Loading...
Send to Friend
 Bookmark
 Review List
  1. Semantic segmentation using events and combination of events and frames (Property)
  2. Simple search
  3. Search result
Semantic segmentation using events and combination of events and frames
72 viewed

Semantic segmentation using events and combination of events and frames

Ghasemzadeh, M

Semantic segmentation using events and combination of events and frames

Ghasemzadeh, M ; Sharif University of Technology | 2023

72 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/978-3-031-43763-2_10
  3. Publisher: Springer Science and Business Media Deutschland GmbH , 2023
  4. Abstract:
  5. Event cameras are bio-inspired sensors. They have outstanding properties compared to frame-based cameras: high dynamic range (120 vs 60), low latency, and no motion blur. Event cameras are appropriate to use in challenging scenarios such as vision systems in self-driving cars and they have been used for high-level computer vision tasks such as semantic segmentation and depth estimation. In this work, we worked on semantic segmentation using an event camera for self-driving cars. i) This work introduces a new event-based semantic segmentation network and we evaluate our model on DDD17 dataset and Event-Scape dataset which was produced using Carla simulator. ii) Event-based networks are robust to lighting conditions but their accuracy is low compared to common frame-based networks, for boosting the accuracy we propose a novel event-frame-based semantic segmentation network that it uses both images and events. We also introduce a novel training method (blurring module), and results show our training method boosts the performance of the network in recognition of small and far objects, and also the network could work when images suffer from blurring. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG
  6. Keywords:
  7. Computer vision ; Event-based camera ; Self-driving cars ; Semantic segmentation ; Sensor fusion
  8. Source: Communications in Computer and Information Science ; Volume 1883 CCIS , 2023 , Pages 167-181 ; 18650929 (ISSN); 978-303143762-5 (ISBN)
  9. URL: https://link.springer.com/chapter/10.1007/978-3-031-43763-2_10