Search

This work proposes LDVS, a learnable binary local descriptor devised for matching natural images within the MPEG CDVS framework. LDVS descriptors are learned so that they can be sign-quantized and compared using the Hamming distance. The underlying convolutional architecture enjoys a moderate parameters count for operations on mobile devices. Our experiments show that LDVS descriptors perform favorably over comparable learned binary descriptors at patch matching on two different datasets. A complete pair-wise image matching pipeline is then designed around LDVS descriptors, integrating them in the reference CDVS evaluation framework. Experiments show that LDVS descriptors outperform the compressed CDVS SIFT-like descriptors at pair-wise image matching over the challenging CDVS image dataset. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder–decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers’ statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. [ABSTRACT FROM AUTHOR]

The realization of a deep neural architecture on a mobile platform is challenging, but can open up a number of possibilities for visual analysis applications. A neural network can be realized on a mobile platform by exploiting the computational power of the embedded GPU and simplifying the flow of a neural architecture trained on the desktop workstation or a GPU server. This paper presents an embedded platform-based Italian license plate detection and recognition system using deep neural classifiers. In this work, trained parameters of a highly precise automatic license plate recognition (ALPR) system are imported and used to replicate the same neural classifiers on a Nvidia Shield K1 tablet. A CUDA-based framework is used to realize these neural networks. The flow of the trained architecture is simplified to perform the license plate recognition in real-time. Results show that the tasks of plate and character detection and localization can be performed in real-time on a mobile platform by simplifying the flow of the trained architecture. However, the accuracy of the simplified architecture would be decreased accordingly. [ABSTRACT FROM AUTHOR]

Convolution is the most computationally intensive task of the Convolutional Neural Network (CNN). It requires a lot of memory storage and computational power. There are different approaches to compute the solution of convolution and reduce its computational complexity. In this paper, a matrix multiplication-based convolution (ConvMM) approach is fully parallelized using concurrent resources of GPU (Graphics Processing Unit) and optimized, considerably improving the performance of the image classifiers and making them applicable to real-time embedded applications. The flow of this CUDA (Compute Unified Device Architecture)-based scheme is optimized using unified memory and hardware-dependent acceleration of matrix multiplication. Proposed flow is evaluated on two different embedded platforms: first on an Nvidia Jetson TX1 embedded board and then on a Tegra K1 GPU of an Nvidia Shield K1 Tablet. The performance of this optimized and accelerated convolutional layer is compared with its sequential and heterogeneous versions. Results show that the proposed scheme significantly improves the overall results including energy efficiency, storage requirement and inference performance. In particular, the proposed scheme on embedded GPUs is hundreds of times faster than the sequential version and delivers tens of times higher performance than the heterogeneous approach. [ABSTRACT FROM AUTHOR]