Heterogeneous sensor data fusion for multiple object association using belief functions

Laghmara, Hind; Laurain, Thomas; Cudel, Christophe; Lauffenburger, Jean-Philippe

doi:10.1016/j.inffus.2019.11.002

Cited by 20 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are, however, situations in which this assumption cannot be guaranteed to be verified. Consider, for instance, the data association problem [12,30], in which agents collect sensor information about a set of objects. Before this information can be combined, we need to match the objects perceived by each pair of agents.…”

Section: Robust Combinationmentioning

confidence: 99%

See 1 more Smart Citation

Distributed combination of belief functions

Denœux

2021

Information Fusion

View full text Add to dashboard Cite

We consider the problem of combining belief functions in a situation where pieces of evidence are held by agents at the node of a communication network, and each agent can only exchange information with its neighbors. Using the concept of weight of evidence, we propose distributed implementations of Dempster's rule and the cautious rule based, respectively, on average and maximum consensus algorithms. We also describe distributed procedures whereby the agents can agree on a frame of discernment and a list of supported hypotheses, thus reducing the amount of data to be exchanged in the network. Finally, we show the feasibility of a robust combination procedure based on a distributed implementation of the random sample consensus (RANSAC) algorithm.

show abstract

Section: Robust Combinationmentioning

confidence: 99%

“…where max ν selects the ν largest in a set. By iteratively applying (30), each β j (t) converges to the set β = {β (1) , . .…”

Section: Distributed Implementationmentioning

confidence: 99%

Distributed combination of belief functions

Denœux

2021

Information Fusion

View full text Add to dashboard Cite

show abstract

“…It assumes that all information sources are reliable and cognitively independent, and most other rules in the literature try to depart from these two assumptions, such as the disjunctive Dubois-Prade's rule [10] that relaxes the need for reliability, or idempotent conjunctive rules [4], [5], [11] that relax the independence assumption. The combination rules are widely applied in data fusion applications, such as [12], [13], etc.…”

Section: Introductionmentioning

confidence: 99%

On Computing Evidential Centroid Through Conjunctive Combination: An Impossibility Theorem

Zhang

Destercke

Zhang

et al. 2023

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

The theory of belief functions (TBF) is now a widespread framework to deal and reason with uncertain and imprecise information, in particular to solve information fusion and clustering problems. Combination functions (rules) and distances are essential tools common to both the clustering and information fusion problems in the context of TBF, which have generated considerable literature. Distances and combination between evidence corpus of TBF are indeed often used within various clustering and classification algorithms, however their interplay and connections have seldom been investigated, which is the topic of this paper. More precisely, we focus on the problem of aggregating evidence corpus to obtain a representative one, and we show through an impossibility theorem that in this case, there is a fundamental contradiction between the use of conjunctive combination rules on the one hand, and the use of distances on the other hand. Rather than adding new methodologies, such results are instrumental in guiding the user among the many methodologies that already exist. To illustrate the interest of our results, we discuss different cases where they are at play. Impact Statement-Within the theory of belief functions, both distances and conjunctive combination rules can be used to achieve very similar purposes: evaluating the conflict between sources, performing supervised or unsupervised learning in presence of evidential information, or more simply obtaining a synthetic representation of multiple items of information. However, the results obtained by both approaches may show some inconsistency between them. This paper provides some insight as to why this may happen, showing that the two approaches are definitely at odds, and that using distances is, for instance, incompatible with some fundamental notions of the theory of belief functions, such as the least commitment principle. We illustrate the importance of the studied differences on problems such as k-centroid clustering, and discuss the importance of interpretations in such problems, which is rarely done in the literature.

show abstract

“…The robustness to weather condition of radar is limited by its low accuracy. Thus, the cons of one modality need to be complemented by the pros of the other by multi-modal sensor fusion [8], [9]. The fusion can be at early, middle or late stage of the processing pipeline [3].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Architecture Reduction on Camera-Lidar Fusion for Autonomous Vehicles

Geletu

Josso-Laurain

Devanne

et al. 2022

2022 2nd International Conference on Computers and Automation (CompAuto)

View full text Add to dashboard Cite

Autonomous vehicles (AVs) are the dream of the present era and are close to become reality. In AVs, perception is a challenging task. It gives understanding of the driving environment. One type of such task is road detection, where the goal is to segment the road area into drivable and nondrivable using multi-modal sensors like cameras and lidars. For their ability on a road detection task, deep neural networks, with an encoder-decoder architecture, are chosen in this paper. Since deep learning models have large size and AVs have constrained computational power, model reduction is important. Therefore, architecture reduction of a convolutional neural network is proposed on a deep learning based multi-modal fusion model. This model is used as the baseline of our work, and camera and lidar are its modalities. The baseline model's weights that are used to fuse the camera processing pipeline with the lidar pipeline are analysed. The analysis shows that the strength of fusion between the two modalities changes from layer to layer. Using this result and a support from generic encoder-decoder architecture, a reduced architecture is proposed. The latter is further processed by removing some layers of the baseline to produce a lite model. The reduced architectures are validated to show comparable performance with the baseline. Furthermore, both the reduced architectures outperform the baseline on a brightness adjusted camera image. These reduced architectures can be used from the perspective of embedded system, or they can be used to boost performance by appending additional algorithm.The training and validation are done on the KITTI dataset.

show abstract

Heterogeneous sensor data fusion for multiple object association using belief functions

Cited by 20 publications

References 18 publications

Distributed combination of belief functions

Distributed combination of belief functions

On Computing Evidential Centroid Through Conjunctive Combination: An Impossibility Theorem

Deep Learning Based Architecture Reduction on Camera-Lidar Fusion for Autonomous Vehicles

Contact Info

Product

Resources

About