Variational Pedestrian Detection
This addresses the problem of occluded pedestrian detection for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles pedestrian detection in crowded scenes by formulating it as a variational inference problem, resulting in a method that improves performance on datasets like CrowdHuman and CityPersons, with notable gains for both single-stage and two-stage detectors.
Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization of our proposed algorithm, a classical detector can be fashioned into a variational pedestrian detector. Experiments conducted on CrowdHuman and CityPersons datasets show that the proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stage detectors. Our method can also be flexibly applied to two-stage detectors, achieving notable performance enhancement.