Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Images
This work addresses pedestrian detection for safety applications in thermal imaging, but it is incremental as it builds on existing maximum margin frameworks and sliding window methodologies.
The authors tackled pedestrian detection in low-resolution, noisy thermal infrared images by proposing a mid-level attribute using Local Steering Kernel descriptors and a new image similarity kernel within a support vector machine framework, achieving a relatively short training phase and very fast detection via multichannel discrete Fourier transform.
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.