ABSTRACT
The concept of "video" is synonymous with frame-sequence image representations. However, neuromorphic "event" cameras, which are rapidly gaining adoption for computer vision tasks, record frameless video. We believe that these different paradigms of video capture can each benefit from the lessons of the other. To usher in the next era of video systems and accommodate new event camera designs, we argue that we will need an asynchronous, source-agnostic processing pipeline. In this paper, we propose an end-to-end framework for frameless video, and we describe its modularity and amenability to compression and both existing and future applications.
- Andrew C. Freeman, Chris Burgess, and Ketan Mayer-Patel. 2021. Motion Segmentation and Tracking for Integrating Event Cameras. In Proceedings of the 12th ACM Multimedia Systems Conference (Istanbul, Turkey) (MMSys '21). Association for Computing Machinery, New York, NY, USA, 1--11. Google ScholarDigital Library
- Andrew C. Freeman, Montek Singh, and Ketan Mayer-Patel. 2023. An Asynchronous Intensity Representation for Framed and Event Video Sources. Google ScholarCross Ref
- G. Gallego, T. Delbruck, G. M. Orchard, C. Bartolozzi, B. Taba, A. Censi, S. Leutenegger, A. Davison, J. Conradt, K. Daniilidis, and D. Scaramuzza. 2020. Event-based Vision: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020), 1--1. Google ScholarDigital Library
- P. Lichtsteiner, C. Posch, and T. Delbruck. 2006. A 128 X 128 120db 30mw asynchronous vision sensor that responds to relative intensity change. In 2006 IEEE International Solid State Circuits Conference - Digest of Technical Papers. 2060--2069.Google Scholar
- Sherif A. S. Mohamed, Jawad N. Yasin, Mohammad-Hashem Haghbayan, Antonio Miele, Jukka Heikkonen, Hannu Tenhunen, and Juha Plosila. 2020. Asynchronous Corner Tracking Algorithm Based on Lifetime of Events for DAVIS Cameras. In Advances in Visual Computing, George Bebis, Zhaozheng Yin, Edward Kim, Jan Bender, Kartic Subr, Bum Chul Kwon, Jian Zhao, Denis Kalkofen, and George Baciu (Eds.). Springer International Publishing, Cham, 530--541.Google Scholar
- Zhaoqing Pan, Sam Kwong, Yun Zhang, Jianjun Lei, and Hui Yuan. 2014. Fast Coding Tree Unit depth decision for high efficiency video coding. In 2014 IEEE International Conference on Image Processing (ICIP). 3214--3218. Google ScholarCross Ref
- David Tedaldi, Guillermo Gallego, Elias Mueggler, and Davide Scaramuzza. 2016. Feature detection and tracking with the dynamic and active-pixel vision sensor (DAVIS). In 2016 Second International Conference on Event-based Control, Communication, and Signal Processing (EBCCSP). 1--7. Google ScholarCross Ref
Index Terms
- The ADΔER Framework: Tools for Event Video Representations
Recommendations
An Asynchronous Intensity Representation for Framed and Event Video Sources
MMSys '23: Proceedings of the 14th ACM Multimedia Systems ConferenceNeuromorphic "event" cameras, designed to mimic the human vision system with asynchronous sensing, unlock a new realm of high-speed and high-dynamic-range applications. However, researchers often either revert to a framed representation of event data for ...
An Open Software Suite for Event-Based Video
MMSys '24: Proceedings of the 15th ACM Multimedia Systems ConferenceWhile traditional video representations are organized around discrete image frames, event-based video is a new paradigm that forgoes image frames altogether. Rather, pixel samples are temporally asynchronous and independent of one another. Until now, ...
Accelerated Event-Based Feature Detection and Compression for Surveillance Video Systems
MMSys '24: Proceedings of the 15th ACM Multimedia Systems ConferenceThe strong temporal consistency of surveillance video enables compelling compression performance with traditional methods, but downstream vision applications operate on decoded image frames with a high data rate. Since it is not straightforward for ...
Comments