Szczegóły publikacji
Opis bibliograficzny
Detection-segmentation convolutional neural network for autonomous vehicle perception / Maciej Baczmański, Robert Synoczek, Mateusz WĄSALA, Tomasz KRYJAK // W: MMAR 2023 [Dokument elektroniczny] : 27th international conference on Methods and Models in Automation and Robotics : 22–25 August 2023, Międzyzdroje, Poland : on line proceedings : technical papers. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2023. — (International Conference on Methods and Models in Automation and Robotics ; ISSN 2835-2815). — Dod. ISBN: 979-8-3503-1106-8 (USB), 979-8-3503-1108-2 (print on demand). — e-ISBN: 979-8-3503-1107-5. — S. 117–122. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 122, Abstr. — Publikacja dostępna online od: 2023-09-11
Autorzy (4)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 148543 |
|---|---|
| Data dodania do BaDAP | 2023-10-06 |
| Tekst źródłowy | URL |
| DOI | 10.1109/MMAR58394.2023.10242398 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | International Conference on Methods and Models in Automation and Robotics 2023 |
| Czasopismo/seria | International Conference on Methods and Models in Automation and Robotics |
Abstract
Object detection and segmentation are two core modules of an autonomous vehicle perception system. They should have high efficiency and low latency while reducing computational complexity. Currently, the most commonly used algorithms are based on deep neural networks, which guarantee high efficiency but require high-performance computing platforms. In the case of autonomous vehicles, i.e. cars, but also drones, it is necessary to use embedded platforms with limited computing power, which makes it difficult to meet the requirements described above. A reduction in the complexity of the network can be achieved by using an appropriate: architecture, representation (reduced numerical precision, quantisation, pruning), and computing platform. In this paper, we focus on the first factor – the use of so-called detection-segmentation networks as a component of a perception system. We considered the task of segmenting the drivable area and road markings in combination with the detection of selected objects (pedestrians, traffic lights, and obstacles). We compared the performance of three different architectures described in the literature: MultiTask V3, HybridNets, and YOLOP. We conducted the experiments on a custom dataset consisting of approximately 500 images of the drivable area and lane markings, and 250 images of detected objects. Of the three methods analysed, MultiTask V3 proved to be the best, achieving 99% mAP 50 for detection, 97% MIoU for drivable area segmentation, and 91% MIoU for lane segmentation, as well as 124 fps on the RTX 3060 graphics card. This architecture is a good solution for embedded perception systems for autonomous vehicles. The code is available at: https://github.com/vision-agh/MMAR_2023.
