IMRA (France)

Lane detection is a crucial task in the automotive industry, forming a fundamental and safety-critical component of autonomous driving systems. Over the years, numerous approaches have been proposed, with the majority relying on convolutional neural networks processing RGB images. While these methods achieve high accuracy and robustness, they come at the cost of significant computational and energy demands, making them unsuitable for real-time operation on power-constrained embedded systems. In this work, we explore an alternative approach leveraging neuromorphic hardware and spiking neural networks to develop a more energy-efficient solution. By designing a lightweight spiking convolutional neural network with only 6365 parameters, we demonstrate that lane detection can be performed with a power consumption of just 12mW, two orders of magnitude lower than the current state-of-the-art. Our work is a new step towards efficient lane detection in resource-limited automotive applications.

Pedestrian recognition is one of the key components for assisted and autonomous driving. So far many researchers have investigated systems combining a high density LIDAR with cameras or stereo, which results in an expensive and complex setup where the LIDAR data is mostly used to extract regions of interest for the 2D sensor. Very few work has focused on using pure 3D data coming from the LIDAR to recognize pedestrians, and even less have made an intensive use of the intensity information returned by the LIDAR. The intensity information displays a high frequency change between neighboring points of similar material, this can be due to the angle or distance. Due to this, it has not been frequently investigated as a potentially interesting feature as it would require extensive time consuming feature engineering to be worthwhile. In this paper we present a novel 2D representation of a 3D point cloud including the intensity information. We show the ability of convolutional neural networks to handle this data in order to accurately recognize pedestrians in complex driving scenes. Our system outperformed state of the art technique on the STC database. Additionally we show that this system is still highly accurate on low density LIDAR data.

In our recently published work, the positive effect of a Ge nanolayer introduced into the processing of Cu2ZnSnSe4 absorbers (CZTSe) was demonstrated. In this contribution, the complete optimizatio ...

Kesterite semiconductors have been successfully employed in thin-film solar cells, with potential for high conversion efficiency solely from abundant materials. Although the best devices have come from mixed sulfo-selenide compounds, the underlying defect physics in this family has remained mysterious. The authors present a comprehensive study of electronic defects as a function of chalcogenide composition, providing a much needed, consistent view of shallow and deep levels in Cu${}_{2}$ZnSn(S,Se)${}_{4}$ and their consequences for device performance.

International audience