This article presents a two-staged approach to recognize pedestrians in video sequences on board of a moving vehicle. The system combines the advantages of two feature families by splitting the recognition process into two stages: In the first stage, a fast search mechanism based on simple features is applied to detect interesting regions. The second stage uses a computationally more expensive, but also more accurate set of features on these regions to classify them into pedestrian and non-pedestrian. We compared various feature extraction configurations of different complexities regarding classification performance and speed. The complete system was evaluated on a number of labeled test videos taken from real-world drives and also compared against a publicly available pedestrian detector. This first system version analyzes only single image frames without using any temporal information like tracking. Still, it achieves good recognition performance at reasonable run time.
Abstract. In this article, we present a fast pedestrian detection system for driving assistance. We use current state-of-the-art HOG and LBP features and combine them into a set of powerful classifiers. We propose an encoding scheme that enables LBP to be used efficiently with the integral image approach. This way, HOG and LBP block features can be computed in constant time, regardless of block position or scale. To further speed up the detection process, a coarse-to-fine scanning strategy based on input resolution is employed. The original camera resolution is consecutively downsampled and fed to different stage classifiers. Early stages in low resolutions reject most of the negative candidate regions, while few samples are passed through all stages and are evaluated by more complex features. Results presented on the INRIA set show competetive accuracy performance, while both processing and training time of our system outperforms current state-of-the-art work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.