Interactive image segmentation which needs the user to give certain hard constraints has shown promising performance for object segmentation. In this paper, we consider characters in text image as a special kind of ob...
详细信息
Interactive image segmentation which needs the user to give certain hard constraints has shown promising performance for object segmentation. In this paper, we consider characters in text image as a special kind of object, and propose an adaptive graph cut based text binarization method to segment text from background. The main contributions of the paper lie in: 1) in order to make the binarization local adaptive with uneven background, the text region image is firstly roughly split into several sub-images on which graph cut is applied, and 2) considering the unique characteristics of the text, we propose to automatically classify some pixels as text or background with high confidence, severed as hard constraints seeds for graph cut to extract text from background by spreading the seeds into the whole sub-image. The experimental results show that our approach could get better performance in both character extraction accuracy and recognition accuracy.
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 patie...
详细信息
ISBN:
(纸本)9781424441198
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.
In this paper, the Bouc-Wen model widely used in describing hysteretic systems is applied to piezoelectric actuator (PEA) modelling and real-coded adaptive genetic algorithm (GA) is adopted to identify the model param...
详细信息
ISBN:
(纸本)9787900769428
In this paper, the Bouc-Wen model widely used in describing hysteretic systems is applied to piezoelectric actuator (PEA) modelling and real-coded adaptive genetic algorithm (GA) is adopted to identify the model parameters simultaneously. By dynamically adjusting the crossover probability and mutation probability, adaptive genetic algorithm improves the performance of local convergence and premature convergence and enhances search speed and precision of the simple genetic algorithm. Then some experiments are conducted to verify the efficiency of the identification method with satisfactory parameter identification results.
Computer vision and video analytics become increasingly important for intelligent transport systems (ITSs), and violation detection is one of the key points in ITSs. It is widely recognized that image based systems ar...
详细信息
Computer vision and video analytics become increasingly important for intelligent transport systems (ITSs), and violation detection is one of the key points in ITSs. It is widely recognized that image based systems are flexible and versatile for advanced traffic monitoring and enforcement applications. In the proposed method, we first locate the tails from the images captured by a stationary camera, and then SURF(Speeded Up Robust Features) feature points are extracted from these tail images. A matching based rough detection stage is taken place to identify the high risk tails which are seen as violations and the low risk tails which are omitted as regular vehicles. Finally, color and shape information are taken advantages of to accomplish violation detection in the undetermined vehicles in the previous stage. Experiments are conducted using real live video sequences captured from an urban cross road. Results show that our method can potentially have a good performance.
Traffic signal coordination has long been a hot topic in Intelligent Transportation systems (ITS) research. Simulation-based optimization is an important method to optimize the coordination designs as the traffic syst...
详细信息
Traffic micro-simulation is an important tool in the Intelligent Transportation systems (ITS) research. In the micro-simulation, a bottom up system can be built up by the interactions of vehicle agents, road agents, t...
详细信息
Currently, the research issues are becoming increasingly global and complex. In order to master more and more professional and comprehensive ability to solve problems, it is proposed in this paper that academic intell...
详细信息
To further enhance emergency management skills of an organisation's emergency response personnel, emergency response training,especially 3D emergency drill, is currently becoming more and more important in the pet...
详细信息
A visual monitoring network suitable for robotic systems is presented in this paper. The monitoring network is composed of embedded vision nodes. By interacting with an upper computer as well as the robotic system, th...
详细信息
Simulation of plant structure competing for light source has mostly been done by directly modifying plant structure according to light ***-structural plant models,however,emphasize the influence of light interception ...
Simulation of plant structure competing for light source has mostly been done by directly modifying plant structure according to light ***-structural plant models,however,emphasize the influence of light interception on biomass production,and consequently plant *** this paper,we integrate a light distribution model with GreenLab model,which used Beer-Law in computing biomass *** replacing Beer-Law with a light interception model for biomass production,the combined model was able to simulate the effect of light condition on plant structure through source-sink *** positive and negative sides of this approach are discussed.
暂无评论