Patents by Inventor Young-Ki Baik
Young-Ki Baik 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: 11948249Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: GrantFiled: October 7, 2022Date of Patent: April 2, 2024Assignee: QUALCOMM IncorporatedInventors: Young-Ki Baik, ChaeSeong Lim, Duck Hoon Kim
-
Patent number: 11913858Abstract: Disclosed is a disc-shaped sample chamber for collecting molten metal, the chamber comprising: a chamber body having a left body and a right body bonded to each other to define a disc-shaped sample space therebetween; an inlet extending upward from the chamber body and connecting the sample space with the outside; and a welded bonding portion disposed on at least one lateral face of the chamber body for bonding the left body and the right body to each other. Further, a probe having the chamber is disclosed.Type: GrantFiled: December 11, 2020Date of Patent: February 27, 2024Assignee: HERAEUS ELECTRO-NITE INTERNATIONAL N.V.Inventors: Bong-Ki Baik, Young-jin Jung, Cheol-jung Kim
-
Publication number: 20230135153Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: ApplicationFiled: October 7, 2022Publication date: May 4, 2023Inventors: Young-Ki BAIK, ChaeSeong LIM, Duck Hoon KIM
-
Patent number: 11630197Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.Type: GrantFiled: January 2, 2020Date of Patent: April 18, 2023Assignee: QUALCOMM IncorporatedInventors: Jayakrishnan Unnikrishnan, Avdhut Joshi, Shivam Agarwal, Amir Salimi, Sree Sesha Aravind Vadrevu, Gautam Sachdeva, Yoga Y Nadaraajan, Ravi Teja Sukhavasi, Xinzhou Wu, Young-Ki Baik, Duck Hoon Kim, Hyun-Mook Cho
-
Publication number: 20230112799Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: ApplicationFiled: October 18, 2022Publication date: April 13, 2023Inventors: Young-Ki BAIK, Hyun-Mook CHO, Duck Hoon KIM, Jeong-Kyun LEE, Chaeseong LIM, Hee-Seok LEE
-
Patent number: 11544940Abstract: Disclosed are techniques for lane estimation. In aspects, a method includes receiving a plurality of camera frames captured by a camera sensor of a vehicle, assigning a first subset of the plurality of camera frames to a deep learning (DL) detector and a second subset of the plurality of camera frames to a computer vision (CV) detector based on availability of the DL and CV detectors, identifying a first set of lane boundary lines in a first camera frame processed by the DL detector, identifying a second set of lane boundary lines in a second camera frame processed by the CV detector, generating first and second sets of lane models based on the first and second sets of lane boundary lines, and updating a set of previously identified lane models based on the first set of lane models and/or the second set of lane models.Type: GrantFiled: January 2, 2020Date of Patent: January 3, 2023Assignee: QUALCOMM IncorporatedInventors: Young-Ki Baik, Jeong-Kyun Lee, Seok-Soo Hong, Duck Hoon Kim
-
Patent number: 11508122Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: GrantFiled: January 2, 2020Date of Patent: November 22, 2022Assignee: QUALCOMM IncorporatedInventors: Young-Ki Baik, Hyun-Mook Cho, Duck Hoon Kim, Jeong-Kyun Lee, ChaeSeong Lim, Hee-Seok Lee
-
Patent number: 11494979Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: GrantFiled: January 2, 2020Date of Patent: November 8, 2022Assignee: QUALCOMM IncorporatedInventors: Young-Ki Baik, ChaeSeong Lim, Duck Hoon Kim
-
Patent number: 11373332Abstract: Techniques and systems are provided for determining features of one or more objects in one or more images. For example, an image of an object and a three-dimensional model associated with the object can be obtained. From the image, a sample point on the object can be determined. A depth and an angle of the sample point of the object can be determined. A pose and a shape of the three-dimensional model associated with the object can be determined based on the depth and the angle.Type: GrantFiled: January 5, 2021Date of Patent: June 28, 2022Assignee: QUALCOMM IncorporatedInventors: Jeong-Kyun Lee, Young-Ki Baik, Hankyu Cho, Dongju Kim
-
Patent number: 11195028Abstract: Disclosed are techniques for estimating multiple lane boundaries through simultaneous detection of lane markers (LM) and raised pavement markers (RPM). Conventional techniques for lane marker detection (LMD) comprises extracting and clustering line segments from a camera image, fitting the clustered lines to a geometric model, and selecting the multiple lanes using heuristic approaches. Unfortunately, in the conventional technique, an error from each step is sequentially propagated to the next step. Also there are no techniques to estimate both LMs and RPMs. A technique to simultaneously detect in real time both LM and RPMs is proposed. This enables optimal estimation of multiple lane boundaries.Type: GrantFiled: January 2, 2020Date of Patent: December 7, 2021Assignee: QUALCOMM IncorporatedInventors: Jeong-Kyun Lee, Young-Ki Baik, Seungwoo Yoo, Duck Hoon Kim
-
Publication number: 20210209797Abstract: Techniques and systems are provided for determining features of one or more objects in one or more images. For example, an image of an object and a three-dimensional model associated with the object can be obtained. From the image, a sample point on the object can be determined. A depth and an angle of the sample point of the object can be determined. A pose and a shape of the three-dimensional model associated with the object can be determined based on the depth and the angle.Type: ApplicationFiled: January 5, 2021Publication date: July 8, 2021Inventors: Jeong-Kyun LEE, Young-Ki BAIK, Hankyu CHO, Dongju KIM
