Scene-dependent proposals for efficient person detection

作者：

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.

摘要

•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.

论文关键词：Person detection,Scene-dependent proposals,Gaussian mixture model,Scene modelling

论文评审过程：Received 29 October 2016, Revised 26 June 2018, Accepted 8 October 2018, Available online 9 October 2018, Version of Record 22 October 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.10.008