Group cost-sensitive boosting with multi-scale decorrelated filters for pedestrian detection
We propose a novel two-stage pedestrian detection framework that combines multiscale decorrelated filters to extract more discriminative features and a novel group costsensitive boosting algorithm. The proposed boosting algorithm is based on mixture loss to alleviate the influence of annotation erro...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference Paper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147489 |