Y
Yang Chen
Researcher at HRL Laboratories
Publications - 71
Citations - 1295
Yang Chen is an academic researcher from HRL Laboratories. The author has contributed to research in topics: Object detection & Neuromorphic engineering. The author has an hindex of 13, co-authored 71 publications receiving 1063 citations. Previous affiliations of Yang Chen include General Motors.
Papers
More filters
Journal ArticleDOI
Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
TL;DR: A novel approach for converting a deep CNN into a SNN that enables mapping CNN to spike-based hardware architectures and evaluates the resulting SNN on publicly available Defense Advanced Research Projects Agency (DARPA) Neovision2 Tower and CIFAR-10 datasets and shows similar object recognition accuracy as the original CNN.
Patent
Vision system for monitoring humans in dynamic environments
James W. Wells,Roland J. Menassa,Charles W. Wampler,Swarup Medasani,Yuri Owechko,Kyungnam Kim,Yang Chen +6 more
TL;DR: In this paper, a safety monitoring system for a workspace area is proposed, where a plurality of vision-based imaging devices capture time-synchronized image data of the workspace area.
Patent
Rapid object detection by combining structural information from image segmentation with bio-inspired attentional mechanisms
Lei Zhang,Shinko Y. Cheng,Yang Chen,Alexander L. Honda,Kyungnam Kim,Deepak Khosla,Changsoo S. Jeong +6 more
TL;DR: In this paper, a system for rapid object detection combining structural information with bio-inspired attentional mechanisms is described, where an input image is oversegmented into a set of superpixels, where each superpixel comprises a plurality of pixels, and a bounding box defining a region of the input image representing a detection hypothesis is determined.
Patent
Robust static and moving object detection system via attentional mechanisms
Alexander L. Honda,Deepak Khosla,Yang Chen,Kyungnam Kim,Shinko Y. Cheng,Lei Zhang,Changsoo S. Jeong +6 more
TL;DR: In this article, a multi-scale attentional mechanism is used for object detection via multi-modal attentional mechanisms, where anti-aliasing and downsampling processes are performed to reduce the size of the multi-band image.
Patent
System for representing, storing, and reconstructing an input signal
TL;DR: In this paper, a system for representing, storing, and reconstructing an input signal is described, which constructs an index of unique polychronous groups (PCGs) from a spiking neuron network, and a basis set of spike codes is generated from the unique PCGs.