Abstract
The objective of this article is to study the problem of pedestrian classification across different light spectrum domains (visible and far-infrared (FIR)) and modalities (intensity, depth and motion). In recent years, there has been a number of approaches for classifying and detecting pedestrians in both FIR and visible images, but the methods are difficult to compare, because either the datasets are not publicly available or they do not offer a comparison between the two domains. Our two primary contributions are the following: (1) we propose a public dataset, named RIFIR , containing both FIR and visible images collected in an urban environment from a moving vehicle during daytime; and (2) we compare the state-of-the-art features in a multi-modality setup: intensity, depth and flow, in far-infrared over visible domains. The experiments show that features families, intensity self-similarity (ISS), local binary patterns (LBP), local gradient patterns (LGP) and histogram of oriented gradients (HOG), computed from FIR and visible domains are highly complementary, but their relative performance varies across different modalities. In our experiments, the FIR domain has proven superior to the visible one for the task of pedestrian classification, but the overall best results are obtained by a multi-domain multi-modality multi-feature fusion.
Highlights
The main purpose of constructing intelligent vehicles is to increase the safety for all traffic participants
Our objective is to analyse the relative performance of the state-of-the-art features, including a feature representation the we proposed in our previous work [28], called intensity self-similarity, for pedestrian classification in a multi-modality multi-domain setup
Our main contribution is that we considered the intensity, depth and flow modalities, on the multi-domain axis, considering in addition to the visible domain, the far-infrared one
Summary
The main purpose of constructing intelligent vehicles is to increase the safety for all traffic participants. In this context, pedestrian protection systems have become a necessity. Like Light Detection And Ranging (LiDAR) [1,2,3], work independently of ambient light and give as output a 3D map, they tend to have a low resolution that makes the task of pedestrian hypothesis classification difficult, which is an important module of a pedestrian detection system. Passive sensors, represented by visible and infrared cameras, due to the low cost and high resolution, are by far the most used sensors for pedestrian detection systems, but they require complex processing algorithms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
