Background modeling from a stationary camera is a crucial component in video surveillance. Traditional methods usually adopt single feature type to solve the problem, while the performance is usually unsatisfactory wh...
详细信息
ISBN:
(纸本)9780769547978
Background modeling from a stationary camera is a crucial component in video surveillance. Traditional methods usually adopt single feature type to solve the problem, while the performance is usually unsatisfactory when handling complex scenes. In this paper, we propose a multi-scale strategy, which combines both texture and color features, to achieve a robust and accurate solution. Our contributions are two folds: one is that we propose a novel texture operator named Scale-invariant Center-symmetric Local Ternary Pattern, which is robust to noise and illumination variations;the other is that a multi-scale fusion strategy is proposed for the issue. Our method is verified on several complex real world videos with illumination variation, soft shadows and dynamic backgrounds. We compare our method with four state-of-the-art methods, and the experimental results clearly demonstrate that our method achieves the highest classification accuracy in complex real world videos.
Recently, attributes have been introduced to help object classification. Multi-task learning is an effective methodology to achieve this goal, which shares low-level features between attribute and object classifiers. ...
详细信息
ISBN:
(纸本)9780769547978
Recently, attributes have been introduced to help object classification. Multi-task learning is an effective methodology to achieve this goal, which shares low-level features between attribute and object classifiers. Yet such a method neglects the constraints that attributes impose on classes which may fail to constrain the semantic relationship between the attribute and object classifiers. In this paper, we explicitly consider such attribute-object relationship, and correspondingly, we modify the multi-task learning model by adding attribute regularization. In this way, the learned model not only shares the low-level features, but also gets regularized according to the semantic constrains. Our method is verified on two challenging datasets (KTH and Olympic Sports), and the experimental results demonstrate that our method achieves better results than previous methods in human action recognition.
With the rapid development of the Internet and E-commerce, online shopping sites are becoming a popular platform for products selling. Shopping sites such as ***, dangdang. com provide consumers with a hierarchical na...
详细信息
ISBN:
(纸本)9780769549255;9781467351645
With the rapid development of the Internet and E-commerce, online shopping sites are becoming a popular platform for products selling. Shopping sites such as ***, dangdang. com provide consumers with a hierarchical navigation for selecting products easily from overwhelming amount of products. However, those man-made navigations are so general and professional that consumers still need to spend much time in filtering out their own undesired products personally. Shopping sites provide abundant textual product descriptions for most products, which describes the details of the product. In this paper, we propose a novel model to build a topic hierarchy from the detailed product descriptions, which can automatically model words into a tree structure by hierarchical Latent Dirichlet Allocation (hLDA), besides, our model can also augment words level allocations with the conceptual relation between words in WordNet automatically. Each node in the hierarchical tree contains some relevant keywords of product descriptions, thus clarifying the meaning of the concept in the node. Therefore, consumers can pick out their interested products by using the discovered descriptive and valuable navigation of products. The experimental results on amazon. com, one of the most popular shopping sites in America, demonstrate the efficiency and effectiveness of our proposed model.
Traditional sparse coding has been successfully applied in texture and image classification in the past years. Yet such kind of method neglects the influence of the signs of coding coefficients, which may cause inform...
详细信息
ISBN:
(纸本)9784990644109;9781467322164
Traditional sparse coding has been successfully applied in texture and image classification in the past years. Yet such kind of method neglects the influence of the signs of coding coefficients, which may cause information loss in the sequential max pooling. In this paper, we propose a novel coding strategy for ground-based cloud classification, which is named soft-signed sparse coding. In our method, a constraint on the signs is explicitly added to the objective function of traditional sparse coding model, which can effectively regulate the ratio between the number of positive and negative non-zero coefficients. As a result, the proposed method can not only obtain low reconstruction error but also consider the influence of the signs of coding coefficients. The strategy is verified on two challenging cloud datasets, and the experimental results demonstrate the superior performance of our method compared with previous ones.
Social Manufacturing is a novel manufacturing mode, which can introduced in the apparel industrial and other fashion industries for the mass customization, based on network, 3D fitting mirror and other technologies. I...
