Scene-dependent proposals for efficient person detection. (March 2019)

• Record Type: Journal Article
• Authors: Bartoli, Federico; Lisanti, Giuseppe; Karaman, Svebor; Bimbo, Alberto Del
• Is Part Of: Pattern recognition. Volume 87(2019:Mar.)
• Page Start: 170
• Page End: 178
• Publication Date: 2019-03
• Subjects: Person detection -- Scene-dependent proposals -- Gaussian mixture model -- Scene modelling; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.10.008
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A solution that provides a substantial speed-up of person detection is proposed. The scene under observation is modelled using a probabilistic mixture distribution. The mixture is learnt in an unsupervised way from the output of a person detector. At runtime the most relevant detection windows are sampled using the scene model. Abstract: In this paper, we present a new method that provides a substantial speed-up of person detection while showing high classification accuracy. Our method learns a Gaussian Mixture Model of locations and scales of the persons in the scene under observation. The model is learnt in an unsupervised way from a set of detections extracted from a small number of frames, so that each component of the mixture represents the expectation of finding a target in a region of the image at a specific scale. At runtime, the windows that most likely contain a person are sampled from the components and evaluated by the classifier. Experimental results show that replacing the classic sliding window approach with our scene-dependent proposals in state of the art person detectors allows us to drastically reduce the computational complexity while granting equal or higher performance in terms of accuracy.