ACE: An Efficient Asynchronous Corner Tracker for Event Cameras

Alzugaray, Ignacio; Chli, Margarita

doi:10.1109/3dv.2018.00080

Cited by 53 publications

(52 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We could therefore obtain invariance by normalizing the times of the events according to their local speed. However, normalization techniques suitable for intensity images cannot be applied to the time surface, as explained in [3]. [3] proposed to sort the times of the events in a local patch.…”

Section: Speed Invariant Time Surfacementioning

confidence: 99%

See 1 more Smart Citation

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Manderscheid

Sironi

Bourdis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions. Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range. However, the properties of event-based data are very different compared to standard intensity images, and simple extensions of corner detection methods designed for these images do not perform well on event-based data. We first introduce an efficient way to compute a time surface that is invariant to the speed of the objects. We then show that we can train a Random Forest to recognize events generated by a moving corner from our time surface. Random Forests are also extremely efficient, and therefore a good choice to deal with the high capture frequency of event-based cameras-our implementation processes up to 1.6Mev/s on a single CPU. Thanks to our time surface formulation and this learning approach, our method is significantly more robust to abrupt changes of direction of the corners compared to previous ones. Our method also naturally assigns a confidence score for the corners, which can be useful for postprocessing. Moreover, we introduce a highresolution dataset suitable for quantitative evaluation and comparison of corner detection methods for event-based cameras. We call our approach SILC, for Speed Invariant Learned Corners, and compare it to the state-of-the-art with extensive experiments, showing better performance.

show abstract

Section: Speed Invariant Time Surfacementioning

confidence: 99%

“…Normalization Speed Invariant Time Surface method of [3] Time Surface Figure 4: Different types of Time Surfaces for two different patches. The two last methods achieve similar results with a high contrast around the edge in comparison with the standard Time Surface.…”

Section: Standardmentioning

confidence: 99%

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Manderscheid

Sironi

Bourdis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Alzugaray and Chli [2], and later Manderscheid et al in the evaluation of [17], established local correspondence of corners based on the proximity of the detections. Using a more complex strategy, the work in [1] retrieved feature tracks considering a set of multiple hypotheses per each asynchronously detected corner in the event stream.…”

Section: Related Workmentioning

confidence: 99%

“…However, instead of artificially accumulating events between tracking iterations, we implement an event-by-event approach that is able to process each event asynchronously. The method is inspired by [1] in the way that we explore different hypotheses per feature, but does not require from the detection of corners events and is able to process the raw event stream.…”

Section: Related Workmentioning

confidence: 99%

“…Other works, such as [7] attempt to manually label the correct tracks, but this approach does not scale well as the scenes become more complex. An alternative would be to benchmark different tacking algorithms inspecting how 1 github.com/daniilidis-group/event_feature_tracking they perform in a generic VO pipeline able to process eventdata, e.g. [27].…”

Section: Benchmarking Of Event-based Trackersmentioning

confidence: 99%

See 1 more Smart Citation

Asynchronous Multi-Hypothesis Tracking of Features with Event Cameras

Alzugaray

Chli

2019

2019 International Conference on 3D Vision (3DV)

Self Cite

View full text Add to dashboard Cite

With the emergence of event cameras, increasing research effort has been focusing on processing the asynchronous stream of events. With each event encoding a discrete intensity change at a particular pixel, uniquely time-stamped with high accuracy, this sensing information is so fundamentally different to the data provided by traditional frame-based cameras that most of the wellestablished vision algorithms are not applicable. Inspired by the need of effective event-based tracking, this paper addresses the tracking of generic patch features relying solely on events, while exploiting their asynchronicity and hightemporal resolution. The proposed approach outperforms the state-of-the-art in event-based feature tracking on wellestablished event camera datasets, retrieving longer and more accurate feature tracks at higher a frequency. Considering tracking as an optimization problem of matching the current view to a feature template, the proposed method implements a simple and efficient technique that only requires the evaluation of a discrete set of tracking hypotheses.

show abstract

Investigating University-Based Science and Technology for Creating World-Class Technology-Oriented Higher Education in China

Xue

Jian

2020

Perspectives on Rethinking and Reforming Education

View full text Add to dashboard Cite

We present CEIA, an effective framework for open-world event-based understanding. Currently training a large event-text model still poses a huge challenge due to the shortage of paired event-text data. In response to this challenge, CEIA learns to align event and image data as an alternative instead of directly aligning event and text data. Specifically, we leverage the rich event-image datasets to learn an event embedding space aligned with the image space of CLIP through contrastive learning. In this way, event and text data are naturally aligned via using image data as a bridge. Particularly, CEIA offers two distinct advantages. First, it allows us to take full advantage of the existing event-image datasets to make up the shortage of large-scale event-text datasets. Second, leveraging more training data, it also exhibits the flexibility to boost performance, ensuring scalable capability. In highlighting the versatility of our framework, we make extensive evaluations through a diverse range of event-based multi-modal applications, such as object recognition, event-image retrieval, event-text retrieval, and domain adaptation. The outcomes demonstrate CEIA's distinct zero-shot superiority over existing methods on these applications.

show abstract

ACE: An Efficient Asynchronous Corner Tracker for Event Cameras

Cited by 53 publications

References 22 publications

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Asynchronous Multi-Hypothesis Tracking of Features with Event Cameras

Investigating University-Based Science and Technology for Creating World-Class Technology-Oriented Higher Education in China

Contact Info

Product

Resources

About