-
公开(公告)号：US20170091943A1
公开(公告)日：2017-03-30
申请号：US14866781
申请日：2015-09-25
Applicant: QUALCOMM Incorporated
Inventor： Qi Pan , Romain Tallonneau , Emilio Maggio , Stefan Walk
CPC classification number: G06K9/481 , G06K9/3233 , G06K9/34 , G06K9/46 , G06K9/4633 , G06K9/4671 , G06K9/6212 , G06K9/6277 , G06K2009/3291 , G06T7/10 , G06T7/11 , G06T7/136 , G06T7/70 , G06T7/74 , G06T2207/20076
Abstract: Disclosed are a system, apparatus, and method for detecting objects. Input image frames may be received and distinct regions created within each frame. Descriptors may be extracted from the regions according to their associated probability. Extracted descriptors may be matched to reference descriptors. Votes or confidence is cast for particular regions according to region properties. The region properties may be determined from center voting methods based on vector intersection to other vectors or intersections with a region. The probability of selecting particular regions can increase with each vote or increase in confidence for a region. In response to updating probabilities, additional regions may be selected and additional descriptors may be extracted. Additional voting iterations can update the probability of selecting a next region. An object pose may be estimated in response to meeting one or more thresholds.
-
公开(公告)号：US09727800B2
公开(公告)日：2017-08-08
申请号：US14866781
申请日：2015-09-25
Applicant: QUALCOMM Incorporated
Inventor： Qi Pan , Romain Tallonneau , Emilio Maggio , Stefan Walk
CPC classification number: G06K9/481 , G06K9/3233 , G06K9/34 , G06K9/46 , G06K9/4633 , G06K9/4671 , G06K9/6212 , G06K9/6277 , G06K2009/3291 , G06T7/10 , G06T7/11 , G06T7/136 , G06T7/70 , G06T7/74 , G06T2207/20076
Abstract: Disclosed are a system, apparatus, and method for detecting objects. Input image frames may be received and distinct regions created within each frame. Descriptors may be extracted from the regions according to their associated probability. Extracted descriptors may be matched to reference descriptors. Votes or confidence is cast for particular regions according to region properties. The region properties may be determined from center voting methods based on vector intersection to other vectors or intersections with a region. The probability of selecting particular regions can increase with each vote or increase in confidence for a region. In response to updating probabilities, additional regions may be selected and additional descriptors may be extracted. Additional voting iterations can update the probability of selecting a next region. An object pose may be estimated in response to meeting one or more thresholds.
-
Search Results
2
records
(took 0.011 seconds)
