Issue No. 08 - Aug. (2012 vol. 34)
A. Prati , Dept. of Eng. Sci. & Methods, Univ. of Modena & Reggio Emilia, Reggio Emilia, Italy
G. Gualdi , Dept. of Inf. Eng., Univ. of Modena & Reggio Emilia, Modena, Italy
R. Cucchiara , Dept. of Inf. Eng., Univ. of Modena & Reggio Emilia, Modena, Italy
The common paradigm employed for object detection is the sliding window (SW) search. This approach generates grid-distributed patches, at all possible positions and sizes, which are evaluated by a binary classifier: The tradeoff between computational burden and detection accuracy is the real critical point of sliding windows; several methods have been proposed to speed up the search such as adding complementary features. We propose a paradigm that differs from any previous approach since it casts object detection into a statistical-based search using a Monte Carlo sampling for estimating the likelihood density function with Gaussian kernels. The estimation relies on a multistage strategy where the proposal distribution is progressively refined by taking into account the feedback of the classifiers. The method can be easily plugged into a Bayesian-recursive framework to exploit the temporal coherency of the target objects in videos. Several tests on pedestrian and face detection, both on images and videos, with different types of classifiers (cascade of boosted classifiers, soft cascades, and SVM) and features (covariance matrices, Haar-like features, integral channel features, and histogram of oriented gradients) demonstrate that the proposed method provides higher detection rates and accuracy as well as a lower computational burden w.r.t. sliding window detection.
search problems, Bayes methods, feature extraction, Gaussian processes, grid computing, image classification, image sampling, Monte Carlo methods, object detection, sliding window detection, multistage particle windows, accurate object detection, fast object detection, sliding window search, grid-distributed patches, binary classifier, statistical-based search, Monte Carlo sampling, likelihood density function, Gaussian kernels, multistage strategy, Bayesian-recursive framework, temporal coherency, face detection, pedestrian detection, Face, Feature extraction, Accuracy, Object detection, Support vector machines, Search problems, Face detection, coarse-to-fine search refinement., Efficient object detection, pedestrian detection
A. Prati, G. Gualdi, R. Cucchiara, "Multistage Particle Windows for Fast and Accurate Object Detection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1589-1604, Aug. 2012, doi:10.1109/TPAMI.2011.247