Efficient Spatial-Temporal Normalization of SAE Representation for Event Camera

Lin, Shijie; Xu, Fang; Wang, Xuhong; Yang, Wen; Yu, Lei

doi:10.1109/lra.2020.2995332

Cited by 8 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first author developed this study's technique in M5 Predicting Precision tournaments. The business-oriented approach may be effective for strategic business planning [24].…”

Section: Related Workmentioning

confidence: 99%

Spatial and Temporal Normalization for Multi-Variate Time Series Prediction Using Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

Multi-variable time series (MTS) information is a typical type of data inference in the real world. Every instance of MTS is produced via a hybrid dynamical scheme, the dynamics of which are often unknown. The hybrid species of this dynamical service are the outcome of high-frequency and low-frequency external impacts, as well as global and local spatial impacts. These influences impact MTS’s future growth; hence, they must be incorporated into time series forecasts. Two types of normalization modules, temporal and spatial normalization, are recommended to accomplish this. Each boosts the original data’s local and high-frequency processes distinctly. In addition, all components are easily incorporated into well-known deep learning techniques, such as Wavenet and Transformer. However, existing methodologies have inherent limitations when it comes to isolating the variables produced by each sort of influence from the real data. Consequently, the study encompasses conventional neural networks, such as the multi-layer perceptron (MLP), complex deep learning methods such as LSTM, two recurrent neural networks, support vector machines (SVM), and their application for regression, XGBoost, and others. Extensive experimental work on three datasets shows that the effectiveness of canonical frameworks could be greatly improved by adding more normalization components to how the MTS is used. This would make it as effective as the best MTS designs are currently available. Recurrent models, such as LSTM and RNN, attempt to recognize the temporal variability in the data; however, as a result, their effectiveness might soon decline. Last but not least, it is claimed that training a temporal framework that utilizes recurrence-based methods such as RNN and LSTM approaches is challenging and expensive, while the MLP network structure outperformed other models in terms of time series predictive performance.

show abstract

“…The first author developed this study's technique in M5 Predicting Precision tournaments. The business-oriented approach may be effective for strategic business planning [24].…”

Section: Related Workmentioning

confidence: 99%

Spatial and Temporal Normalization for Multi-Variate Time Series Prediction Using Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Indeed, instead of searching for features on the whole field of view, the Spike extraction is organized around the pixel of the last incoming Spike, in comparison with the state of the neighboring pixels. This is made possible through the use of SAE (Surface of Active Events), a surface that is updated each time a Spike signal is emitted and that keeps in memory all the last Spikes emitted on each pixel [17]. In this way, we can access the real state of a pixel neighborhood without choosing a temporal discretization.…”

Section: Event-based Corner Detectionmentioning

confidence: 99%

Visual homing guidance for projectiles using event-cameras

Bamond

Hueber

Strub

et al. 2022

Emerging Imaging and Sensing Technologies for Security and Defence VII

View full text Add to dashboard Cite

Compared to frame-based visual streams, event-driven visual streams offer very low bandwidth needs and high temporal resolution, making them an interesting choice for embedded object recognition. Such visual systems are seen to overcome standard cameras performances but have not yet been studied in the frame of Homing Guidance for projectiles, with drastic navigation constraints. This work starts from a first interaction model between a standard camera and an event camera, validated in the context of unattended ground sensors and situational awareness applications from a static position. In this paper we propose to extend this first interaction model by bringing a higher-level activity analysis and object recognition from a moving position. The proposed event-based terminal guidance system is studied firstly through a target laser designation scenario and the optical flow computation to validate guidance parameters. Real-time embedded processing techniques are evaluated, preparing the design of a future demonstrator of a very fast navigation system. The first results have been obtained using embedded Linux architectures with multi-threaded features extractions. This paper shows and comments these first results.

show abstract

“…Other recent normalization methods have been proposed, such as chain SAE [30] and ATSLTD [31]. Although they are both driven asynchronously, the former is more suitable for on-demand tasks, while the latter is used to generate high-contrast artificial frames.…”

Section: B Sae Normalizationmentioning

confidence: 99%

SE-Harris and eSUSAN: Asynchronous Event-Based Corner Detection Using Megapixel Resolution CeleX-V Camera

Li,

Guo,

et al. 2021

Preprint

View full text Add to dashboard Cite

Event cameras are novel neuromorphic vision sensors with ultrahigh temporal resolution and low latency, both in the order of microseconds. Instead of image frames, event cameras generate an asynchronous event stream of perpixel intensity changes with precise timestamps. The resulting sparse data structure impedes applying many conventional computer vision techniques to event streams, and specific algorithms should be designed to leverage the information provided by event cameras. We propose a corner detection algorithm, eSUSAN, inspired by the conventional SUSAN (smallest univalue segment assimilating nucleus) algorithm for corner detection. The proposed eSUSAN extracts the univalue segment assimilating nucleus from the circle kernel based on the similarity across timestamps and distinguishes corner events by the number of pixels in the nucleus area. Moreover, eSUSAN is fast enough to be applied to CeleX-V, the event camera with the highest resolution available. Based on eSUSAN, we also propose the SE-Harris corner detector, which uses adaptive normalization based on exponential decay to quickly construct a local surface of active events and the event-based Harris detector to refine the corners identified by eSUSAN. We evaluated the proposed algorithms on a public dataset and CeleX-V data. Both eSUSAN and SE-Harris exhibit higher realtime performance than existing algorithms while maintaining high accuracy and tracking performance.

show abstract

Efficient Spatial-Temporal Normalization of SAE Representation for Event Camera

Cited by 8 publications

References 20 publications

Spatial and Temporal Normalization for Multi-Variate Time Series Prediction Using Machine Learning Algorithms

Spatial and Temporal Normalization for Multi-Variate Time Series Prediction Using Machine Learning Algorithms

Visual homing guidance for projectiles using event-cameras

SE-Harris and eSUSAN: Asynchronous Event-Based Corner Detection Using Megapixel Resolution CeleX-V Camera

Contact Info

Product

Resources

About