Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras

Baldwin, R. Wes; Almatrafi, Mohammed; Kaufman, Jason R.; Asari, Vijayan K.; Hirakawa, Keigo

doi:10.1007/978-3-030-27272-2_35

Cited by 22 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the proposed use of distance surface would benefit from denoising randomly activated events. Denoising used in this work is a modified version of the filtering proposed in [52]. In this work, event t i (X) is classified into one of the following three categories: Background Activity (BA), Inceptive Event (IE), or Trailing Event (TE).…”

Section: Robustness Analysis and Denoisingmentioning

confidence: 99%

See 1 more Smart Citation

Distance Surface for Event-Based Optical Flow

Almatrafi

Baldwin

Aizawa

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

We propose DistSurf-OF, a novel optical flow method for neuromorphic cameras. Neuromorphic cameras (or event detection cameras) are an emerging sensor modality that makes use of dynamic vision sensors (DVS) to report asynchronously the log-intensity changes (called "events") exceeding a predefined threshold at each pixel. In absence of the intensity value at each pixel location, we introduce a notion of "distance surface"-the distance transform computed from the detected events-as a proxy for object texture. The distance surface is then used as an input to the intensity-based optical flow methods to recover the two dimensional pixel motion. Real sensor experiments verify that the proposed DistSurf-OF accurately estimates the angle and speed of each events.

show abstract

Section: Robustness Analysis and Denoisingmentioning

confidence: 99%

“…In recognition tasks, it was demonstrated empirically that IE was shown to be most useful for describing object shapes [52]. In our work, however, we are concerned about the negative impact of random activations (BA) on the distance surfaces.…”

Section: Robustness Analysis and Denoisingmentioning

confidence: 99%

Distance Surface for Event-Based Optical Flow

Almatrafi

Baldwin

Aizawa

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since their introduction, neuromorphic cameras have proven useful in simultaneous localization and mapping (SLAM) [37,46], optical flow [2,8,48], depth estimation [14,49], space applications [15,17], tactile sensing [33,39], autonomous navigation [30,41], and object classification [4,6,10,21,34]. Many approaches rely on hand-crafted features such as [16,26,27,32,44], while other applications use deep learning architectures trained using simulated data [38,42].…”

Section: Neuromorphic Camerasmentioning

confidence: 99%

“…Edge arrival typically generates multiple events. The first event is called an "inceptive event" (IE) [4] and coincides with the edge's exact moment of arrival. Events directly following IE are called "trailing events" (TE), representing edge magnitude.…”

Section: Denoisingmentioning

confidence: 99%

See 1 more Smart Citation

Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras

Baldwin

Almatrafi

Asari

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a novel method for labeling realworld neuromorphic camera sensor data by calculating the likelihood of generating an event at each pixel within a short time window, which we refer to as "event probability mask" or EPM. Its applications include (i) objective benchmarking of event denoising performance, (ii) training convolutional neural networks for noise removal called "event denoising convolutional neural network" (EDnCNN), and (iii) estimating internal neuromorphic camera parameters. We provide the first dataset (DVSNOISE20) of real-world labeled neuromorphic camera events for noise removal.

show abstract

KF-PEV: a causal Kalman filter-based particle event velocimetry

AlSattam,

Mongin,

Grose

et al. 2024

Exp Fluids

View full text Add to dashboard Cite

Event-based pixel sensors asynchronously report changes in log-intensity in microsecond-order resolution. Its exceptional speed, cost effectiveness, and sparse event stream make it an attractive imaging modality for particle tracking velocimetry. In this work, we propose a causal Kalman filter-based particle event velocimetry (KF-PEV). Using the Kalman filter model to track the events generated by the particles seeded in the flow medium, KF-PEV yields the linear least squares estimate of the particle track velocities corresponding to the flow vector field. KF-PEV processes events in a computationally efficient and streaming manner (i.e., causal and iteratively updating). Our simulation-based benchmarking study with synthetic particle event data confirms that the proposed KF-PEV outperforms the conventional frame-based particle image/tracking velocimetry as well as the state-of-the-art event-based particle velocimetry methods. In a real-world water tunnel event-based sensor data experiment performed on what we believe to be the widest field view ever reported, KF-PEV accurately predicted the expected flow field of the SD7003 wing, including details such as the lower velocity in the wake and the flow separation around the underside of an angled wing.

show abstract

Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras

Cited by 22 publications

References 17 publications

Distance Surface for Event-Based Optical Flow

Distance Surface for Event-Based Optical Flow

Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras

KF-PEV: a causal Kalman filter-based particle event velocimetry

Contact Info

Product

Resources

About