Image fusion by considering multimodal partial deep neural networks for self driving during winter

Boisclair, Jonathan; Kélouwani, Sousso; Amamou, Ali; Alam, Muhammad Zeshan; Zeghmi, Lotfi; Agbossou, Kodjo

doi:10.1109/vppc53923.2021.9699335

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finding alternative ways to help mitigate performance degradation in challenging environments is essential. In the study by Boisclair et al [100], the fusion of different image modalities into a single network is proposed as a solution to the performance degradation of neural networks under adverse weather conditions such as snowfall or rainfall. The authors adopt a parallel multimodal network that receives any image modality.…”

Section: Discussionmentioning

confidence: 99%

Analyzing Performance Effects of Neural Networks Applied to Lane Recognition under Various Environmental Driving Conditions

Ortegon-Sarmiento

Kélouwani

Alam

et al. 2022

WEVJ

Self Cite

View full text Add to dashboard Cite

Lane detection is an essential module for the safe navigation of autonomous vehicles (AVs). Estimating the vehicle’s position and trajectory on the road is critical; however, several environmental variables can affect this task. State-of-the-art lane detection methods utilize convolutional neural networks (CNNs) as feature extractors to obtain relevant features through training using multiple kernel layers. It makes them vulnerable to any statistical change in the input data or noise affecting the spatial characteristics. In this paper, we compare six different CNN architectures to analyze the effect of various adverse conditions, including harsh weather, illumination variations, and shadows/occlusions, on lane detection. Among all the aforementioned adverse conditions, harsh weather in general and snowy night conditions particularly affect the performance by a large margin. The average detection accuracy of the networks decreased by 75.2%, and the root mean square error (RMSE) increased by 301.1%. Overall, the results show a noticeable drop in the networks’ accuracy for all adverse conditions because the features’ stochastic distributions change for each state.

show abstract

Section: Discussionmentioning

confidence: 99%