Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images

TL;DR

This paper introduces a novel CNN-based method for cross-view gait recognition using silhouette sequences, employing feature map pooling to improve feature aggregation and recognition accuracy.

Contribution

It proposes a new network architecture that extracts and aggregates features from gait silhouette sequences, outperforming existing methods in accuracy.

Findings

Effective feature extraction and aggregation from silhouette sequences.

Achieves significant equal error rates and high identification rates.

Demonstrates superiority over state-of-the-art methods.

Abstract

In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images. The network takes a pair of arbitrary length sequence images as inputs and extracts features for each silhouette independently. Then a feature map pooling strategy is adopted to aggregate sequence features. Subsequently, a network which is similar to Siamese network is designed to perform recognition. The proposed network is simple and easy to implement and can be trained in an end-to-end manner. Cross-view gait recognition experiments are conducted on OU-ISIR large population dataset. The results demonstrate that our network can extract and aggregate features from silhouette sequence effectively. It also achieves significant equal error rates and comparable identification rates when compared with the state of the art.