This paper investigates the performance of event-based vision sensors under adverse weather conditions relevant to ADAS applications. Through controlled tests across varying rainfall rates, fog visibility levels, ambient light, and target distances, the study evaluates how rain and fog affect sensor output and shows how camera settings can help mitigate rain-related effects.
IDS and Prophesee have signed a Letter of Intent to deepen collaboration on next-generation industrial vision systems combining conventional imaging with event-based sensing for faster, more accurate and power-efficient machine vision.
Terranet’s new BlincVision MVP leverages Prophesee’s event-based vision to deliver ultra-low-latency sensing for safer urban mobility and improved hazard detection.
This paper presents an event-based opto-tactile skin, a neuromorphic tactile sensing system that integrates dual dynamic vision sensors (DVS) with a flexible optical waveguide to enable high-speed, low-latency touch detection over large areas of soft robotic surfaces. The system leverages sparse event streams for press localization, using clustering-based triangulation to achieve accurate tactile mapping with minimal computational overhead. Experimental results demonstrate reliable contact detection and localization across a 100 cm² sensing area, highlighting its potential for real-time, energy-efficient soft robotics applications.
This paper introduces SkyShield, an event-driven framework for detecting submillimeter-scale thin obstacles—such as steel wires and kite strings—that endanger autonomous drones in complex environments. Using the high temporal resolution of event-based cameras, SkyShield leverages a lightweight U-Net and a novel Dice-Contour Regularization Loss to accurately capture thin structures in event streams. Experiment results show a mean F1 score of 0.7088 with 21.2 ms latency, making the approach well suited for real-time, edge, and mobile drone applications.