Combination detector and object detection method using the same
AssigneeSamsung Electronics Co., Ltd.
InventorsHaibing Ren, Jung Bae Kim, Jong Ha Lee
Life of this patent
Estimating the term…
Loading patent…
AssigneeSamsung Electronics Co., Ltd.
InventorsHaibing Ren, Jung Bae Kim, Jong Ha Lee
Estimating the term…
Provided are a detector and a method of detecting an object using the detector. The method includes combining a first detector and a second detector in a combination scheme to form a multi-layer combination detector, the second detector being of a type different from that of the first detector, processing a binary classification detection with respect to an inputted sample starting from an uppermost layer detector, allowing a sample of an object detected from a current layer to approach a lower layer, while rejecting a sample of a non-object detected from the current layer whereby the rejected non-object may not approach the lower layer, and outputting a sample passing through all layers as a detected object.
A method of detecting an object using a combination detector including a processor having executable instructions, the method comprising:
A method of detecting an object using a combination detector including a processor having executable instructions, the method comprising:
A combination detector, in which a first detector and a second detector, the second detector being of a type different from that of the first detector, are combined, a binary classification detection with respect to an inputted sample is processed, a sample of an object detected from a current layer is allowed to approach a lower layer, a sample of a non-object detected from the current layer is rejected from approaching the lower layer, and a sample passing through all layers is outputted as a detected object.
A combination detector, in which a first detector and a second detector, the second detector being a type different from that of the first detector, are combined, a plurality of appearance images are classified into a plurality of sub classes in accordance with a viewing angle, a binary classification detection is processed with respect to an inputted sample of the plurality of sub classes, a sample of an object detected from a current layer is allowed to approach a lower layer, a sample of a non-object detected from the current layer is rejected from approaching the lower layer, and final samples passing through all layer are combined as a detected object.
Dependencies are inferred from the claim text.