Paper Info
Title
SOFEA: A Non-iterative and Robust Optical Flow Estimation Algorithm for Dynamic Vision Sensors
Abstract
We introduce the single-shot optical flow estimation algorithm (SOFEA) to non-iteratively compute the continuous-time flow information of events produced from bio-inspired cameras such as the dynamic vision sensor (DVS). The output of a DVS is a stream of asynchronous spikes ("events"), transmitted at very minimal latency (1-10 μs), caused by local brightness changes. Due to this unconventional output, a continuous representation of events over time is invaluable to most applications using the DVS. To this end, SOFEA consolidates the spatio-temporal information on the surface of active events for flow estimation in a single-shot manner, as opposed to iterative methods in the literature. In contrast to previous works, this is also the first principled method towards finding locally optimal set of neighboring events for plane fitting using an adaptation of Prim's algorithm. Consequently, SOFEA produces flow estimates that are more accurate across a wide variety of scenes compared to state-of-the-art methods. A direct application of such flow estimation is rendering sharp event images using the set of active events at a given time, which is further demonstrated and compared to existing works (source code will be made available at our homepage after the review process).
Year
DOI
Venue
2020
10.1109/CVPRW50498.2020.00049
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Keywords
DocType
ISSN
sharp event image rendering,plane fitting,first principled method,asynchronous spikes,noniterative optical flow estimation algorithm,robust optical flow estimation algorithm,Prim algorithm,neighboring events,iterative methods,active events,spatio-temporal information,continuous representation,local brightness changes,DVS,bio-inspired cameras,continuous-time flow information,SOFEA,single-shot optical flow estimation algorithm,dynamic vision sensor,time 1.0 mus to 10.0 mus
Conference
2160-7508
ISBN
Citations 
PageRank 
978-1-7281-9361-8
0
0.34
References 
Authors
10
4
Name
Order
Citations
PageRank
Weng Fei Low100.34
Zhi Gao23310.15
Cheng Xiang355139.85
Ramesh Bharath4478.96