We report the object-recognition performance of VGG16, ResNet, and SqueezeNet, three state-of-the-art Convolutional Neural Networks (CNNs) trained on ImageNet, across 15 different lighting conditions using the Phos dataset and a ResNet-like network trained on Pascal VOC on the ExDark dataset. The instabilities in the normalized softmax values are used to highlight that pre-trained networks are not...Show More
The Internet of Things is poised to transform lighting from a simple illumination source, which is most often taken for granted, into a smart and data-rich infrastructure for the cities. To this end, we propose the Lighting-Enabled Smart City APplications and Ecosystems (LENSCAPEs) framework. LENSCAPEs involve i) city-wide wireless Outdoor Lighting Networks (OLNs), to connect the streetlights usin...Show More
