The design and development of complex 2D symbol library system based on GIS system is completed by combining design pattern ***,it states that the design of the symbol library system has its unique *** diversity and c...
详细信息
ISBN:
(纸本)9781510835368
The design and development of complex 2D symbol library system based on GIS system is completed by combining design pattern ***,it states that the design of the symbol library system has its unique *** diversity and complexity of symbol library lead to difficulties in the design of ***,using the abstraction to implement the classification and generalization of symbol *** and Improving the classic composite pattern to extend the diversity of symbols with the method of combining primitive *** factory method and template method pattern to reduce the coupling between modules and improve the extendibility of the ***,the design of the system is very good to achieve the 2D symbol library's function under ***'s integrated in the existing GIS system ***'s powerful,reusable and good extendibility.
During the tracking process of infrared (IR) multi-targets, sometimes there exists occlusion of targets in a short time, which leads to target losing in subsequent tracking. In order to improve the accuracy of detecti...
详细信息
ISBN:
(纸本)9781849199940
During the tracking process of infrared (IR) multi-targets, sometimes there exists occlusion of targets in a short time, which leads to target losing in subsequent tracking. In order to improve the accuracy of detecting and the robustness of tracking, we propose to detect moving IR targets utilizing the correlation of their tracks and adopt the Kalman Filter model to do tracking. Both the detecting and tracking algorithms are implemented on a FPGA system. In order to lower the computational cost, the features of the targets are stored in the memory instead of the whole frame image. Experimental results indicate that the proposed method is effective to address the drawbacks of the short-time occlusion of targets efficiently with high speed.
As the common method using JTAG to update the programs of DSP and FPGA is limited by the environment and equipment, there is a need for remote updating. This paper proposes a method based on RS-422 serial communicatio...
详细信息
ISBN:
(纸本)9781849199940
As the common method using JTAG to update the programs of DSP and FPGA is limited by the environment and equipment, there is a need for remote updating. This paper proposes a method based on RS-422 serial communication and HDLC protocol. Comparing with other remote updating methods, it is fast, stable and easy to be implemented. Apart from this, we design a system to verify the method. At last, we do an experiment to show the full process.
In practical applications, target detection and tracking requires both high detection accuracy and good real-time performance, especially in the case of hardware implementation. Hence, the target detection and trackin...
详细信息
ISBN:
(纸本)9781849199940
In practical applications, target detection and tracking requires both high detection accuracy and good real-time performance, especially in the case of hardware implementation. Hence, the target detection and tracking algorithm should be simple and effective and the hardware needs to be powerful enough to meet the real-time requirement. In this paper, we proposed a moving target detection and tracking method based on fast corner detection and frame subtraction under dynamic background. An emerging eight-core DSP, i.e., TMS320C6678, is then adopted for the implementation of the proposed algorithm. Since it is multi-core, the algorithm can be divided into several small tasks executed in different cores simultaneously, which save running time dramatically. Experimental results show that the proposed method has good detection and tracking performance and TMS320C6678 is able to realize real-time tracking of the moving car under the dynamic background.
A novel adaptive real-time image compression framework based on TMS320C6713 is presented in this paper. Via analyzing image texture, different compression ratio is applied for reducing the code stream. Owing to its lo...
详细信息
ISBN:
(纸本)9781849199940
A novel adaptive real-time image compression framework based on TMS320C6713 is presented in this paper. Via analyzing image texture, different compression ratio is applied for reducing the code stream. Owing to its low-cost, highspeed and low power performances, C6713 is selected as the main processor of framework. Firstly, the original image is transformed through lifting wavelet transform algorithm. Then, the resultant transformed data is encoded with zero tree wavelet, thereby completing the compression of 320x256 image with input bandwidth 2.34MB/s and output bandwidth 100kB/s. Moreover, the experimental results demonstrate that the adaptive image ratio can reach 25:1 with PSNR 30 and frame frequency can achieve 25fps with a high-speed processor.
Single feature extract method for image retrieval usually cannot get good results and it is hard to find a stable fusion method when across image datasets because the image descriptors usually describe image from sing...
