Xidian University

About: Xidian University is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Antenna (radio) & Computer science. The organization has 32099 authors who have published 38961 publications receiving 431820 citations. The organization is also known as: University of Electronic Science and Technology at Xi'an & Xīān Diànzǐ Kējì Dàxué.

Traffic flow time series prediction based on statistics learning theory

Abstract: For intelligent transportation systems, a new traffic flow time series prognostication is proposed in this paper. Compared with classical methods, support vector machine has a good generalize ability for limited training samples, which has a characteristic of rapid convergence and avoiding the local minimum. At the end of this paper, the simulation experiment for the traffic flow of one practice crossing proves the validity and efficiency and high application value in traffic flow prediction.

Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation

Abstract: Recently, the research field of salient object detection is undergoing a rapid and remarkable development along with the wide usage of deep neural networks. Being trained with a large number of images annotated with strong pixel-level ground-truth masks, the deep salient object detectors have achieved the state-of-the-art performance. However, it is expensive and time-consuming to provide the pixel-level ground-truth masks for each training image. To address this problem, this paper proposes one of the earliest frameworks to learn deep salient object detectors without requiring any human annotation. The supervisory signals used in our learning framework are generated through a novel supervision synthesis scheme, in which the key insights are “knowledge source transition” and “supervision by fusion”. Specifically, in the proposed learning framework, both the external knowledge source and the internal knowledge source are explored dynamically to provide informative cues for synthesizing supervision required in our approach, while a two-stream fusion mechanism is also established to implement the supervision synthesis process. Comprehensive experiments on four benchmark datasets demonstrate that the deep salient object detector trained by our newly proposed learning framework often works well without requiring any human annotated masks, which even approaches to its upper-bound obtained under the fully supervised learning fashion (within only 3 percent performance gap). Besides, we also apply the salient object detector learnt with our annotation-free learning framework to assist the weakly supervised semantic segmentation task, which demonstrates that our approach can also alleviate the heavy supplementary supervision required in the existing weakly supervised semantic segmentation framework.

New ISAR imaging algorithm based on modified Wigner–Ville distribution

Abstract: Inverse synthetic aperture radar (ISAR) imaging of air, space or ship targets with complex motion has attracted the attention of many researchers in the past decade. Complex motion of targets induce cross-range scatterer-variant quadratic phase terms, which will degrade the cross-range resolution and affect focusing quality. A new algorithm is proposed for the ISAR imaging of complex moving targets. First, conventional range alignment, phase compensation and range compression are performed over the raw phase history data such that each range bin can be modelled as the sum of several linear frequency modulation or chirp signals. Secondly, a modified-Wigner-Ville distribution (referred to as M-WVD) approach is proposed, which is based on a scale transform in the time-frequency distribution plane and can effectively suppress the troublesome cross-term interference associated with WVD via coherent integration. Finally, the azimuth ISAR image can be obtained via a simple maximisation projection from the two-dimensional accumulated plot to the azimuth dimension. Compared with existing WVD-based ISAR imaging algorithms, the proposed method has the following features: better cross-term interference reduction achieved at no resolution loss, computationally more efficient with no expensive two-dimensional parameter search, and higher signal processing gain because of coherent integration during the whole imaging time. Both numerical and experimental results are provided to demonstrate the performance of the proposed method.

Performance Evaluation of IEEE 802.15.4 for Wireless Body Area Network (WBAN)

Abstract: IEEE 802.15.4 is a current major technology for low-rate low-power wireless networks. To study the applicability of IEEE 802.15.4 over a wireless body area network (WBAN), in this paper we evaluate its three different access schemes' performance through several metrics. Considering the coexistence of contention access period (CAP) and contention-free period (CFP), we also study the mutual influences of these two traffics. The results show the unslotted mode has better performance than the slotted one in terms of throughput and latency but with the cost of much power consumption. In addition, the guaranteed time slot (GTS) in CFP can not guarantee the successful transmission of the CFP frames without sufficient GTS allocation. Finally, we give the suggestions for the novel medium access control (MAC) design for a WBAN.

Corner Detection and Classification Using Anisotropic Directional Derivative Representations

Abstract: This paper proposes a corner detector and classifier using anisotropic directional derivative (ANDD) representations. The ANDD representation at a pixel is a function of the oriented angle and characterizes the local directional grayscale variation around the pixel. The proposed corner detector fuses the ideas of the contour- and intensity-based detection. It consists of three cascaded blocks. First, the edge map of an image is obtained by the Canny detector and from which contours are extracted and patched. Next, the ANDD representation at each pixel on contours is calculated and normalized by its maximal magnitude. The area surrounded by the normalized ANDD representation forms a new corner measure. Finally, the nonmaximum suppression and thresholding are operated on each contour to find corners in terms of the corner measure. Moreover, a corner classifier based on the peak number of the ANDD representation is given. Experiments are made to evaluate the proposed detector and classifier. The proposed detector is competitive with the two recent state-of-the-art corner detectors, the He & Yung detector and CPDA detector, in detection capability and attains higher repeatability under affine transforms. The proposed classifier can discriminate effectively simple corners, Y-type corners, and higher order corners.