Patents by Inventor Jinghong Zheng
Jinghong Zheng 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: 11747144Abstract: A camera-based localization system is provided. The camera-based localization system may assist an unmanned vehicle to continue its operation in a GPS-denied environment with minimal increase in vehicular cost and payload. In one aspect, a method, a computer-readable medium, and an apparatus for localization via visual inertial odometry are provided. The apparatus may construct an optical flow based on feature points across a first video frame and a second video frame captured by a camera of the apparatus. The apparatus may refine the angular velocity and the linear velocity corresponding to the second video frame via solving a quadratic optimization problem constructed based on the optical flow, the initial values of the angular velocity and the linear velocity corresponding to the second video frame. The apparatus may estimate the pose of the apparatus based on the refined angular velocity and the refined linear velocity.Type: GrantFiled: March 29, 2018Date of Patent: September 5, 2023Assignee: Agency for Science, Technology and ResearchInventors: Zhengguo Li, Jinghong Zheng, Zijian Orson Zhu, Qinyuan Ren, Kong Wah Wan, Wei Yun Yau
-
Publication number: 20200025570Abstract: A camera-based localization system is provided. The camera-based localization system may assist an unmanned vehicle to continue its operation in a GPS-denied environment with minimal increase in vehicular cost and payload. In one aspect, a method, a computer-readable medium, and an apparatus for localization via visual inertial odometry are provided. The apparatus may construct an optical flow based on feature points across a first video frame and a second video frame captured by a camera of the apparatus. The apparatus may refine the angular velocity and the linear velocity corresponding to the second video frame via solving a quadratic optimization problem constructed based on the optical flow, the initial values of the angular velocity and the linear velocity corresponding to the second video frame. The apparatus may estimate the pose of the apparatus based on the refined angular velocity and the refined linear velocity.Type: ApplicationFiled: March 29, 2018Publication date: January 23, 2020Inventors: Zhengguo Li, Jinghong Zheng, Zijian Orson Zhu, Qinyuan Ren, Kong Wah Wan, Wei Yun Yau
-
Patent number: 9979908Abstract: According to various embodiments, an image processing device may be provided. The image processing device may include: an input circuit configured to receive input image data including pixels related to varying exposure times; an interpolation circuit configured to determine an output image based on an interpolation based on the input image data; and an output circuit configured to output the output image.Type: GrantFiled: March 31, 2015Date of Patent: May 22, 2018Assignee: Agency for Science, Technology and ResearchInventors: Zhengguo Li, Jinghong Zheng
-
Publication number: 20180122051Abstract: Various embodiments provide a method of processing an input image to generate a de-hazed image. The method may include determining an atmospheric light based on the input image; determining a medium transmission map by applying an edge-preserving smoothing filter to the input image; and recovering scene radiances of the input image based on the determined atmospheric light and the determined medium transmission map. The recovered scene radiances form the de-hazed image.Type: ApplicationFiled: March 30, 2016Publication date: May 3, 2018Inventors: Zhengguo Li, Jinghong Zheng
-
Patent number: 9754356Abstract: In various embodiments of the present disclosure, there is provided a method for processing an input image. The method includes generating a base layer portion and a detail layer portion from the input image by carrying out a linear transformation of pixels of a guidance image, and determining, for each of the pixels of the guidance image, a variance of the pixels in a surrounding window of pixels. Further, the method includes determining, for each of the pixels of the guidance image, a weight value of the pixels based on the determined variance, wherein the pixels are weighted in the linear transformation according to the determined weight value. Accordingly, a system for processing an input image is also provided.Type: GrantFiled: April 11, 2014Date of Patent: September 5, 2017Assignee: Agency for Science, Technology and ResearchInventors: Zhengguo Li, Jinghong Zheng, Zijian Zhu, Shiqian Wu, Wei Yao, Susanto Rahardja
-
Publication number: 20170026593Abstract: According to various embodiments, an image processing device may be provided. The image processing device may include: an input circuit configured to receive input image data including pixels related to varying exposure times; an interpolation circuit configured to determine an output image based on an interpolation based on the data; and an output circuit configured to output the output image.Type: ApplicationFiled: March 31, 2015Publication date: January 26, 2017Applicant: Agency for Science, Technology and ResearchInventors: Zhengguo LI, Jinghong ZHENG
-
Publication number: 20170018062Abstract: According to various embodiments, an image processing device may be provided. The image processing device may include: an input circuit configured to receive input image data including pixels related to varying exposure times; a selecting circuit configured to select a reference image from the input images; a weighting determination circuit configured to determine at least one weighting for each pixel of the input image data based on the selected reference image; an output image determination circuit configured to determine an output image based the determined weightings; and an output circuit configured to output the output image.Type: ApplicationFiled: March 31, 2015Publication date: January 19, 2017Applicant: Agency for Science, Technology and ResearchInventors: Zhengguo LI, Zijian ZHU, Jinghong ZHENG
