Semantic segmentation is an important computer vision task, particularly for scene understanding and navigation of autonomous vehicles and UAVs. Several variations of deep neural network architectures have been designed to tackle this task. However, due to their huge computational costs and their high memory consumption, these models are not meant to be deployed on resource-constrained systems. To address this limitation, we introduce an end-to-end biologically inspired semantic segmentation approach by combining Spiking Neural Networks (SNNs, a low-power alternative to classical neural networks) with event cameras whose output data can directly feed these neural network inputs. We have designed EvSegSNN, a biologically plausible encoder-decoder U-shaped architecture relying on Parametric Leaky Integrate and Fire neurons in an objective to trade-off resource usage against performance. The experiments conducted on DDD17 demonstrate that EvSegSNN outperforms the closest state-of-the-art model in terms of MIoU while reducing the number of parameters by a factor of $1.6$ and sparing a batch normalization stage.
Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network
Propulsion and Space Research Center (PSRC) at the Technology Innovation Institute (TII)(技术创新研究所推进与空间研究中心(PSRC));Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University of Science and Technology(哈利法科技大学自主机器人系统中心(KUCARS),哈利法科技大学);Advanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology(哈利法科技大学先进研究与创新中心(ARIC),哈利法科技大学)
A Neuromorphic Dataset for Object Segmentation in Indoor Cluttered Environment
Advanced Research and Innovation Center (ARIC), Khalifa University(哈利法大学高级研究与创新中心(ARIC));Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University(哈利法大学自主机器人系统中心(KUCARS));School of Computer Science and Mathematics, Kingston University(金斯顿大学计算机科学与数学学院);Department of Aerospace Engineering, Khalifa University(哈利法大学航空航天工程系)
Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation
Institute of Automation, Chinese Academy of Sciences (CAS)(中国科学院自动化研究所);Research Center for Brain-inspired Intelligence, Institute of Automation, CAS(中国科学院自动化研究所类脑智能研究中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院);National Laboratory of Pattern Recognition, Institute of Automation, CAS(中国科学院自动化研究所模式识别国家重点实验室)
EventHDR: from Event to High-Speed HDR Videos and Beyond
Beijing Institute of Technology(北京理工大学);School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);University of Tsukuba(筑波大学);Next Generation Artificial Intelligence Research Center, the University of Tokyo(东京大学下一代人工智能研究中心)
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology(地质灾害预防与地质环境保护国家重点实验室,成都理工大学);Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province, Chengdu University of Technology(四川省应用核技术地质科学重点实验室,成都理工大学);Engineering & Technical College of Chengdu University of Technology(成都理工大学工程与技术学院);Southwestern Institute of Physics(西南物理研究院);Chengdu University(成都大学)
Wandering around: A bioinspired approach to visual attention through object motion sensitivity
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague(捷克技术大学普拉茨分校电子工程系);IBM Research Europe, Zurich, Switzerland(IBM欧洲研究院,瑞士苏黎世);Italian Institute of Technology, Genoa, Italy(意大利理工学院,热那亚);National Research Council of Canada & Systems Design Engineering, University of Waterloo, Canada(加拿大国家研究理事会与系统设计工程,滑铁卢大学);European Space Agency, Noordwijk, The Netherlands(欧洲航天局,荷兰诺德维克);Adapsent, Leiden, The Netherlands(Adapsent,荷兰莱顿)