Boosted translation-tolerable classifiers for fast object detection

Different classifiers show different sensitivities to translation-variance. The translation-insensitive classifiers are capable of accelerating the detection process by searching over a coarse grid as well as guaranteeing the recall rate.In this paper, we define a concept of Translation-Tolerable Region (TTR) for a classifier. The TTR is such a region that all the detection windows in it have consistent (stable) results output by the classifier. We use the classifier's Maximal Translation-Tolerable Region (MTTR) to measure its sensitivity to the translation-variance. For object detection, we propose an algorithm for training the discriminative classifiers as well as learning the associated MTTRs. The discriminative classifiers are assembled into a cascaded classifier in descending order of their MTTR sizes. To speed up the detection process, we propose a Granularity-Adaptively-Tunable (GAT) search strategy according to the classifiers' MTTRs. Furthermore, we prove that the recall rate is Probably Approximately Admissible (PAA) in the GAT search, which means that the proposed approach can theoretically guarantee the accuracy while accelerating the detection process.Based on the boosting framework with Histograms of Oriented Gradients (HOG) features, we evaluate the proposed approach on the public datasets containing both rigid and non-rigid object classes. The experimental results show that our approach achieves considerable results with a fast speed. Display Omitted Highlights? We define the Maximal Translation-Tolerable Region (MTTR) to measure classifiers' sensitivity to translation-variance. ? We train a cascaded classifier that the MTTRs of the earlier strong classifiers in it are large and vice versa. ? We propose a Granularity-Adaptively-Tunable (GAT) search according to the strong classifiers' MTTRs. ? The recall rate is probably approximately admissible in the GAT search.