National University of Defense Technology

About: National University of Defense Technology is a education organization based out in Changsha, China. It is known for research contribution in the topics: Radar & Synthetic aperture radar. The organization has 39430 authors who have published 40181 publications receiving 358979 citations. The organization is also known as: Guófáng Kēxuéjìshù Dàxué & NUDT.

Inshore Ship Detection via Saliency and Context Information in High-Resolution SAR Images

Abstract: So far, the detection of ships on sea has been widely studied, while fewer works are available on inshore ship detection. Due to the high similarity between the harbor and the ship body on gray and texture features, the traditional methods are unable to achieve effective detection of inshore ships. In this letter, we present a novel approach via saliency and context information to deal with this issue. First, we employ the superpixel-generating algorithm to generate the superpixel region. Second, we propose a new method based on the salient region detection to complete the inshore ship detection. Finally, a ship discrimination framework is presented to remove the false alarm. The experimental results demonstrate the noise robustness and effectiveness of the proposed approach using synthetic aperture radar (SAR) images and real SAR images.

Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA

Abstract: Three-dimensional convolutional neural networks (3D CNNs) are used efficiently in many computer vision applications. Most previous work in this area has concentrated only on designing and optimizing accelerators for 2D CNN, with few attempts made to accelerate 3D CNN on FPGA. We find accelerating 3D CNNs on FPGA to be challenge due to their high computational complexity and storage demands. More importantly, although the computation patterns of 2D and 3D CNNs are analogous, the conventional approaches adopted for accelerating 2D CNNs may be unfit for 3D CNN acceleration. In this paper, in order to accelerate 2D and 3D CNNs using a uniform framework, we propose a uniform template-based architecture that uses templates based on the Winograd algorithm to ensure fast development of 2D and 3D CNN accelerators. Furthermore, we also develop a uniform analytical model to facilitate efficient design space explorations of 2D and 3D CNN accelerators based on our architecture. Finally, we demonstrate the effectiveness of the template-based architecture by implementing accelerators for real-life 2D and 3D CNNs (VGG16 and C3D) on multiple FPGA platforms. On S2C VUS440, we achieve up to 1.13 TOPS and 1.11 TOPS under low resource utilization for VGG16 and C3D, respectively. End-to-end comparisons with CPU and GPU solutions demonstrate that our implementation of C3D achieves gains of up to 13x and 60x in performance and energy relative to a CPU solution, and a 6.4x energy efficiency gain over a GPU solution.

Hundred-watt-level high power random distributed feedback Raman fiber laser at 1150 nm and its application in mid-infrared laser generation.

Abstract: Two kinds of hundred-watt-level random distributed feedback Raman fiber have been demonstrated. The optical efficiency can reach to as high as 84.8%. The reported power and efficiency of the random laser is the highest one as we know. We have also demonstrated that the developed random laser can be further used to pump a Ho-doped fiber laser for mid-infrared laser generation. Finally, 23 W 2050 nm laser is achieved. The presented laser can obtain high power output efficiently and conveniently and opens a new direction for high power laser sources at designed wavelength.

Autoscanning for coupled scene reconstruction and proactive object analysis

Abstract: Detailed scanning of indoor scenes is tedious for humans. We propose autonomous scene scanning by a robot to relieve humans from such a laborious task. In an autonomous setting, detailed scene acquisition is inevitably coupled with scene analysis at the required level of detail. We develop a framework for object-level scene reconstruction coupled with object-centric scene analysis. As a result, the autoscanning and reconstruction will be object-aware, guided by the object analysis. The analysis is, in turn, gradually improved with progressively increased object-wise data fidelity. In realizing such a framework, we drive the robot to execute an iterative analyze-and-validate algorithm which interleaves between object analysis and guided validations. The object analysis incorporates online learning into a robust graph-cut based segmentation framework, achieving a global update of object-level segmentation based on the knowledge gained from robot-operated local validation. Based on the current analysis, the robot performs proactive validation over the scene with physical push and scan refinement, aiming at reducing the uncertainty of both object-level segmentation and object-wise reconstruction. We propose a joint entropy to measure such uncertainty based on segmentation confidence and reconstruction quality, and formulate the selection of validation actions as a maximum information gain problem. The output of our system is a reconstructed scene with both object extraction and object-wise geometry fidelity.