Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313124159> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4313124159 abstract "Autonomous Driving (AD) related features represent important elements for the next generation of mobile robots and autonomous vehicles focused on increasingly intelligent, autonomous, and interconnected systems. The applications involving the use of these features must provide, by definition, real-time decisions, and this property is key to avoid catastrophic accidents. Moreover, all the decision processes must require low power consumption, to increase the lifetime and autonomy of battery-driven systems. These challenges can be addressed through efficient implementations of Spiking Neural Networks (SNNs) on Neuromorphic Chips and the use of event-based cameras instead of traditional frame-based cameras. In this paper, we present a new SNN-based approach, called LaneSNN, for detecting the lanes marked on the streets using the event-based camera input. We develop four novel SNN models characterized by low complexity and fast response, and train them using an offline supervised learning rule. Afterward, we implement and map the learned SNNs models onto the Intel Loihi Neuromorphic Research Chip. For the loss function, we develop a novel method based on the linear composition of Weighted binary Cross Entropy (WCE) and Mean Squared Error (MSE) measures. Our experimental results show a maximum Intersection over Union (IoU) measure of about 0.62 and very low power consumption of about 1 W. The best IoU is achieved with an SNN implementation that occupies only 36 neurocores on the Loihi processor while providing a low latency of less than 8 ms to recognize an image, thereby enabling real-time performance. The IoU measures provided by our networks are comparable with the state-of-the-art, but at a much low power consumption of 1 W." @default.
- W4313124159 created "2023-01-06" @default.
- W4313124159 creator A5014762265 @default.
- W4313124159 creator A5028540594 @default.
- W4313124159 creator A5042642081 @default.
- W4313124159 creator A5057618925 @default.
- W4313124159 creator A5078077776 @default.
- W4313124159 date "2022-10-23" @default.
- W4313124159 modified "2023-10-16" @default.
- W4313124159 title "LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor" @default.
- W4313124159 cites W1829670322 @default.
- W4313124159 cites W2085261163 @default.
- W4313124159 cites W2169353679 @default.
- W4313124159 cites W2563705555 @default.
- W4313124159 cites W2783525259 @default.
- W4313124159 cites W2940734441 @default.
- W4313124159 cites W2972000740 @default.
- W4313124159 cites W2973083016 @default.
- W4313124159 cites W2984844508 @default.
- W4313124159 cites W2999350649 @default.
- W4313124159 cites W3010825489 @default.
- W4313124159 cites W3084892460 @default.
- W4313124159 cites W3091431973 @default.
- W4313124159 cites W3108426037 @default.
- W4313124159 cites W3112139896 @default.
- W4313124159 cites W3119639195 @default.
- W4313124159 cites W3196320736 @default.
- W4313124159 cites W3198957722 @default.
- W4313124159 doi "https://doi.org/10.1109/iros47612.2022.9981034" @default.
- W4313124159 hasPublicationYear "2022" @default.
- W4313124159 type Work @default.
- W4313124159 citedByCount "4" @default.
- W4313124159 countsByYear W43131241592023 @default.
- W4313124159 crossrefType "proceedings-article" @default.
- W4313124159 hasAuthorship W4313124159A5014762265 @default.
- W4313124159 hasAuthorship W4313124159A5028540594 @default.
- W4313124159 hasAuthorship W4313124159A5042642081 @default.
- W4313124159 hasAuthorship W4313124159A5057618925 @default.
- W4313124159 hasAuthorship W4313124159A5078077776 @default.
- W4313124159 hasBestOaLocation W43131241592 @default.
- W4313124159 hasConcept C113775141 @default.
- W4313124159 hasConcept C11731999 @default.
- W4313124159 hasConcept C121332964 @default.
- W4313124159 hasConcept C149635348 @default.
- W4313124159 hasConcept C151927369 @default.
- W4313124159 hasConcept C154945302 @default.
- W4313124159 hasConcept C163258240 @default.
- W4313124159 hasConcept C2779662365 @default.
- W4313124159 hasConcept C2984118289 @default.
- W4313124159 hasConcept C41008148 @default.
- W4313124159 hasConcept C50644808 @default.
- W4313124159 hasConcept C62520636 @default.
- W4313124159 hasConcept C76155785 @default.
- W4313124159 hasConcept C79403827 @default.
- W4313124159 hasConcept C82876162 @default.
- W4313124159 hasConceptScore W4313124159C113775141 @default.
- W4313124159 hasConceptScore W4313124159C11731999 @default.
- W4313124159 hasConceptScore W4313124159C121332964 @default.
- W4313124159 hasConceptScore W4313124159C149635348 @default.
- W4313124159 hasConceptScore W4313124159C151927369 @default.
- W4313124159 hasConceptScore W4313124159C154945302 @default.
- W4313124159 hasConceptScore W4313124159C163258240 @default.
- W4313124159 hasConceptScore W4313124159C2779662365 @default.
- W4313124159 hasConceptScore W4313124159C2984118289 @default.
- W4313124159 hasConceptScore W4313124159C41008148 @default.
- W4313124159 hasConceptScore W4313124159C50644808 @default.
- W4313124159 hasConceptScore W4313124159C62520636 @default.
- W4313124159 hasConceptScore W4313124159C76155785 @default.
- W4313124159 hasConceptScore W4313124159C79403827 @default.
- W4313124159 hasConceptScore W4313124159C82876162 @default.
- W4313124159 hasLocation W43131241591 @default.
- W4313124159 hasLocation W43131241592 @default.
- W4313124159 hasOpenAccess W4313124159 @default.
- W4313124159 hasPrimaryLocation W43131241591 @default.
- W4313124159 hasRelatedWork W2885510266 @default.
- W4313124159 hasRelatedWork W3010477810 @default.
- W4313124159 hasRelatedWork W3090951784 @default.
- W4313124159 hasRelatedWork W3157350647 @default.
- W4313124159 hasRelatedWork W3157535122 @default.
- W4313124159 hasRelatedWork W3158120979 @default.
- W4313124159 hasRelatedWork W4294690999 @default.
- W4313124159 hasRelatedWork W4385488572 @default.
- W4313124159 hasRelatedWork W4385805109 @default.
- W4313124159 hasRelatedWork W4386227293 @default.
- W4313124159 isParatext "false" @default.
- W4313124159 isRetracted "false" @default.
- W4313124159 workType "article" @default.