An improved event-by-event clustering algorithm for noisy acquisition

Lesage, Xavier; Tran, Rosalie; Mancini, Stéphane; Fesquet, Laurent

doi:10.1109/ebccsp56922.2022.9845512

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a continuation of the previous work [ 2 ], the simulator was extended to include the TFS pixels. It consists of two parts (see Figure 2 ): an event stream generator, described below, and the design under test, in our case an event-by-event clustering algorithm (the orange block in Figure 2 ).…”

Section: Event-based Simulatorsmentioning

confidence: 99%

“…See also Figure 5 for a visual representation where the red box represents the cluster, the green box the seek region, the orange dot the center, and the blue arrow the velocity vector. This summarizes the implemented algorithm in the details required to understand the contribution; however, interested readers may refer to [ 2 ].…”

Section: Spatio-temporal Clusteringmentioning

confidence: 99%

“…Event-based algorithms have been developed for many vision tasks, from feature extraction to pattern recognition [ 1 ]. In a previous work [ 2 ], we proposed an event-by-event clustering algorithm that can retrieve the position and size of objects directly from the event stream of a Dynamic Vision Sensor (DVS) camera. With low-power sensing in mind, this work focuses on the low computational cost and small memory footprint of clustering.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Velocity and Color Estimation Using Event-Based Clustering

Lesage,

Tran,

Mancini

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Event-based clustering provides a low-power embedded solution for low-level feature extraction in a scene. The algorithm utilizes the non-uniform sampling capability of event-based image sensors to measure local intensity variations within a scene. Consequently, the clustering algorithm forms similar event groups while simultaneously estimating their attributes. This work proposes taking advantage of additional event information in order to provide new attributes for further processing. We elaborate on the estimation of the object velocity using the mean motion of the cluster. Next, we are examining a novel form of events, which includes intensity measurement of the color at the concerned pixel. These events may be processed to estimate the rough color of a cluster, or the color distribution in a cluster. Lastly, this paper presents some applications that utilize these features. The resulting algorithms are applied and exercised thanks to a custom event-based simulator, which generates videos of outdoor scenes. The velocity estimation methods provide satisfactory results with a trade-off between accuracy and convergence speed. Regarding color estimation, the luminance estimation is challenging in the test cases, while the chrominance is precisely estimated. The estimated quantities are adequate for accurately classifying objects into predefined categories.

show abstract

Section: Event-based Simulatorsmentioning

confidence: 99%

Section: Spatio-temporal Clusteringmentioning

confidence: 99%