Patents by Inventor Daw-Tung Lin

Daw-Tung Lin 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).

  • Publication number: 20240236274
    Abstract: An image synchronization method for multiple cameras, comprising the following steps: receiving a first video of a first camera and a second video of a second camera; capturing a first object in the first video and a second object in the second video; determining whether the first object is the same as the second object; if yes, transferring a first coordinate of the first object and a second coordinate of the second object to a uniform coordinate; regulating a timing sequence of the second video to calculate a plurality of multi-object tracking accuracy values for the second video and the first video and identifying a maximum multi-object tracking accuracy value; generating a time compensation value according to a time different corresponding to the maximum multi-object tracking accuracy value and synchronizing the first camera and the second camera according to the time compensation.
    Type: Application
    Filed: November 17, 2022
    Publication date: July 11, 2024
    Applicant: INSTITUTE FOR INFORMATION INDUSTRY
    Inventors: YU-SHENG TSENG, Daw-Tung LIN, Matveichev Dmitrii
  • Publication number: 20240137662
    Abstract: An image synchronization method for multiple cameras, comprising the following steps: receiving a first video of a first camera and a second video of a second camera; capturing a first object in the first video and a second object in the second video; determining whether the first object is the same as the second object; if yes, transferring a first coordinate of the first object and a second coordinate of the second object to a uniform coordinate; regulating a timing sequence of the second video to calculate a plurality of multi-object tracking accuracy values for the second video and the first video and identifying a maximum multi-object tracking accuracy value; generating a time compensation value according to a time different corresponding to the maximum multi-object tracking accuracy value and synchronizing the first camera and the second camera according to the time compensation.
    Type: Application
    Filed: November 17, 2022
    Publication date: April 25, 2024
    Applicant: INSTITUTE FOR INFORMATION INDUSTRY
    Inventors: YU-SHENG TSENG, Daw-Tung LIN, Matveichev Dmitrii
  • Publication number: 20230055783
    Abstract: A 3D bounding box reconstruction method includes obtaining masks corresponding to a target object in images, obtaining a trajectory direction of the target object according to the masks, generating a target contour according to one of the masks, transforming the target contour into a transformed contour using a transformation matrix, obtaining a first bounding box according to the transformed contour and the trajectory direction, transforming the first bounding box into a second bounding box corresponding to the target contour using the transformation matrix, obtaining first reference points according to the target contour and the second bounding box, transforming the first reference points into second reference points using the transformation matrix, obtaining a third bounding box using the second reference points, transforming the third bounding box into a fourth bounding box using the transformation matrix, and obtaining a 3D bounding box using the second bounding box and the fourth bounding box.
    Type: Application
    Filed: September 29, 2021
    Publication date: February 23, 2023
    Applicant: INSTITUTE FOR INFORMATION INDUSTRY
    Inventors: Wen Kai LIU, Yu-Sheng TSENG, Dmitrii MATVEICHEV, Daw-Tung LIN
  • Patent number: 9122908
    Abstract: Disclosed herein is a method for counting the number of the targets using the layer scanning method. The steps of this method includes constructing a background frame, filtering the noise of foreground frame and classifying the targets, and screening the area of targets based on layer scanning to calculate the number of targets by determining the highest positions of the respective targets. In addition, the dynamic numbers of targets are calculated using algorithm. Accordingly, the present invention is beneficial in automatically, effectively and precisely calculating the number of the targets in/out a specific area, achieving the flow control for targets and reducing artificial error upon calculation.
    Type: Grant
    Filed: October 30, 2012
    Date of Patent: September 1, 2015
    Assignee: National Chiao Tung University
    Inventors: Daw-Tung Lin, Dong-Han Jhuang
  • Publication number: 20140071242
    Abstract: Disclosed herein is a method for counting the number of the targets using the layer scanning method. The steps of this method includes constructing a background frame, filtering the noise of foreground frame and classifying the targets, and screening the area of targets based on layer scanning to calculate the number of targets by determining the highest positions of the respective targets. In addition, the dynamic numbers of targets are calculated using algorithm. Accordingly, the present invention is beneficial in automatically, effectively and precisely calculating the number of the targets in/out a specific area, achieving the flow control for targets and reducing artificial error upon calculation.
    Type: Application
    Filed: October 30, 2012
    Publication date: March 13, 2014
    Applicant: NATIONAL CHIAO TUNG UNIVERSITY
    Inventors: Daw-Tung Lin, Dong-Han Jhuang
  • Patent number: 8126212
    Abstract: Proposed is a method of detecting a moving object, including: providing an image-set at least including a first image and a second image correlated in a time series, the first image preceding the second image; defining a detecting region and a detecting direction so as to construct a virtual gate in the first image; estimating the motion vector in a time series; comparing, by the virtual gate, the second image with the first image so as to determine a difference therebetween in terms of an object's position and motion vector; and retrieving the object to be an effective moving object upon determination of the object as lying within the detecting region defined in the virtual gate and moving in a direction substantively the same with the detecting direction. This invention presents a moving object detection method without the need to construct a background model a priori.
    Type: Grant
    Filed: November 11, 2008
    Date of Patent: February 28, 2012
    Assignee: Natinoal Chiao Tung University
    Inventors: Daw-Tung Lin, Li-Wei Liu
  • Publication number: 20090324011
    Abstract: Proposed is a method of detecting a moving object, including: providing an image-set at least including a first image and a second image correlated in a time series, the first image preceding the second image; defining a detecting region and a detecting direction so as to construct a virtual gate in the first image; estimating the motion vector in a time series; comparing, by the virtual gate, the second image with the first image so as to determine a difference therebetween in terms of an object's position and motion vector; and retrieving the object to be an effective moving object upon determination of the object as lying within the detecting region defined in the virtual gate and moving in a direction substantively the same with the detecting direction. This invention presents a moving object detection method without the need to construct a background model a priori.
    Type: Application
    Filed: November 11, 2008
    Publication date: December 31, 2009
    Inventors: Daw-Tung LIN, Li-Wei LIU