Canon Kabushiki Kaisha

The University of Sydney

Pantelis Elinas

Xin Yu Liu

Eric William Nettleton

Hugh Durrant-Whyte

Surya P N Singh

Linthotage Dushantha Lochana Perera

A method of tracking an object in a plurality of image frames includes receiving an initial contour associated with the edge object in a first one of the image frames. A plurality of first measurement points distributed non-uniformly along the initial contour are determined. The first measurement points are biased to relatively high information portions of the initial contour. A set of subsequent contours are estimated from the initial contour in a second image frame. An identical plurality of second measurement points are determined along each of the set of estimated subsequent contours in the second image frame using the same non-uniform distribution of the first measurement points in the first image frame. The method selects at least one contour of the set of estimated subsequent contours using a confidence measure determined from the second measurement points as distributed along the selected subsequent contour.

Non-uniform curve sampling method for object tracking

A method of determining a contour segment for an object in an image captured by a camera is disclosed. A plurality of corner points located on a part of an object in the image is determined. Pairs of corner points are selected from the determined corner points. A path for at least one of the pairs of corner points is determined, the path connecting the corner points of the at least one pair of corner points along the boundary of the object. The contour segment is determined for the object using the determined path.

Method, system and apparatus for determining a contour segment for an object in an image captured by a camera

Described herein is a method and system for vehicle localization in an open pit mining environment having intermittent or incomplete GPS coverage. The system comprises GPS receivers associated with the vehicles and providing GPS measurements when available, as well as one or more camerasoverlooking the mine region. The camerasare at a known location and are used for generating a sequence of images in a field of view with predetermined calibration in a fixed coordinate system. The system further comprises a vehicle recognition processorfor analyzing individual images from the camera to identify and locate within an image a vehicle in the mine region, as well as a vehicle tracking processorfor analyzing a sequence of images from the camera to track the identified vehicle location in the sequence of images. A data fusion processoris coupled to receive GPS measurements, when available, from the vehicle GPS receivers, to fuse the received GPS measurement and corresponding vehicle image location, and to output a vehicle localization output

Vehicle localization in open-pit mining using GPS and monocular camera

Forming a sequence plan for a machine to travel to a series of specified locations is described. An initial cost table () and a pattern of locations () is inputted to a Sequential Ordering Problem (SOP) solver (). The resulting sequence () is processed by a motion planner () to derive by a motion planning procedure a plan of machine motions through the sequence. A cost table update () is performed based on the motion plan, which is then used for another iteration of the SOP solver ().

Growing community of inventors

Glebe, Australia

Pantelis Elinas