Linear Support Tensor Machine With LSK Channels: Pedestrian Detection in Thermal Infrared Images

Abstract

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.

Context-aware Pedestrian Detection with Salient Region Self-growing in Far-infrared Images

“…The HSC-SRC-ID [4] uses a sparse representation classification. As for other methods, LSK-M3CS [10] uses a linear support tensor machine with LSK channels, achieves 24.64%; HOG-SRC is the old version of [4], achieves 28%; MMSS [2] is a superpixel segmentation method, achieves 32.62%; FLBP [5] uses the variation of LBP features, achieves 33.16%; CMeans-CNN [6] is also based on CNN, achieves 34%.…”

Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives

“…There are two possible scenarios: 1) y m takes a continuous set of values, which leads to the tensor regression problem, and 2) y m P t+1,´1u that is, it takes categorical values, which is a standard classification problem. For the classification case, STM [Biswas and Milanfar, 2016, Hao et al, 2013, Tao et al, 2005 can be formulated through the following minimization problem…”

Generalization ability of region proposal networks for multispectral person detection

“…This is of specific interest when determining the Reasonable subdatasets, in which a person must have a height of 50 pixels or more inside the image. Although the dataset was published several years ago back in 2005 already, annotations for the person detection task were not available until 2017 17 . There are six image sequences in total acquired by a stationary sensor mounted on a building.…”