Format

Send to

Choose Destination
IEEE Trans Pattern Anal Mach Intell. 2012 Oct;34(10):2005-18.

Learning optimal embedded cascades.

Author information

1
Statistical Visual Computing Laboratory,University of California, San Diego, Room 5512, 9500 Gilman Drive, Mail code 0407, EBU 1, La Jolla, CA 92093-0407, USA. saberian@ucsd.edu

Abstract

The problem of automatic and optimal design of embedded object detector cascades is considered. Two main challenges are identified: optimization of the cascade configuration and optimization of individual cascade stages, so as to achieve the best tradeoff between classification accuracy and speed, under a detection rate constraint. Two novel boosting algorithms are proposed to address these problems. The first, RCBoost, formulates boosting as a constrained optimization problem which is solved with a barrier penalty method. The constraint is the target detection rate, which is met at all iterations of the boosting process. This enables the design of embedded cascades of known configuration without extensive cross validation or heuristics. The second, ECBoost, searches over cascade configurations to achieve the optimal tradeoff between classification risk and speed. The two algorithms are combined into an overall boosting procedure, RCECBoost, which optimizes both the cascade configuration and its stages under a detection rate constraint, in a fully automated manner. Extensive experiments in face, car, pedestrian, and panda detection show that the resulting detectors achieve an accuracy versus speed tradeoff superior to those of previous methods.

PMID:
22213762
DOI:
10.1109/TPAMI.2011.281
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IEEE Engineering in Medicine and Biology Society
Loading ...
Support Center