Szczegóły publikacji
Opis bibliograficzny
Embedded vision system for pedestrian detection based on HOG+SVM and use of motion information implemented in Zynq heterogeneous device / Bartosz Meus, Tomasz KRYJAK, Marek GORGOŃ // W: SPA 2017 : Signal Processing : Algorithms, Architectures, Arrangements, and Applications : Poznan, 20–22nd September 2017 : conference proceedings / IEEE The Institute of Electrical and Electronics Engineers Inc. Region 8 – Europe, Middle East and Africa. Poland Section, Circuits and Systems Chapter , Poznań University of Technology. Faculty of Computing. Institute of Automation and Robotics. Division of Signal Processing and Electronic Systems. — [Piscataway] : IEEE, [2017]. — W bazie Web of Science ISBN: 978-8-3620-6530-1. — ISBN: 978-83-62065-28-8. — S. 406–411. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 411, Abstr.
Autorzy (3)
Dane bibliometryczne
| ID BaDAP | 108956 |
|---|---|
| Data dodania do BaDAP | 2017-09-29 |
| DOI | 10.23919/SPA.2017.8166901 |
| Rok publikacji | 2017 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | Signal Processing : Algorithms, Architectures, Arrangements, and Applications |
Abstract
Pedestrian detection is a very important application of embedded real-time vision systems. It is essential in Advanced Driver Assistance Systems (ADAS) and Advanced Video Surveillance Systems (AVSS). The most widely used method involves a combination of Histogram of Oriented Gradients (HOG) features and Support Vector Machine (SVM) classifier. It offers quite high detection accuracy at the cost of high computational complexity. Therefore, it is impossible to use GPP-based (General Purpose Processor) embedded systems for this application. In this paper a hardware-software HOG+SVM pedestrian detection system implemented in a heterogeneous Xilinx Zynq device is presented. The base algorithm is supported with detection grouping and tracking procedures. They increase the performance of the solution, especially in case of temporal partially occluded or vague visible objects. The system is able to process a 1280 x 720 @ 60 fps video stream in real-time.