Abstract :
Detection of objects of a given class is important for many applications. However it is difficult to learn a general detector with high detection rate as well as low false alarm rate. Especially, the labor needed for manually labeling a huge training sample set is usually not affordable. We propose an unsupervised, incremental learning approach based on online boosting to improve the performance on special applications of a set of general part detectors, which are learned from a small amount of labeled data and have moderate accuracy. Our oracle for unsupervised learning, which has high precision, is based on a combination of a set of shape based part detectors learned by off-line boosting. Our online boosting algorithm, which is designed for cascade structure detector, is able to adapt the simple features, the base classifiers, the cascade decision strategy, and the complexity of the cascade automatically to the special application. We integrate two noise restraining strategies in both the oracle and the online learner. The system is evaluated on two public video corpora.
Keywords :
object detection; unsupervised learning; cascade decision strategy; cascade structure detector; huge training sample set; manually labeling; part based object detection; public video corpora; unsupervised incremental learning approach; unsupervised learning; unsupervised online boosting; Boosting; Computer vision; Detectors; Face detection; Intelligent robots; Intelligent systems; Labeling; Motion segmentation; Object detection; Surveillance;
