Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Images

TL;DR

This paper introduces a novel tensor-based pedestrian detection method in thermal infrared images, utilizing local geometry descriptors, a new similarity kernel, and Fourier-based localization for improved speed and accuracy.

Contribution

It presents a new tensor attribute with LSK descriptors, a novel similarity kernel for SVMs, and a Fourier transform-based detection approach, advancing thermal pedestrian detection.

Findings

Effective detection in noisy thermal images

Faster detection via Fourier transform

Public release of annotated thermal dataset

Abstract

Pedestrian detection in thermal infrared images poses unique challenges because of the low resolution and noisy nature of the image. Here we propose a mid-level attribute in the form of multidimensional template, or tensor, using Local Steering Kernel (LSK) as low-level descriptors for detecting pedestrians in far infrared images. LSK is specifically designed to deal with intrinsic image noise and pixel level uncertainty by capturing local image geometry succinctly instead of collecting local orientation statistics (e.g., histograms in HOG). Our second contribution is the introduction of a new image similarity kernel in the popular maximum margin framework of support vector machines that results in a relatively short and simple training phase for building a rigid pedestrian detector. Our third contribution is to replace the sluggish but de facto sliding window based detection methodology with multichannel discrete Fourier transform, facilitating very fast and efficient pedestrian localization. The experimental studies on publicly available thermal infrared images justify our proposals and model assumptions. In addition, the proposed work also involves the release of our in-house annotations of pedestrians in more than 17000 frames of OSU Color Thermal database for the purpose of sharing with the research community.