International Business Machines Corporation

Other

The University of Queensland

Lisa Maire Brown

Rogerio Schmidt Feris

Arun Hampapur

Sharathchandra UmapathiRao Pankanti

Yun Zhai

Ankur Datta

Andrew William Senior

Russell Patrick Bobbitt

Chiao-Fe Shu

Ying-Li Tian

Jonathan Hudson Connell, Ii

Daniel Andre Vaquero

Quanfu Fan

Frederik C M Kjeldsen

Raymond A Cooke

Kristina Scherbaum

Sayed Ali Emami

Mehrtash Harandi

Rudolf Maarten Bolle

Christopher Scott Milite

Lalit Agarwalla

Zuoxuan Lu

Chung-Ching Lin

Frederik C Kjeldsen

Mandis S Beigi

Sergio Borger

Kevin Carl Brown

Susan Crayne

Stephen R Russo

Behjat Siddiquie

Senem Velipasalar

Christopher R Carlson

Honghui Shi

James Petterson

Sharatchandra Pankanti

Barry Gottlieb

Christopher A LoGiudice

Linda C Owen

A system and a method for tracking a plurality of objects, including obtaining input data, estimating a number of skipping frames of the input data based on information from the input data, predicting results based on the estimating of the number of skipping frames, and correcting the predicted results.

System and method for multiple object tracking

An approach for re-identifying an object in a test image is presented. Similarity measures between the test image and training images captured by a first camera are determined. The similarity measures are based on Bhattacharyya distances between feature representations of an estimated background region of the test image and feature representations of background regions of the training images. A transformed test image based on the Bhattacharyya distances has a brightness that is different from the test image's brightness and matches a brightness of training images captured by a second camera. An appearance of the transformed test image resembles an appearance of a capture of the test image by the second camera. Another image included in test images captured by the second camera is identified as being closest in appearance to the transformed test image and another object in the identified other image is a re-identification of the object.

Re-identifying an object in a test image

Techniques for facilitating a video surveillance search of a person are provided. The techniques include maintaining a database of one or more attributes of one or more people captured on one or more video cameras, indexing the one or more attributes in the database extracted from the one or more video cameras, and pruning one or more images captured from the one or more video cameras using the one or more attributes and one or more items of qualifying information to facilitate a video surveillance search of a person.

Facilitating people search in video surveillance

Machine logic that pre-processes and post-processes images for visual object detection by performing the following steps: receiving a set of image(s); filtering the set of image(s) using a set of multimodal integral filter(s), thereby removing at least a portion of the set of image(s) and resulting in a filtered set of image(s); performing object detection on the filtered set of image(s) to generate a set of object-detected image(s); assembling a first plurality of object-detected image(s) from the set of object-detected image(s); and upon assembling the first plurality of object-detected image(s), performing non-maximum suppression on the assembled first plurality of object-detected image(s).

Filtering methods for visual object detection

An approach for re-identifying an object in a test image is presented. Similarity measures between the test image and training images captured by a first camera are determined. The similarity measures are based on Bhattacharyya distances between feature representations of an estimated background region of the test image and feature representations of background regions of the training images. A transformed test image based on the Bhattacharyya distances has a brightness that is different from the test image's brightness, and matches a brightness of training images captured by a second camera. An appearance of the transformed test image resembles an appearance of a capture of the test image by the second camera. Another image included in test images captured by the second camera is identified as being closest in appearance to the transformed test image and another object in the identified other image is a re-identification of the object.

Image-matching tracks the movements of the objects from initial camera scenes to ending camera scenes in non-overlapping cameras. Paths are defined through scenes for pairings of initial and ending cameras by different respective scene entry and exit points. For each of said camera pairings a combination path having a highest total number of tracked movements relative to all other combinations of one path through the initial and ending camera scene is chosen, and the scene exit point of the selected path through the initial camera and the scene entry point of the selected path into the ending camera define a path connection of the initial camera scene to the ending camera scene.

Topology determination for non-overlapping camera network

A method to automatically calibrate a static camera in a vehicle is provided. The method may include receiving a captured image file. The method may also include detecting a plurality of vehicles in the captured image file. The method may further include determining a 2D projected shape, size, location, direction of travel, and a plurality of features for each vehicle at various locations in the captured image file. The method may additionally include inferring a plurality of geometry scenes associated with the captured image file, whereby the plurality of geometry scenes is inferred based on the determined 2D projected shape, size, location, direction of travel, and the plurality of features of each vehicle within the detected plurality of vehicles as projected onto the captured image file. The method may include calibrating the static camera based on the inferred plurality of geometry scenes associated with the captured image file.

Self-calibration of a static camera from vehicle information

A method includes the following steps. A video sequence including detection results from one or more detectors is received, the detection results identifying one or more objects. A clustering framework is applied to the detection results to identify one or more clusters associated with the one or more objects. The clustering framework is applied to the video sequence on a frame-by-frame basis. Spatial and temporal information for each of the one or more clusters are determined. The one or more clusters are associated to the detection results based on the spatial and temporal information in consecutive frames of the video sequence to generate tracking information. One or more target tracks are generated based on the tracking information for the one or more clusters. The one or more target tracks are consolidated to generate refined tracks for the one or more objects.

Real-time object analysis with occlusion handling

Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Multi-mode video event indexing

An approach for re-identifying an object in a first test image is presented. Brightness transfer functions (BTFs) between respective pairs of training images are determined. Respective similarity measures are determined between the first test image and each of the training images captured by the first camera (first training images). A weighted brightness transfer function (WBTF) is determined by combining the BTFs weighted by weights of the first training images. The weights are based on the similarity measures. The first test image is transformed by the WBTF to better match one of the training images captured by the second camera. Another test image, captured by the second camera, is identified because it is closer in appearance to the transformed test image than other test images captured by the second camera. An object in the identified test image is a re-identification of the object in the first test image.

Appearance modeling for object re-identification using weighted brightness transfer functions

Techniques for object detection are provided that employ limited learned attribute ranges. One or more objects are initially detected for a full range of one or more attributes at each location of an image. Thereafter, a set of positional constraints are generated indicating an expected range of values for each position in the image for one or more of the attributes based on the detected objects employing a geometric model of a scene in the image. Objects are then detected in the image using the expected range of values for each position in the image for the one or more the attributes. The attributes comprise, for example, one or more of size, pose and rotation of the objects. A best fit is computed to the geometric model to generate the set of positional constraints, for example, using a least squares approach.

Object detection using limited learned attribute ranges

An approach that indexes and searches according to a set of attributes of a person is provided. In one embodiment, there is an extensible indexing and search tool, including an extraction component configured to extract a set of attributes of a person monitored by a set of sensors in a zone of interest. An index component is configured to index each of the set of attributes of the person within an index of an extensible indexing and search tool. A search component is configured to enable a search of the index of the extensible indexing and search tool according to at least one of the set of attributes of the person.

Indexing and searching according to attributes of a person

Growing community of inventors

Pleasantville, NY, United States of America

Lisa Maire Brown