-
Publication number: 20200219315Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Young-Ki BAIK, ChaeSeong LIM, Duck Hoon KIM
-
Publication number: 20200218913Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Jayakrishnan UNNIKRISHNAN, Avdhut JOSHI, Shivam AGARWAL, Amir SALIMI, Sree Sesha Aravind VADREVU, Gautam SACHDEVA, Yoga Y NADARAAJAN, Ravi Teja SUKHAVASI, Aolin XU, Xinzhou WU, Young-Ki BAIK, Duck Hoon KIM, Hyun-Mook CHO
-
Publication number: 20200219316Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Young-Ki BAIK, Hyun-Mook CHO, Duck Hoon KIM, Jeong-Kyun LEE, ChaeSeong LIM, Hee-Seok LEE
-
Publication number: 20200218908Abstract: Disclosed are techniques for estimating multiple lane boundaries through simultaneous detection of lane markers (LM) and raised pavement markers (RPM). Conventional techniques for lane marker detection (LMD) comprises extracting and clustering line segments from a camera image, fitting the clustered lines to a geometric model, and selecting the multiple lanes using heuristic approaches. Unfortunately, in the conventional technique, an error from each step is sequentially propagated to the next step. Also there are no techniques to estimate both LMs and RPMs. A technique to simultaneously detect in real time both LM and RPMs is proposed. This enables optimal estimation of multiple lane boundaries.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Jeong-Kyun LEE, Young-Ki BAIK, Seungwoo YOO, Duck Hoon KIM
-
Publication number: 20200218907Abstract: Disclosed are techniques for lane estimation. In aspects, a method includes receiving a plurality of camera frames captured by a camera sensor of a vehicle, assigning a first subset of the plurality of camera frames to a deep learning (DL) detector and a second subset of the plurality of camera frames to a computer vision (CV) detector based on availability of the DL and CV detectors, identifying a first set of lane boundary lines in a first camera frame processed by the DL detector, identifying a second set of lane boundary lines in a second camera frame processed by the CV detector, generating first and second sets of lane models based on the first and second sets of lane boundary lines, and updating a set of previously identified lane models based on the first set of lane models and/or the second set of lane models.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Young-Ki BAIK, Jeong-Kyun LEE, Seok-Soo HONG, Duck Hoon Kim
-
Patent number: 10152540Abstract: A method, performed by an electronic device, for linking a thumbnail of an image and at least one web page is disclosed. In this method, the image including at least one text region may be accessed in a storage unit. At least one text region may be detected in the image and at least one character string in the at least one text region may be recognized. Further, the method may include selecting the at least one web page from the plurality of web pages and linking the thumbnail of the image and the at least one web page.Type: GrantFiled: April 17, 2015Date of Patent: December 11, 2018Assignee: QUALCOMM IncorporatedInventors: Seungwoo Yoo, Duck Hoon Kim, Young-Ki Baik, Kang Kim, Seok-Soo Hong
-
Patent number: 9349066Abstract: A method includes tracking an object in each of a plurality of frames of video data to generate a tracking result. The method also includes performing object processing of a subset of frames of the plurality of frames selected according to a multi-frame latency of an object detector or an object recognizer. The method includes combining the tracking result with an output of the object processing to produce a combined output.Type: GrantFiled: August 6, 2012Date of Patent: May 24, 2016Assignee: QUALCOMM IncorporatedInventors: Hyung-Il Koo, Kisun You, Young-Ki Baik
-
Publication number: 20160104052Abstract: A method for displaying an image is disclosed. The method may be performed in an electronic device. Further, the method may detect at least one text region in the image and determine at least one text category associated with the at least one text region. Based on the at least one text region and the at least one text category, the method may generate at least one thumbnail from the image and display the at least one thumbnail.Type: ApplicationFiled: May 15, 2015Publication date: April 14, 2016Inventors: Kang Kim, Seungwoo Yoo, Young-Ki Baik, Duck-Hoon Kim, Seok-Soo Hong
-
Publication number: 20160103915Abstract: A method, performed by an electronic device, for linking a thumbnail of an image and at least one web page is disclosed. In this method, the image including at least one text region may be accessed in a storage unit. At least one text region may be detected in the image and at least one character string in the at least one text region may be recognized. Further, the method may include selecting the at least one web page from the plurality of web pages and linking the thumbnail of the image and the at least one web page.Type: ApplicationFiled: April 17, 2015Publication date: April 14, 2016Inventors: Seungwoo Yoo, Duck Hoon Kim, Young-Ki Baik, Kang Kim, Seok-Soo Hong