Pedestrian Attribute Classification in Surveillance: Database and Evaluation

Attributes are helpful to infer high-level semantic knowledge of pedestrians, thus improving the performance of pedestrian tracking, retrieval, re-identification, etc. However, current pedestrian databases are mainly for the pedestrian detection or tracking application, and semantic attribute annotations related to pedestrians are rarely provided. In this paper, we construct an Attributed Pedestrians in Surveillance (APiS) database with various scenes. The APiS 1.0 database includes 3661 images with 11 binary and 2 multi-class attribute annotations. Moreover, we develop an evaluation protocol for researchers to evaluate pedestrian attribute classification algorithms. With the APiS 1.0 database, we present two baseline methods, one for binary attribute classification and the other for multi-class attribute classification. For binary attribute classification, we train AdaBoost classifiers with color and texture features, while for multi-class attribute classification, we adopt a weighted K Nearest Neighbors (KNN) classifier with color features. Finally, we report and discuss the baseline performance on the APiS 1.0 database following the proposed evaluation protocol.

1. Introduction

In the past two decades, there is an explosive growth in surveillance video applications in the world. Surveillance cameras are installed in many places such as airports, train stations, parking lots, banks, etc. The videos captured by these cameras are very massive which presents formidable challenges for people to search useful information. Therefore, the smart video surveillance technology [21] has been used to process online video in real time for saving expensive human resources. Video analysis is a key module for smart video surveillance, including object detection [12], [25], object tracking [26], and object classification [13], etc. Figure 1. Thirty pedestrian examples in our database. Images in red rectangles are three examples of pedestrians with female and short hair attributes.