Real-time pedestrian recognition on low computational resources

TL;DR

This paper develops and compares three methods for real-time pedestrian recognition on low-resource small devices, achieving over 95% accuracy and 5 fps speed on a 1.8 GHz CPU.

Contribution

It introduces optimized LBP, HOG, and CNN-based methods tailored for low-power, small hardware platforms for pedestrian detection.

Findings

All three methods achieved over 95% accuracy.

Each method reached more than 5 frames per second.

The approaches are compatible with small mobile devices.

Abstract

Pedestrian recognition has successfully been applied to security, autonomous cars, Aerial photographs. For most applications, pedestrian recognition on small mobile devices is important. However, the limitations of the computing hardware make this a challenging task. In this work, we investigate real-time pedestrian recognition on small physical-size computers with low computational resources for faster speed. This paper presents three methods that work on the small physical size CPUs system. First, we improved the Local Binary Pattern (LBP) features and Adaboost classifier. Second, we optimized the Histogram of Oriented Gradients (HOG) and Support Vector Machine. Third, We implemented fast Convolutional Neural Networks (CNNs). The results demonstrate that the three methods achieved real-time pedestrian recognition at an accuracy of more than 95% and a speed of more than 5 fps on a small physical size computational platform with a 1.8 GHz Intel i5 CPU. Our methods can be easily applied to small mobile devices with high compatibility and generality.