Aggregated Channels Network for Real-Time Pedestrian Detection

TL;DR

This paper introduces a novel CNN-based pedestrian detection pipeline that reuses enriched features for faster, real-time performance on low-power hardware, achieving results close to state-of-the-art without GPUs.

Contribution

It proposes a new detection pipeline that leverages feature reuse and a simplified network for real-time pedestrian detection on low-resource devices.

Findings

Achieves real-time pedestrian detection without GPU.

Runs at frame rate with competitive accuracy.

Serves as an effective proposal generator.

Abstract

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually performed on low-consumption hardware. In order to alleviate this drawback, most strategies focus on using a two-stage cascade approach. Essentially, in the first stage a fast method generates a significant but reduced amount of high quality proposals that later, in the second stage, are evaluated by the CNN. In this work, we propose a novel detection pipeline that further benefits from the two-stage cascade strategy. More concretely, the enriched and subsequently compressed features used in the first stage are reused as the CNN input. As a consequence, a simpler network architecture, adapted for such small input sizes, allows to achieve real-time performance and obtain results close to the state-of-the-art while running significantly faster without the use of GPU. In particular, considering that the proposed pipeline runs in frame rate, the achieved performance is highly competitive. We furthermore demonstrate that the proposed pipeline on itself can serve as an effective proposal generator.