A Multi-Cluster Tracking Algorithm with an Event Camera

Aladem, Mohamed; Rawashdeh, Samir A.

doi:10.1109/naecon46414.2019.9058204

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The camera point of view should be a top-down view, looking down at the ground, so that the objects are supposed to be not or slightly deformable. To account for deformation, further processing of the clusters are required such as cluster fusion [ 17 , 18 ] or probability distributions that handle occlusions [ 19 ].…”

Section: Event-based Image Sensorsmentioning

confidence: 99%

“…The work of Lagorce et al [ 25 ] and the improvement by Aladem et al [ 18 ] use bivariate Gaussian distributions to describe the event clusters, and the events are distributed in the cluster based on the maximum likelihood. Another example of such a clustering algorithm is the work of Barranco et al [ 26 ] that uses Kalman filters to smoothen trajectories.…”

Section: Spatio-temporal Clusteringmentioning

confidence: 99%

“…The aforementioned clustering algorithm can incorporate a velocity estimation using the cluster property. The work of Aladem et al [ 18 ] refers to utilize velocity, with a focus on angular estimation, when merging clusters that move in the same direction to create a larger, singular cluster. In this case, the velocity is estimated using the covariance matrix of the cluster representation.…”

Section: Velocity Estimationmentioning

confidence: 99%

“…As we constrain ourselves to low-power, low-calculation applications, the outcomes are less accurate compared to the values cited in [ 12 , 30 ]. Neither [ 18 ] nor [ 24 ] report the angular error, but we consider an angular error of less than 20 sufficient for exit detection and the estimation of rough trajectory. Moreover, errors are primarily attributed to outliers in the error distribution.…”

Section: Velocity Estimationmentioning

confidence: 99%

See 3 more Smart Citations

Velocity and Color Estimation Using Event-Based Clustering

Lesage,

Tran,

Mancini

et al. 2023

Sensors

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 Image Sensorsmentioning

confidence: 99%