Self-Supervised Optical Flow with Spiking Neural Networks and Event Based Cameras

• Published in: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) pp. 5892 - 5899
• Main Authors: Chaney, Kenneth, Panagopoulou, Artemis, Lee, Chankyu, Roy, Kaushik, Daniilidis, Kostas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 27.09.2021
• Subjects: Cameras; Computer vision; Encoding; Image motion analysis; Low latency communication; Robot vision systems; Sensors

Optical flow can be leveraged in robotic systems for obstacle detection where low latency solutions are critical in highly dynamic settings. While event-based cameras have changed the dominant paradigm of sending by encoding stimuli into spike trails, offering low bandwidth and latency, events are s...