HARSH NANDA
Pilots at Lk Sammamish Pkwy, Redmond, WA
License number
Washington A5247145
Issued Date
May 2015
Expiration Date
May 2020
Category
Airmen
Type
Authorized Aircraft Instructor
Address
Address
4214 W Lake Sammamish Pkwy NE APT 203, Redmond, WA 98052
Professional information
Visual Tracking Using Depth Data
US Patent:
7372977, May 13, 2008
Filed:
May 28, 2004
Appl. No.:
10/857581
Inventors:
Kikuo Fujimura - Palo Alto CA, US
Harsh Nanda - Redmond WA, US
Harsh Nanda - Redmond WA, US
Assignee:
Honda Motor Co., Ltd. - Tokyo
International Classification:
G06K 9/00
US Classification:
382103
Abstract:
Real-time visual tracking using depth sensing camera technology, results in illumination-invariant tracking performance. Depth sensing (time-of-flight) cameras provide real-time depth and color images of the same scene. Depth windows regulate the tracked area by controlling shutter speed. A potential field is derived from the depth image data to provide edge information of the tracked target. A mathematically representable contour can model the tracked target. Based on the depth data, determining a best fit between the contour and the edge of the tracked target provides position information for tracking. Applications using depth sensor based visual tracking include head tracking, hand tracking, body-pose estimation, robotic command determination, and other human-computer interaction systems.
Visual Tracking Using Depth Data
US Patent:
7590262, Sep 15, 2009
Filed:
Apr 21, 2008
Appl. No.:
12/106788
Inventors:
Kikuo Fujimura - Palo Alto CA, US
Harsh Nanda - Redmond WA, US
Harsh Nanda - Redmond WA, US
Assignee:
Honda Motor Co., Ltd. - Tokyo
International Classification:
G06K 9/00
US Classification:
382104, 382103, 382106, 382154
Abstract:
Real-time visual tracking using depth sensing camera technology, results in illumination-invariant tracking performance. Depth sensing (time-of-flight) cameras provide real-time depth and color images of the same scene. Depth windows regulate the tracked area by controlling shutter speed. A potential field is derived from the depth image data to provide edge information of the tracked target. A mathematically representable contour can model the tracked target. Based on the depth data, determining a best fit between the contour and the edge of the tracked target provides position information for tracking. Applications using depth sensor based visual tracking include head tracking, hand tracking, body-pose estimation, robotic command determination, and other human-computer interaction systems.