This Article 
 Bibliographic References 
 Add to: 
Learning Optimal Embedded Cascades
Oct. 2012 (vol. 34 no. 10)
pp. 2005-2018
Mohammad Javad Saberian, UC San Diego, La Jolla
Nuno Vasconcelos, UC San Diego, La Jolla
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.
Index Terms:
Computer vision,Detectors,Training,Real-time systems,Algorithm design and analysis,Object detection,Computer architecture,boosting.,Computer vision,real-time object detection,embedded detector cascades
Mohammad Javad Saberian, Nuno Vasconcelos, "Learning Optimal Embedded Cascades," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 10, pp. 2005-2018, Oct. 2012, doi:10.1109/TPAMI.2011.281
Usage of this product signifies your acceptance of the Terms of Use.