Other

Bendix Commercial Vehicle Systems LLC

Puretech Systems Inc.

Dilip Swaminathan

Fereydoun Maali

Marvin Wade Barnes

Travis Alexander Woodrow

Monroe Milas Thomas

Andreas U Kuehnle

Hans M Molin

Cathy L Boon

Ken D Au

Chandra Sekhar Gatla

Jeffrey S Lawson

In an example embodiment, an image based vehicle detection and measuring apparatus that employs an accelerated, structured, search method is described for quickly finding the extrema of a multivariable function. The input domain of the function is determined. The method exploits information as it becomes available, calculating a best possible value with the information available so far, and terminating further evaluation when the best possible value does not exceed the extreme value found so far. Ordering and best guess schemes are added to the best possible value idea to accelerate it further. The method is applied to speed up an image processing problem, an example of which is given, but has general application, for example, in fields such as vehicle detection.

Image-based vehicle detection and distance measuring method and apparatus

A system and method for autonomous tracking of aerial targets in real space in a featureless background includes capturing and processing first and second images. A resultant image is produced which includes blobs corresponding to elements in the real space. The resultant image is further processed, together with either or both of the first and second images. One of the blobs is analyzed, classified, and tracked as a target.

System and method for autonomous PTZ tracking of aerial targets

A system for autonomous tracking of aerial targets in real space. The imaging means captures and aligns first and second images. A normalized correlation operation initiates a process for producing a resultant image including blobs corresponding to elements in the real space, despite the presence of a homogenous aerial background. One of the blobs is analyzed, classified, and tracked as a target.

A surveillance system and method includes imaging means for processing images so that objects in the foreground are detected in the background and threats are identified. In the method, the imaging means acquires images and an initial background model is constructed from those images. Pixels are classified as either background or foreground for subsequent processing stages. In some embodiments, the imaging means is fixed in location and attitude, while in other embodiments, the imaging means is mounted to a moving platform and can alter its attitude. In such mobile applications, the system exploits geo-referencing as an aid in determining information about the pixels.

Background modeling for imaging surveillance

An autonomous lock-on target tracking system and method with imaging means for a real space. The imaging means captures and aligns first and second images. A frame-differencing operation produces a resultant image including blobs corresponding to elements in the real space. One of the blobs is analyzed, classified, and tracked as a target.

System and method for autonomous lock-on target tracking

A video camera surveillance system includes a camera for acquiring a video stream and converting terrain space into image space and a method for processing the video stream so that objects in the foreground are detected in the background and threats are identified. In the method, the camera acquires the video stream, images in the video stream are stabilized, an initial background model is constructed, and pixels are classified as either background or foreground for subsequent processing stages such as morphological filtering, image segmentation, and background model updating. In some embodiments of the invention, the camera is fixed in location and attitude, while in other embodiments, the camera is mounted to a moving platform and can alter its attitude.

Background modeling for fixed, mobile, and step- and-stare video camera surveillance

An autonomous lock-on target tracking system and method with geospatial-aware PTZ cameras includes a camera imaging a terrain space. The camera acquires images, and first and second images are aligned. A frame-differencing operation produces a resultant image including blobs corresponding to elements in the terrain space. One of the blobs is classified as an object and tracked as a target. The target is tracked by determining the distance between a centroid of the target and a center of a field of view of the camera, and instructing the camera to move through the distance. The distance is continually updated as the camera and the target move. Disclosed are also methods for deploying the georeferencing enabled version of such PTZ camera on stationary and mobile land, sea and air platforms.

Autonomous lock-on target tracking with geospatial-aware PTZ cameras

An autonomous lock-on target tracking system and method with geospatial-aware PTZ cameras includes a camera imaging a terrain space. The camera acquires images, and first and second images are aligned. A frame-differencing operation produces a resultant image including blobs corresponding to elements in the terrain space. One of the blobs is classified as an object and tracked as a target. The target is tracked by determining the distance between a centroid of the target and a center of a field of view of the camera, and instructing the camera to move through the distance. The distance is continually updated as the camera and the target move.

Growing community of inventors

Irvine, CA, United States of America

Dilip Swaminathan