-
Patent number: 9521685Abstract: The present invention is a circuit arrangement for a wireless cellular network. The circuit arrangement includes a determiner configured to determine a priority value of each packet of a plurality of packets based on at least a position of a video frame in a group of pictures and a type of the video frame, the video frame or a part thereof being contained in the packet, wherein the type of video frame comprises I frame data or P frame data; and wherein the determiner is further configured to set the priority value of a packet including I frame data lower than the priority value of at least one other packet including P frame data; and a controller configured to control scheduling of the packet based on the determined priority value for a communication device in a wireless cellular network. A method of determining a priority of packet scheduling is also disclosed.Type: GrantFiled: September 21, 2012Date of Patent: December 13, 2016Assignees: Agency for Science, Technology and Research, Huawei International PTE., Ltd.Inventors: Peng Hui Tan, Jinghong Zheng, Sumei Sun, Zhengguo Li, Kedi Wu, Yuejun Wei
-
Patent number: 9466007Abstract: Embodiments provide a method for processing an input image having a plurality of pixels, wherein each pixel has a pixel position. The method may include determining, for each pixel position, a vector based on the input image; and determining, for each pixel position, a detail value for the pixel position based on the determined vectors at a plurality of neighboring pixel positions within a predetermined neighboring block of the pixel position.Type: GrantFiled: January 18, 2013Date of Patent: October 11, 2016Assignee: Agency for Science, Technology and ResearchInventors: Zhengguo Li, Jinghong Zheng, Zijian Zhu, Shiqian Wu, Susanto Rahardja
-
Publication number: 20160292824Abstract: In various embodiments of the present disclosure, there is provided a method for processing an input image. The method includes generating a base layer portion and a detail layer portion from the input image by carrying out a linear transformation of pixels of a guidance image, and determining, for each of the pixels of the guidance image, a variance of the pixels in a surrounding window of pixels. Further, the method includes determining, for each of the pixels of the guidance image, a weight value of the pixels based on the determined variance, wherein the pixels are weighted in the linear transformation according to the determined weight value. Accordingly, a system for processing an input image is also provided.Type: ApplicationFiled: April 11, 2014Publication date: October 6, 2016Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCHInventors: Zhengguo LI, Jinghong ZHENG, Zijian ZHU, Shiqian WU, Wei YAO, Susanto RAHARDJA
-
Publication number: 20150250001Abstract: The present invention is a circuit arrangement for a wireless cellular network. The circuit arrangement includes a determiner configured to determine a priority value of each packet of a plurality of packets based on at least a position of a video frame in a group of pictures and a type of the video frame, the video frame or a part thereof being contained in the packet, wherein the type of video frame comprises I frame data or P frame data; and wherein the determiner is further configured to set the priority value of a packet including I frame data lower than the priority value of at least one other packet including P frame data; and a controller configured to control scheduling of the packet based on the determined priority value for a communication device in a wireless cellular network. A method of determining a priority of packet scheduling is also disclosed.Type: ApplicationFiled: September 21, 2012Publication date: September 3, 2015Applicants: Huawei International PTE., Ltd., Agency for Science, Technology and ResearchInventors: Peng Hui Tan, Jinghong Zheng, Sumei Sun, Zhengguo Li, Kedi Wu, Yuejun Wei
-
Publication number: 20150154468Abstract: Embodiments provide a method for processing an input image having a plurality of pixels, wherein each pixel has a pixel position. The method may include determining, for each pixel position, a vector based on the input image; and determining, for each pixel position, a detail value for the pixel position based on the determined vectors at a plurality of neighboring pixel positions within a predetermined neighboring block of the pixel position.Type: ApplicationFiled: January 18, 2013Publication date: June 4, 2015Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCHInventors: Zhengguo Li, Jinghong Zheng, Zijian Zhu, Shiqian Wu, Susanto Rahardja
-
Patent number: 8687883Abstract: Embodiments provide a method for merging a plurality of first digital pictures, wherein each first digital picture includes a plurality of pixel values. The method includes extracting details from the plurality of first digital pictures. The method further includes combining the pixel values of the plurality of first digital pictures to generate a combined digital picture. The method further includes modifying the combined digital picture with the extracted details to generate a merged digital picture.Type: GrantFiled: January 17, 2012Date of Patent: April 1, 2014Assignee: Agency for Science, Technology and ResearchInventors: Jinghong Zheng, Zhengguo Li, Susanto Rahardja
-
Publication number: 20120183210Abstract: Embodiments provide a method for merging a plurality of first digital pictures, wherein each first digital picture includes a plurality of pixel values. The method includes extracting details from the plurality of first digital pictures. The method further includes combining the pixel values of the plurality of first digital pictures to generate a combined digital picture. The method further includes modifying the combined digital picture with the extracted details to generate a merged digital picture.Type: ApplicationFiled: January 17, 2012Publication date: July 19, 2012Inventors: Jinghong Zheng, Zhengguo Li, Susanto Rahardja