University of Cambridge

About: University of Cambridge is a education organization based out in Cambridge, United Kingdom. It is known for research contribution in the topics: Population & Galaxy. The organization has 118293 authors who have published 282289 publications receiving 14497093 citations. The organization is also known as: Cambridge University & Cambridge.

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Abstract: We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network [1] . The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN [2] and also with the well known DeepLab-LargeFOV [3] , DeconvNet [4] architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures and can be trained end-to-end using stochastic gradient descent. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. These quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/ .

Interpretation of Raman spectra of disordered and amorphous carbon

Abstract: The model and theoretical understanding of the Raman spectra in disordered and amorphous carbon are given. The nature of the G and D vibration modes in graphite is analyzed in terms of the resonant excitation of \ensuremath{\pi} states and the long-range polarizability of \ensuremath{\pi} bonding. Visible Raman data on disordered, amorphous, and diamondlike carbon are classified in a three-stage model to show the factors that control the position, intensity, and widths of the G and D peaks. It is shown that the visible Raman spectra depend formally on the configuration of the ${\mathrm{sp}}^{2}$ sites in ${\mathrm{sp}}^{2}$-bonded clusters. In cases where the ${\mathrm{sp}}^{2}$ clustering is controlled by the ${\mathrm{sp}}^{3}$ fraction, such as in as-deposited tetrahedral amorphous carbon (ta-C) or hydrogenated amorphous carbon (a-C:H) films, the visible Raman parameters can be used to derive the ${\mathrm{sp}}^{3}$ fraction.

A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking

Abstract: Increasingly, for many application areas, it is becoming important to include elements of nonlinearity and non-Gaussianity in order to model accurately the underlying dynamics of a physical system. Moreover, it is typically crucial to process data on-line as it arrives, both from the point of view of storage costs as well as for rapid adaptation to changing signal characteristics. In this paper, we review both optimal and suboptimal Bayesian algorithms for nonlinear/non-Gaussian tracking problems, with a focus on particle filters. Particle filters are sequential Monte Carlo methods based on point mass (or "particle") representations of probability densities, which can be applied to any state-space model and which generalize the traditional Kalman filtering methods. Several variants of the particle filter such as SIR, ASIR, and RPF are introduced within a generic framework of the sequential importance sampling (SIS) algorithm. These are discussed and compared with the standard EKF through an illustrative example.