An apparatus for locating an object of interest using offset. The object may be a mobile platform, or portion of same, associated with a vehicle, or a pavement segment or feature of or on a pavement segment on which the mobile platform is located. The vehicle includes first and second fixed points having a known offset from each other. An image sensor whose field of view includes the second fixed point and a segment of the pavement surface provides image data which is used with the known offset to calculate the precise location of the object of interest.

A system and method for determining a viewpoint of a traffic camera includes obtaining images of a real road captured by the traffic camera, segmenting a road surface from the captured images to generate a mask of the real road, generating a 3D model of a simulated road corresponding to the real road, from geographical data of the real road, adding a simulated camera corresponding to the traffic camera to a location in the 3D model that is corresponding to a location of the traffic camera in the real road, generating a plurality of simulated images of the simulated road using the 3D model, each corresponding to a set of viewpoint parameters of the simulated traffic camera, selecting the simulated image that provides the best fit between the simulated image and the mask, and generating mapping between pixel locations in the captured images and locations on the real road.

A target tracking method includes: obtaining feature data of a reference frame of a first image frame, wherein the first image frame and at least one second image frame have the same reference frame; and determining the position of a tracking target in the first image frame based on the feature data of the reference frame. Based on the embodiments in the present disclosure, feature data of a reference frame of a first image frame is acquired, and the position of a tracking target in the first image frame is determined based on the feature data of the reference frame.

A local extension method for segmentation of anatomical treelike structures includes receiving an initial segmentation of 3D image data including an initial treelike structure. A target point in the 3D image data is defined, and a region of interest based on the target point is extracted to create a sub-image. Highly tubular voxels are detected in the sub-image, and a spillage-constrained region growing is performed using the highly tubular voxels as seed points. Connected components are extracted from the results of the region growing. The extracted components are pruned to discard components not likely to be connected to the initial treelike structure, keeping only candidate components likely to be a valid sub-tree of the initial treelike structure. The candidate components are connected to the initial treelike structure, thereby extending the initial segmentation in the region of interest.

In an image processing apparatus, a foreground extraction unit extracts each foreground from input images, and generates a foreground extraction result. A movement trajectory feature extraction unit tracks each foreground based on the foreground extraction result, and extracts a movement trajectory feature of the foreground. The area variation feature extraction unit extracts an area variation feature representing a temporal area variation of each foreground. A foreground center estimation unit estimates a center of each foreground using the movement trajectory feature and the area variation feature.

An image processing method includes defining relations between entities of a target of which a motion is to be predicted from an image of a first time point based on a feature vector of the entities, estimating a dynamic interaction between the entities at the first time point based on the defined relations between the entities, predicting a motion of the entities changing at a second time point based on the estimated dynamic interaction, and outputting a result to which the motion predicted at the second time point is applied.

Methods, systems, and apparatus for remote camera-assisted robot guidance are disclosed. A method includes obtaining images of objects approaching a door of a property; identifying candidate paths to the door based on the images of the objects approaching the door of the property; determining movement capabilities of the objects; storing the candidate paths to the door labeled by the movement capabilities of the objects that took the paths; determining capability information for a robot at the property that indicates movement capabilities of the robot; selecting, from the candidate paths, a path for the robot to take to the door based on the movement capabilities of the robot and the labels of the candidate paths; and providing guidance information to the robot that guides the robot to the door along the selected path.

Methods, systems, and apparatus, including medium-encoded computer program products, for pre-processing image data before 3D object tracking include, in at least one aspect, a method including: performing object detection in uncompressed, two-dimensional image data from a camera to produce two-dimensional location data for objects of interest; processing the two-dimensional location data for the objects of interest using a motion criterion to generate possible paths data for the objects of interest; and constructing a flight track of an object in three-dimensional space, from the possible paths data and position information obtained from a sensor, by filtering out false positives in the possible paths data.

In implementations of systems for estimating three-dimensional trajectories of physical objects, a computing device implements a three-dimensional trajectory system to receive radar data describing millimeter wavelength radio waves directed within a physical environment using beamforming and reflected from physical objects in the physical environment. The three-dimensional trajectory system generates a cloud of three-dimensional points based on the radar, each of the three-dimensional points corresponds to a reflected millimeter wavelength radio wave within a sliding temporal window. The three-dimensional points are grouped into at least one group based on Euclidean distances between the three-dimensional points within the cloud. The three-dimensional trajectory system generates an indication of a three-dimensional trajectory of a physical object corresponding to the at least one group using a Kalman filter to track a position and a velocity a centroid of the at least one group in three-dimensions.

Systems, apparatuses and methods may provide for technology that detects an unidentified individual at a first location along a trajectory in a scene based on a video feed of the scene, wherein the video feed is to be associated with a stationary camera, and selects a non-stationary camera from a plurality of non-stationary cameras based on the trajectory and one or more settings of the selected non-stationary camera. The technology may also automatically instruct the selected non-stationary camera to adjust at least one of the one or more settings, capture a face of the individual at a second location along the trajectory, and identify the unidentified individual based on the captured face of the unidentified individual.