Human Attribute Analysis Using a Top-View Camera Based on Two-Stage Classification

Abstract

SUMMARYThis paper presents a technique that analyzes pedestrians' attributes such as gender and bag-possession status from surveillance video. One of the technically challenging issues is that we use only topview camera images to protect privacy. The shape features over the frames are extracted by bag-of-features (BoF) using histogram of oriented gradients (HoG) vectors. In order to enhance the classification accuracy, a two-staged classification framework is presented. Multiple classifiers are trained by changing the parameters in the first stage. The outputs from the first stage is further trained and classified in the second stage classifier. The experiments using 60-minute video captured at Haneda Airport, Japan, show that the accuracies for the gender classification and the bagpossession classification were 95.8% and 97.2%, respectively, which is a significant improvement from our previous work.

Headgear Accessories Classification Using an Overhead Depth Sensor

“…However, none of the previous works use depth information only or top-view images, and thus do not take into account the privacy issues so sensible in surveillance applications. On the other hand, the work in [ 12 ] proposes an approach for human attribute analysis, such as gender and whether they have bags with them, based on multi-layer classification, and using top-view RGB camera images. In our case, we still want to avoid the use of RGB data for privacy consideration issues.…”