QUALCOMM Incorporated
Accumulate across stages in machine learning object detection

Abstract:

Apparatus, methods, systems, and instructions stored on computer-readable medium are presented for performing classification. A hardware engine may be configurable to implement multiple stages of a cascade classifier including a first stage and a second stage. The hardware engine may be configurable to (a) access a value indicative of whether to accumulate, and (b) responsive to the value indicative of whether to accumulate meeting a continue evaluation condition, (i) access a first numeric value obtained from evaluation of the first stage of the cascade classifier, (ii) accumulate the first numeric value with a second numeric value obtained from evaluation of the second stage of the cascade classifier to generate an accumulated value, and (iii) utilize the accumulated value to determine an outcome for the second stage of the cascade classifier.