13 April 2018 Aggregated channels network for real-time pedestrian detection
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106960I (2018) https://doi.org/10.1117/12.2309864
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually performed on low-consumption hardware. In order to alleviate this drawback, most strategies focus on using a two-stage cascade approach. Essentially, in the first stage a fast method generates a significant but reduced amount of high quality proposals that later, in the second stage, are evaluated by the CNN. In this work, we propose a novel detection pipeline that further benefits from the two-stage cascade strategy. More concretely, the enriched and subsequently compressed features used in the first stage are reused as the CNN input. As a consequence, a simpler network architecture, adapted for such small input sizes, allows to achieve real-time performance and obtain results close to the state-of-the-art while running significantly faster without the use of GPU. In particular, considering that the proposed pipeline runs in frame rate, the achieved performance is highly competitive. We furthermore demonstrate that the proposed pipeline on itself can serve as an effective proposal generator.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Farzin Ghorban, Farzin Ghorban, Javier Marín, Javier Marín, Yu Su, Yu Su, Alessandro Colombo, Alessandro Colombo, Anton Kummert, Anton Kummert, "Aggregated channels network for real-time pedestrian detection", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106960I (13 April 2018); doi: 10.1117/12.2309864; https://doi.org/10.1117/12.2309864

Back to Top