详细信息
ISBN:
(纸本)9781479905287
Social Manufacturing is a novel manufacturing mode, which can introduced in the apparel industrial and other fashion industries for the mass customization, based on network, 3D fitting mirror and other technologies. In social manufacturing, the consumers are involved fully into the production process by the internet; the manufacturing equipments and the intelligent interactive service terminals (3D fitting mirrors) are online, forming the manufacture and service equipment network; to realize the social manufacturing, a powerful modern logistics system are needed to support the production and E-business. Therefore, the manufacture and service equipment network, mass-customization or mass-rent webs involving a large number of people, and modern logistics network are combined in the social manufacturing platform by using the network, cloud technology, and other technologies. in the near future everyone will need the novel manufacture mode and the traditional enterprises, such as apparel enterprises, will be transformed into the intelligent enterprises which can proactively perceive and respond the personalized demands of the large quantity of consumers, and realize the mass customization by the social manufacture cloud service platform.
The k-nearest neighbor (k-NN) nonparametric regression is a classic model for single point short-term traffic flow forecasting. The traffic flows of the same clock time of the days are viewed as neighbors to each othe...
详细信息
This paper proposes three training strategies based on impedance control, including passive training, damping-active training and spring-active training, for a 3-DOF lower limb rehabilitation robot designed for patien...
详细信息
ISBN:
(纸本)9781457717871
This paper proposes three training strategies based on impedance control, including passive training, damping-active training and spring-active training, for a 3-DOF lower limb rehabilitation robot designed for patients with paraplegia or hemiplegia. controllers with similar structure are developed for these training strategies, consisting of dual closed loops, the outer impedance control loop and the inner position/velocity control loop, known as position-based impedance control method. Simulation results verify that position-based impedance control approach is feasible to accomplish the training strategies.
A distributed sampled-data based protocol is proposed for the average consensus of double-integrator multiagent systems with switching topologies and communication noises. The proposed protocol uses information from t...
详细信息
ISBN:
(纸本)9781467313988
A distributed sampled-data based protocol is proposed for the average consensus of double-integrator multiagent systems with switching topologies and communication noises. The proposed protocol uses information from two aspects: the agent's own state and the relative states between the agent and its neighbors. Due to the existence of communication noises, the relative states cannot be obtained accurately. To deal with this difficulty, a time-varying consensus gain is employed to attenuate the noise effect. Under the proposed protocol, it is proved that sufficient conditions for ensuring mean square average consensus are: the consensus gain satisfies the stochastic approximation type condition and the communication topology graph at each sampling instant is a balanced graph with a spanning tree. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed consensus protocol.
With China's rapid economic development and improving the level of the socialist market economy and the deepening of economic reforms, the materials management and logistics management mode, which relied on state-...
详细信息
ISBN:
(纸本)9781467303644
With China's rapid economic development and improving the level of the socialist market economy and the deepening of economic reforms, the materials management and logistics management mode, which relied on state-owned capital and enterprise group support, are facing new challenges. By comparing the development status and trend of the related domestic and foreign power enterprises, new online supermarket system for power materials is proposed in this article, which is based on e-commerce transactions mode, and its system framework is designed, the effectiveness of the design program in reducing enterprise material distribution, transport, warehousing, actual operation cost is validated by actual project implementation. So, the online supermarket can improve circulation efficiency of power material, and the whole system efficiency.
This paper addresses the mechatronic issues of a novel bio-inspired robotic dolphin capable of fast swimming. The robot mechanically consists of a dorsoventrally propulsion mechanism, a turning mechanism, and an up-an...
详细信息
ISBN:
(纸本)9781467313988
This paper addresses the mechatronic issues of a novel bio-inspired robotic dolphin capable of fast swimming. The robot mechanically consists of a dorsoventrally propulsion mechanism, a turning mechanism, and an up-and-down mechanism. Since the swimming robot is predominantly driven by a series of DC motors and servo motors, the possible alternative to improve the swimming speed is to maximize the motor efficiency. Based on this idea, a new slider-crank centered flapping mechanism with the continuous rotation of the DC motor is proposed to mimic the oscillations of the posterior body and the fluke. Finally, the preliminary robotic prototype is built to validate the effectiveness of the formed robotic design ideas.
暂无评论