详细信息
ISBN:
(纸本)9781509037117
Single feature extract method for image retrieval usually cannot get good results and it is hard to find a stable fusion method when across image datasets because the image descriptors usually describe image from single aspect. For this pragmatic issue, an improved FCTH-BoVW feature fusion algorithm called robust FCTH-BoVW is proposed in this paper. Traditional feature fusion methods almost use liner weight method, but this method will be easily affected by the weights, and not easy to find the optimal weights. In this paper, FCTH feature is used as the global feature and BoVW feature as the local feature, and use k-reciprocal nearest neighbors method to fuse them. FCTH is an efficient descriptor and contains both color and texture information, in order to emphasize the center area as main region of interest, an annular weight method is proposed to improve the global feature. A soft assignment method is adopted to quantize the visual words for the improvement of the local feature. This method enhances the description ability of both global and local features. We find those improvements are quite practical, the results show that this fused method gets a higher retrieval precision, and we also find it is a stable image retrieval method for varieties of image datasets.
The sound recognition is considered as an effective tool to improve the performance of man-machine interaction. However, because of the non-ideal effect during the propagation and the extensive variation range of soun...
详细信息
ISBN:
(纸本)9781849199940
The sound recognition is considered as an effective tool to improve the performance of man-machine interaction. However, because of the non-ideal effect during the propagation and the extensive variation range of sound signal, it is quite difficult to achieve high accuracy target sound recognition for conventional sound recognition methods. In order to improve the performance of sound recognition, a robust sound recognition method based on human auditory bionic processing is proposed in this paper. In the proposed method, by analyzing the major function of human auditory system, the mathematical model of human auditory system is firstly developed to simulate the sound propagation in human auditory physiological processing. Then by extracting the muti-dimensional eigenvectors of the auditory spectrum, the feature of target sound signal is obtained. Afterwards, the recognition and classification of sound signal is achieved by the back-propagation (BP) neural network method. Based on the simulation of actual sound signal, it is verified that the proposed method can effectively simulate the sound propagation and achieve desirable sound recognition performance under noise condition.
For ground penetrating radar (GPR), clutter suppression effect has an important role on target detection. Approaches based on minimal entropy, the signal to clutter ratio (SCR) and image contrast are widely used for a...
详细信息
ISBN:
(纸本)9781849199940
For ground penetrating radar (GPR), clutter suppression effect has an important role on target detection. Approaches based on minimal entropy, the signal to clutter ratio (SCR) and image contrast are widely used for assessment. These traditional approaches have inevitable defects. Such as, minimum entropy and image contrast methods lead to inaccurate image evaluation under the cases of heavy clutter. SCR method will be influenced by subjective feeling. This paper presents an adaptive SCR evaluation method. This method can evaluate clutter cancellation effect quantitatively without being influenced by subjective factors.
A wideband PAR (Phased Array Radar) implementation framework based on wide band digital intermediate frequency is proposed for aperture full time problem. A method compensating the aperture full time by digital stretc...
详细信息
ISBN:
(纸本)9781849199940
A wideband PAR (Phased Array Radar) implementation framework based on wide band digital intermediate frequency is proposed for aperture full time problem. A method compensating the aperture full time by digital stretch processing for chirp signal is presented. A compensation approach for RF channels phase consistency using phase adjustment of digital oscillator is also given. Experiment results based on hardware system indicate that the method is effective and engineering realizable.
The performance of the conventional Gram-Schmidt orthogonalization of covariance matrix (RGS) beamforming method will decrease significantly when non-ideal factors exists such as the appearances of fast moving interfe...
详细信息
ISBN:
(纸本)9781849199940
The performance of the conventional Gram-Schmidt orthogonalization of covariance matrix (RGS) beamforming method will decrease significantly when non-ideal factors exists such as the appearances of fast moving interferences, array platform movement. In order to improve the robustness of interference suppression, a derivative constrained Gram-Schmidt orthogonalization of covariance matrix (CRGS) beamforming method with widened nulls is proposed in this paper. In the proposed method, the number of interference P is initially estimated and the first subspace is reconstructed by Gram-Schmidt orthogonalization of the first P columns of sample covariance matrix. Afterwards, the derivative constrained vectors and the second subspace spanned of these vectors are constructed. At last the adaptive weight vector is obtained by orthogonally projecting the quiescent weight vector onto the interference subspace made up of the first subspace and the second subspace. Based on the numeral simulation results, it is verified that the proposed method can form widened nulls and effectively improve the robustness of interference suppression.
暂无评论