the video configuration does not correct for fisheye distortion, so as to maximize the field of view in the video while the mobile equipment is immobile. In the second machine state, the video configuration does correct for fisheye distortion, so as to prevent disorientation of the remote operator while the mobile equipment is mobile.

The invention provides an autonomous vehicle with a video camera that merges images taken a different light levels by replacing saturated parts of an image with corresponding parts of a lower-light image to stream a video with a dynamic range that extends to include very low-light and very intensely lit parts of a scene. The high dynamic range (HDR) camera streams the HDR video to a HDR system in real timeas the vehicle operates. As pixel values are provided by the camera's image sensors, those values are streamed directly through a pipeline processing operation and on to the HDR system without any requirement to wait and collect entire images, or frames, before using the video information.

Example implementations may relate to use of a light-control feature to control extent of light encountered by an image capture device of a self-driving vehicle. In particular, a computing system of the vehicle may make a determination that quality of image data generated by an image capture device is or is expected to be lower than a threshold quality due to external light encountered or expected to be encountered by the image capture device. In response to the determination, the computing system may make an adjustment to the light-control feature to control the extent of external light encountered or expected to be encountered by the image capture device. This adjustment may ultimately help improve quality of image data generated by the image capture device. As such, the computing system may operate the vehicle based at least on image data generated by the image capture device.