Apparatus, Systems and Methods For Shadow Assisted Object Recognition and Tracking

Number: 20200013186
Published: 2020-01-09
Filed: 2019-09-20
Assignee: Disney Enterprises, lnc.
Inventors: ZHANG; Yuecheng, AKIN; ILKE
CPC: G06V20/42; G06T7/90; G06T7/73
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

CV shadow-assisted object recognition/tracking technique.

Abstract

Described herein are apparatus, systems and methods for shadow assisted object recognition and tracking. The methods performed by the apparatus and system include identifying a blob within a video image, the video image having at least one object and at least one shadow of the at least one object, the at least one shadow of the at least one object cast by at least one light source. Identifying the blob includes identifying an object projection corresponding to the at least one object and a shadow projection corresponding to the at least one shadow. A location of an object portion of the at least one object is determined based on the shadow projection.

Background

BACKGROUND

Video object tracking is the process of locating a moving object or multiple objects over time using one or multiple cameras. It has a variety of uses, some of which are: human-computer interaction, security and surveillance, video communication and compression, augmented reality, traffic control, medical imaging and video editing. Video object tracking can be a time consuming process due to the amount of data that is contained in video. Adding further to the complexity is the possible need to use object recognition techniques for tracking, a challenging problem in its own right.

The objective of video object tracking is to detect and then associate a target object's image projections in consecutive video frames as it changes its position. The association may be difficult when the object is moving fast relative to the frame rate or when multiple objects are being tracked. Another situation that increases the complexity of the problem is when the tracked object changes its orientation and pose over time. To address this complexity, video object tracking systems usually employ an object model which characterizes the object's appearance and motion.

Automated video object tracking applications are known in the art. Generally, such applications receive video frames as input, and act to detect objects of interest within the frame images, such as moving objects or the like, frequently using background subtraction techniques. Having detected an object wit

Claims

21. A method, comprising: receiving a video image that includes: an object that is elevated with respect to ground level in the video image, and a shadow of the object; and determining three-dimensional positional information corresponding to a location of the object based on a detected position of the object in the video image and a two-dimensional position of the shadow of the object. 28. A device, comprising: a memory having a program stored thereon; and a processor coupled to the memory, wherein the processor executes the program to cause the processor to perform operations comprising: receiving a video image that includes: an object that is elevated with respect to ground level in the video image, and a shadow of the object; and determining three-dimensional positional information corresponding to a location of the object based on a detected position of the object in the video image and a two-dimensional position of the shadow of the object. 34. A non-transitory computer readable storage medium comprising a plurality of instructions, that when executed by a processor cause the processor to perform operations comprising: receiving a video image that includes: an object that is elevated with respect to ground level in the video image, and a shadow of the object; and determining three-dimensional positional information corresponding to a location of the object based on a detected position of the object in the video image and a two-dimensional position of the shadow of the object.