Patents by Inventor Sang-Hack Jung
Sang-Hack Jung has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9977972Abstract: A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models based at least in part on the set of p-scores and the set of n-scores.Type: GrantFiled: October 21, 2014Date of Patent: May 22, 2018Assignee: SRI InternationalInventors: Saad Masood Khan, Hui Cheng, Dennis Lee Matthies, Harpreet Singh Sawhney, Sang-Hack Jung, Chris Broaddus, Bogdan Calin Mihai Matei, Ajay Divakaran
-
Publication number: 20160379062Abstract: A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.Type: ApplicationFiled: October 21, 2014Publication date: December 29, 2016Inventors: Saad Masood Khan, Hui Cheng, Dennis Lee Matthies, Harpreet Singh Sawhney, Sang-Hack Jung, Chris Broaddus, Bogdan Calin Mihai Matei, Ajay Divakaran
-
Patent number: 8913783Abstract: A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.Type: GrantFiled: October 28, 2010Date of Patent: December 16, 2014Assignee: SRI InternationalInventors: Saad Masood Khan, Hui Cheng, Dennis Lee Matthies, Harpreet Singh Sawhney, Sang-Hack Jung, Chris Broaddus, Bogdan Calin Mihai Matei, Ajay Divakaran
-
Patent number: 8861842Abstract: A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.Type: GrantFiled: February 7, 2011Date of Patent: October 14, 2014Assignee: SRI InternationalInventors: Sang-Hack Jung, Mayank Bansal, Bogdan Calin Mihai Matei, Jayan Eledath, Harpreet Singh Sawhney, Rakesh Kumar, Raia Hadsell
-
Patent number: 8860813Abstract: A computer-implemented method for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invarient distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.Type: GrantFiled: December 11, 2012Date of Patent: October 14, 2014Assignee: SRI InternationalInventors: Sang-Hack Jung, Ajay Divakaran, Harpreet Singh Sawhney
-
Patent number: 8744122Abstract: The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.Type: GrantFiled: October 22, 2009Date of Patent: June 3, 2014Assignee: SRI InternationalInventors: Garbis Salgian, John Benjamin Southall, Sang-Hack Jung, Vlad Branzoi, Jiangjian Xiao, Feng Han, Supun Samarasekera, Rakesh Kumar, Jayan Eledath
-
Patent number: 8634638Abstract: The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.Type: GrantFiled: June 22, 2009Date of Patent: January 21, 2014Assignee: SRI InternationalInventors: Feng Han, Hui Cheng, Jiangjian Xiao, Harpreet Singh Sawhney, Sang-Hack Jung, Rakesh Kumar, Yanlin Guo
-
Patent number: 8330819Abstract: A computer-implemented method for for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.Type: GrantFiled: April 12, 2010Date of Patent: December 11, 2012Assignee: SRI InternationalInventors: Sang-Hack Jung, Ajay Divakaran, Harpreet Singh Sawhney
-
Publication number: 20120106800Abstract: A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.Type: ApplicationFiled: October 28, 2010Publication date: May 3, 2012Inventors: Saad Masood Khan, Hui Cheng, Dennis Lee Matthies, Harpreet Singh Sawhney, Sang-Hack Jung, Chris Broaddus, Bogdan Calin Mihai Matei, Ajay Divakaran
-
Patent number: 8102427Abstract: A method for estimating egomotion of a camera mounted on a vehicle that uses infra-red images is disclosed, comprising the steps of (a) receiving a pair of frames from a plurality of frames from the camera, the first frame being assigned to a previous frame and an anchor frame and the second frame being assigned to a current frame; (b) extracting features from the previous frame and the current frame; (c) finding correspondances between extracted features from the previous frame and the current frame; and (d) estimating the relative pose of the camera by minimizing reprojection errors from the correspondences to the anchor frame.Type: GrantFiled: September 3, 2008Date of Patent: January 24, 2012Assignee: SRI InternationalInventors: Sang-Hack Jung, Jayan Eledath
-
Publication number: 20110255741Abstract: A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.Type: ApplicationFiled: February 7, 2011Publication date: October 20, 2011Inventors: Sang-Hack Jung, Mayank Bansal, Bogdan Calin Mihai Matei, Jayan Eledath, Harpreet Singh Sawhney, Rakesh Kumar, Raia Hadsell
-
Publication number: 20100328452Abstract: A computer-implemented method for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.Type: ApplicationFiled: April 12, 2010Publication date: December 30, 2010Inventors: Sang-Hack Jung, Ajay Divakaran, Harpreet Singh Sawhney
-
Publication number: 20100202657Abstract: The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.Type: ApplicationFiled: October 22, 2009Publication date: August 12, 2010Inventors: Garbis Salgian, John Benjamin Southall, Sang-Hack Jung, Vlad Branzoi, Jiangjian Xiao, Feng Han, Supun Samarasekera, Rakesh Kumar, Jayan Eledath
-
Publication number: 20090316983Abstract: The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.Type: ApplicationFiled: June 22, 2009Publication date: December 24, 2009Inventors: Feng Han, Hui Cheng, Jiangjian Xiao, Harpreet Singh Sawhney, Sang-Hack Jung, Rakesh Kumar, Yanlin Guo
-
Publication number: 20090207257Abstract: A method for estimating egomotion of a camera mounted on a vehicle that uses infra-red images is disclosed, comprising the steps of (a) receiving a pair of frames from a plurality of frames from the camera, the first frame being assigned to a previous frame and an anchor frame and the second frame being assigned to a current frame; (b) extracting features from the previous frame and the current frame; (c) finding correspondances between extracted features from the previous frame and the current frame; and (d) estimating the relative pose of the camera by minimizing reprojection errors from the correspondences to the anchor frame.Type: ApplicationFiled: September 3, 2008Publication date: August 20, 2009Inventors: Sang-Hack Jung, Jayan Eledath