In this paper, we present SEVD, a first-of-its-kind multi-view ego, and fixed perception synthetic event-based dataset using multiple dynamic vision sensors within the CARLA simulator. We evaluate the dataset using state-of-the-art event-based (RED, RVT) and frame-based (YOLOv8) methods for traffic participant detection tasks and provide baseline benchmarks for assessment.
Prophesee et Bpifrance investissent 15 millions d’euros pour le développement d’une nouvelle génération de capteurs neuromorphique, fabriqués en France, destinés à l’IA embarquée dans 1,3 milliard de smartphones.
In this work, we present our exploration of optimizing event-based neural network inference on SENECA, a scalable and flexible neuromorphic architecture. Our optimizations for event-based neural networks can be potentially generalized to a wide range of event-based neuromorphic processors.
This research is the first to investigate the impact of bias modifications on the event-based DMS output and propose an approach for evaluating and comparing DMS performance. The study investigates the impact of pixel-bias alteration on DMS features, which are: face tracking, blink counting, head pose and gaze estimation. The results indicate that the DMS’s functioning is enhanced with proper bias tuning based on the proposed metrics.
This study proposes an innovative approach leveraging neuromorphic sensor technology to enhance traffic monitoring efficiency while still exhibiting robust performance when exposed to difficult conditions. The quantitative evaluation of the ability of event-based models to generalize on nighttime and unseen scenes further substantiates the compelling potential of leveraging event cameras for trac monitoring, opening new avenues for research and application.