A vehicle driving assist apparatus executes a vehicle collision prevention control when a target object distance from a vehicle to a target object is equal to or smaller than a predetermined distance. The apparatus acquires the target object distance on the basis of a position of the target object in a camera image taken by a camera and a height of the camera in a situation that a movable load of the vehicle is a maximum load capacity.

A system and method for detecting obstructions. The system includes a camera coupled to a vehicle and configured to capture image data from a vehicle, and a computing device that includes a processor configured to: detect an edge of a roadway on which the vehicle is traveling; detect objects located proximate an edge of the roadway, based on the captured image data; determine a location of each detected object, based on the captured image data; calculate a distance between each detected object and the edge of the roadway; determine that at least one object of the detected objects is an obstruction, based on at least the calculated distance between each object of the at least one object and the edge of the roadway being below a threshold; and transmit a message to an external device, said message indicating the location of each detected object determined to be an obstruction.

In an object detection apparatus and an object detection method, as first and second images, captured images of an area ahead of a vehicle in a vehicle advancing direction are acquired from first and second imaging units provided in the vehicle. Based on the first and second images, whether or not an object is present in a blind spot ahead of the vehicle in the vehicle advancing direction is determined. When the object is determined to be present in the blind spot, the first and second images are held in time series. As first and second image differences, differences in a feature quantity between a previous image and a current image in the first and second images are acquired. Based on the first and second image differences, whether or not the object is approaching the area ahead of the vehicle is determined.

The inventive subject matter provides devices and methods for improving driving safety using information obtained from images taken by a camera in a device. Among other things, contemplated devices and methods can produce alarms when it appear from rates of speed and acceleration/deceleration, that a vehicle will likely go through a red light, or fail to stop or sufficiently slow down at a stop sign. A significant feature of preferred devices and methods is that they are not dependent on WI-FI, cellular, satellite and radio signals, or any other external data transmission, and are not even dependent on speed, acceleration, or other information native to the vehicle.

Techniques for determining an output from a plurality of sensor modalities are discussed herein. Features from a radar sensor, a lidar sensor, and an image sensor may be input into respective models to determine respective intermediate outputs associated with a tracks associated with an object and associated confidence levels. The Intermediate outputs from a radar model, a lidar model, and an vision model may be input into a fused model to determine a fused confidence level and fused output associated with the track. The fused confidence level and the individual confidence levels are compared to a threshold to generate the track to transmit to a planning system or prediction system of an autonomous vehicle. Additionally, a vehicle controller can control the autonomous vehicle based on the track and/or on the confidence level(s).

A disparity mapping system for an autonomous vehicle can include a stereoscopic camera which acquires a first image and a second image of a scene. The system generates baseline disparity data from a location and orientation of the stereoscopic camera and three-dimensional environment data for the environment around the camera. Using the first image, second image, and baseline disparity data, the system can then generate a disparity map for the scene.

Example embodiments relate to techniques for enabling one or more systems of a vehicle (e.g., an autonomous vehicle) to request remote assistance to help the vehicle navigate in an environment. A computing device may be configured to receive a request for assistance from a vehicle. The request may include an image frame representative of a portion of an environment. The computing device may also be configured to initiate display of a graphical user interface to visually represent the image frame. Further, the computing device may determine a bounding region for the image frame. The bounding region may be associated with one or more objects in the image frame. Additionally, the computing device may be configured to receive, via the GUI, an input that includes an object identifier, and associate the object identifier with each of the one or more objects in the bounding region.

A method of operating a mobile robot for transporting an article in a manufacturing facility, the mobile robot, and an article transport system including the same are proposed. The method of operating the mobile robot includes obtaining a 3-D depth image, extracting, from the 3-D depth image, a region of interest corresponding to a traveling path of the mobile robot on a bottom surface of the manufacturing facility, generating a projected point cloud by projecting an object detected from the region of interest on a reference plane corresponding to the bottom surface, generating an imaginary point cloud filled with voxels in the reference plane, detecting a hole existing in the bottom surface by comparing the imaginary point cloud to the projected point cloud, and travelling while avoiding the hole.

A method, apparatus and computer program product are provided for improving localization of a device. In this regard, a coarse location of the device is determined and a neural network is utilized to determine one or more image-based vectors from the device to respective features in an image captured by an image capture device associated with the device. At one or more location points defined relative to the coarse location of the device, (a) one or more map-based vectors extending from a respective location point to respective features as defined by map data are compared to (b) the one or more image-based vectors. Based on the comparison, a refined location of the device is determined. A method, apparatus and computer program are also provided for training the neural network to determine an image-based vector from the device to a feature in an image captured by the device.

A tracking device includes a processor configured to detect regions each having a confidence score, which indicates how likely a predetermined object is represented, not less than a predetermined detection threshold as candidate regions, determine whether one of the candidate regions can be associated with the predetermined object, based on optical flow between an object region representing the predetermined object in a past image earlier than the image and each candidate region, increment a tracking count of the object by one when the association can be made, set the detection threshold applied to a subsequent image later than the image at a first value when the tracking count is not greater than a predetermined number, and set the detection threshold applied to the subsequent image at a second value lower than the first value when the tracking count is greater than the predetermined number.