According to the problem that conventional laminated paper counting algorithms have some unavoidable shortcomings such as high dependence on the quality of laminated paper and noise sensitivity, we propose a laminated...
详细信息
ISBN:
(纸本)9781479953004
According to the problem that conventional laminated paper counting algorithms have some unavoidable shortcomings such as high dependence on the quality of laminated paper and noise sensitivity, we propose a laminated paper counting algorithm based on compressive sensing (CS) and Hough transform (HT). In the proposed algorithm, the over-complete dictionary which is created by dispersing the Hough transform space of straight lines acts as the sparse matrix. Making use of high degree of sparse nature of the laminated paper image, we can obtain the accurate result through using CS theory. Experimental results on simulation images and laminated paper images have shown that our proposed algorithm can effectively restrain noise of the laminated paper image, and will get accurate experimental results with fewer CS measurements.
We present an online learned framework for multiple target tracking in a crowded scene. The tracking problem is formulated as a detection-based progressive association task. Firstly, reliable tracklets are generated b...
详细信息
ISBN:
(纸本)9781479957521
We present an online learned framework for multiple target tracking in a crowded scene. The tracking problem is formulated as a detection-based progressive association task. Firstly, reliable tracklets are generated by low level constraints among detection responses. Then longer tracklets associations are generated based on online learned Hough forest framework which effectively combines motion and appearance information for discrimination between two tracklets. In online learning scene, the association is formulated as a MAP problem and training examples are collected based on spatial-temporal constraints. In order to alleviate the drifting problem of online learning, Hungarian algorithm is employed to modify associated errors and update the training set. The experimental results show the effectiveness of our approach.
Network coding (NC) is one of the promising techniques to improve network throughput towards the Shannon limit. NC has been proven to be able to achieve the max-flow min-cut bound for single source multicast networks....
详细信息
ISBN:
(纸本)9781479949212
Network coding (NC) is one of the promising techniques to improve network throughput towards the Shannon limit. NC has been proven to be able to achieve the max-flow min-cut bound for single source multicast networks. For multi-information-source multicast networks, however, the question of how to use NC is still to be answered. In this paper we will focus on the simple case of multi-information-source independent network encoding. The region of admissible rate set of this case will be provided. With this rate region obtained, more advanced network encoding algorithms for multi-information source multicast networks can be further developed.
Human action recognition technology has been applied to intelligent security surveillance, content-based image and video retrieval and natural user interface. How to make use of the new type of data, 3D skeleton joint...
Human action recognition technology has been applied to intelligent security surveillance, content-based image and video retrieval and natural user interface. How to make use of the new type of data, 3D skeleton joint position extracted by 3D depth camera, has been a highly active research topic. A posture representation model is proposed, which is invariant to limb length, length ratio between body parts and body orientation. This model contains polar angle and azimuthal angle of each limb in the spherical coordinate system which is established by the features of body joints. Hidden Markov Model（HMM） is exploited for recognition. Skeleton sequences of different body orientation are collected as experimental data. Experimental results demonstrate the effectiveness of our approach.
OvTDM is a new transmission scheme that can obtain high spectral efficiency with very low threshold signal noise ratio (SNR) by using the inter symbol interference (ISI). Fano algorithm (FA) is researched in this pape...
详细信息
ISBN:
(纸本)9781510804166
OvTDM is a new transmission scheme that can obtain high spectral efficiency with very low threshold signal noise ratio (SNR) by using the inter symbol interference (ISI). Fano algorithm (FA) is researched in this paper to implement fast ML decoding at high spectral efficiency for OvTDM. Numerical results show that the complexity of OvTDM with FA has no relationship with the number of state which is lower than 15% of that of Viterbi algorithm and the bit SNR loss is under 2 dB. Moreover, OvTDM with FA can even outperform Shannon limit when spectral is above 6.7 bits/s/Hz.
In recent years, Wireless sensor network (WSNs) has become the main technology to construct underground network for intelligent mining system. Due to the complex roadway topology, there needs an optimized energy conse...
详细信息
In recent years, Wireless sensor network (WSNs) has become the main technology to construct underground network for intelligent mining system. Due to the complex roadway topology, there needs an optimized energy conservation routing protocol. We proposed EERP, an energy-efficient routing protocol for for WSN-based intelligent mining system, which can prolonged lifetime of a network and reduce energy consumption through construct a dominator chain by region partition. Simulation results show that EERP has 8.2 times stable working time than LEACH. When region length is 100m, EERP still can maintain 99% energy after 3000rd transmission.
Moving cast shadow detection is an active research field with improving the performance of moving object detection. In this paper, we propose a novel cast shadow detection method by exploiting the local texture simila...
Moving cast shadow detection is an active research field with improving the performance of moving object detection. In this paper, we propose a novel cast shadow detection method by exploiting the local texture similarity and the intensity ratio effectively between the shadow and background patches. Firstly, local texture analysis of the initial moving patches is carried out using local binary patterns , and a part of moving object pixels and shadow pixels will be detected exactly. Then, the residual moving pixels are classified by the intensity ratio. Consequently, moving shadow pixels and moving object pixels are located respectively. Specially, post processing is employed to adjust error pixels acquired through the first two steps. In order to prove the efficiency and feasibility, comparable experiments are performed and the results validate that it can detect the shadow pixels more accurately and completely than some state-of-the-art methods.
Workflow is commonly used in e-commerce system as modeling method. In this paper, we proposed W2ME, a process-oriented meta model for OTO-oriented e-commerce. W2ME bases on the traditional activity network model and e...
详细信息
ISBN:
(纸本)9781479929528
Workflow is commonly used in e-commerce system as modeling method. In this paper, we proposed W2ME, a process-oriented meta model for OTO-oriented e-commerce. W2ME bases on the traditional activity network model and extends it. Based on the principle of minimum privileges in the authorization problem, W2ME propose the W2MEA algorithm which effectively reduces the complexity for authority management. Simulation results show that W2ME can save 20% CPU occupancy time and has 95th percentile average success rate.
As in computational geometry, CAD/CAM and computer graphics, the basic algorithm of computing of the area of the union of circles is widely used in many fields. In order to solve the problems of judging constraint arc...
详细信息
As in computational geometry, CAD/CAM and computer graphics, the basic algorithm of computing of the area of the union of circles is widely used in many fields. In order to solve the problems of judging constraint arcs' direction vaguely and computing some overlap region's area repeatedly on [2], this paper proposes an improved algorithm for computing the area of union of circles. The improved algorithm can calculate united area of circles with distribution at any possible positions, and experimental comparison shows that the algorithm not only solves those problems, but also has more reliability.
Memory is a fundamental component in human brain and plays very important roles for all mental processes. The analysis of memory systems through cognitive architectures can be performed at the computational, or functi...
详细信息
Memory is a fundamental component in human brain and plays very important roles for all mental processes. The analysis of memory systems through cognitive architectures can be performed at the computational, or functional level, on the basis of empirical data. In this paper we discuss memory systems in the extended Consciousness and Memory Model (CAM) The knowledge representations used in CAM for working memory, semantic memory, episodic memory and procedural memory are introduced. It will be explained how, in CAM, all of these knowledge types are represented in dynamic decription logic (DDL), a formal logic with the capability for description and reasoning regarding dynamic application domains characterized by actions.
暂无评论