A method for object detection includes: obtaining a plurality of to-be-determined targets in a to-be-detected image; determining confidences of the plurality of to-be-determined targets separately belonging to at least one category, determining categories of the plurality of to-be-determined targets according to the confidences, and determining position offset values corresponding to the respective categories of the plurality of to-be-determined targets; using the position offset values corresponding to the respective categories of the plurality of to-be-determined targets as position offset values of the plurality of to-be-determined targets; and determining position information and a category of at least one to-be-determined target in the to-be-detected image according to the categories of the plurality of to-be-determined targets, the position offset values of the plurality of to-be-determined targets, and the confidences of the plurality of to-be-determined targets belonging to the categories thereof.

The present invention relates to a method for determining a location of an object, the method comprising processing image data to determine a direction between a camera capturing an image and the object; processing additional data comprising at least one of map data and velocity sensor data; and combining information based on the image data and the additional data to arrive at a location of the object. The present invention also relates to a corresponding robot configured to carry out such a method.

A method for estimating distance to an object via a vehicular vision system includes disposing a camera at a vehicle so as to view at least exterior of the vehicle. An ECU is provided that includes an image processor. Multiple frames of image data are captured via the camera while the vehicle is moving, and are provided to the ECU. The provided captured frames of image data are processed to determine a three dimensional object present in a field of view of the camera, and a point of interest is determined on the determined object. An estimated location in three dimensional space of the determined point of interest relative to the vehicle is determined, and distance to the estimated location is estimated by comparing provided captured frames of image data where there is movement of the determined point of interest of the determined object relative to the camera.

A map points-of-change detection device includes: a camera capturing an image of an area around a vehicle; a bird's-eye-view transformation section transforming the image into a bird's-eye view image; a map storage portion storing a road map including a road surface map; a collation processing section determining whether a point of change in the road surface map exits, the point of change being a position at which a change has occurred on an actual road surface; and a collation region identification section that determines a region for collation in a width direction of the vehicle from the bird's-eye view image.

Systems and methods for navigating a host vehicle. The system may perform operations comprising receiving, from an image capture device, a plurality of images representative of an environment of the host vehicle; analyzing at least one of the plurality of images to identify a first object in the environment of the vehicle, wherein the first object and a road on which the first object is located are at least partially obscured by a second object in the environment of the vehicle; determining scale change information for the first object based on at least two of the plurality of images; determining, based on the determined scale change information for the first object, a lane position of the first object relative to a lane of the road on which the first object is located; and determining a navigational action for the host vehicle based on the determined lane position.

A method for driving a first vehicle based on information received from a second vehicle, the method may include receiving, by the first vehicle, acquired image information regarding (a) a signature of an acquired image that was acquired by the second vehicle, (b) a location of acquisition of the acquired image; extracting, from the acquired image information, information about objects within the acquired image; and preforming a driving related operation of the first vehicle based on the information about objects within the acquired image.

In various examples, lane location criteria and object class criteria may be used to determine a set of objects in an environment to track. For example, lane information, freespace information, and/or object detection information may be used to filter out or discard non-essential objects (e.g., objects that are not in an ego-lane or adjacent lanes) from objects detected using an object detection algorithm. Further, objects corresponding to non-essential object classes may be filtered out to generate a final filtered set of objects to be tracked that may be of a lower quantity than the actual number of detected objects. As a result, object tracking may only be executed on the final filtered set of objects, thereby decreasing compute requirements and runtime of the system without sacrificing object tracking accuracy and reliability with respect to more pertinent objects.

A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.

A method for classifying objects on a roadway in surroundings of a vehicle. The method includes: reading in image data from a vehicle camera of the vehicle. The image data represent an area of the surroundings which includes the roadway; evaluating the image data including generating a model of a surface of the roadway using identified roadway markings, and an object on the roadway being identified; ascertaining first distance values between the vehicle camera and object image points of the object represented by the image data, and second distance values between the vehicle camera and roadway image points, defined by the model, of the surface of the roadway in surroundings of the object; and comparing the distance values to at least one continuity criterion for distinguishing raised objects from flat objects to classify the object as a raised or flat object as a function of a result of the comparison.

A vehicle, system and method of detecting an object. The system includes an image network, a radar network and a head. The image network receives image data and proposes a boundary box from the image data and an object proposal. The radar network receives radar data and the boundary box and generates a fused set of data including the radar data and the image data. The head determines a parameter of the object from the object proposal and the fused set of data.