For improving accuracy of optical flow computation, we propose a new method to compute optical flow from both gray and color information. First, the Gauss filter is used to pre-filter the color image sequence. Then op...
详细信息
ISBN:
(纸本)9781424446995
For improving accuracy of optical flow computation, we propose a new method to compute optical flow from both gray and color information. First, the Gauss filter is used to pre-filter the color image sequence. Then optical flow recovery is based on the method of neighborhood least squares using brightness information. And the weight coefficients of local neighborhood are determined by U and V channels in LUV color space. Finally, the optical flow result is filtered by median filter. The experiment results show that the proposed method produces dense optical flow field and accuracy of the results can also be improved.
The test vector generation algorithm and the compression algorithm based on general structure model of SoC was introduced in this paper. We have analyzed the PODEM algorithm for test vectors generation and translated ...
详细信息
The test vector generation algorithm and the compression algorithm based on general structure model of SoC was introduced in this paper. We have analyzed the PODEM algorithm for test vectors generation and translated the test pattern, and then formed the SoC general structural model test vector. Through the experimental comparison, we find the use of Golomb coding for test vector compression/decompression method is simple and effective, and test data compression rate improved by using the minimizing Hamming distance sorting algorithm to compress and decompress the test vector significantly.
A simple and effective electrochemical deposition method to fabricate lead oxide micro-octahedrons is reported. Unlike previous reports in which the current densities of electrochemical deposition were normally not mo...
详细信息
Being difficult to determine hidden unitspsilas number and unsuitable to select central position in radial basis function (RBF) layer, particle swarm optimization and resource allocation (RAN) were proposed for traini...
详细信息
Being difficult to determine hidden unitspsilas number and unsuitable to select central position in radial basis function (RBF) layer, particle swarm optimization and resource allocation (RAN) were proposed for training RBF neural networks. First, determine unitspsilas number in RBF layer using RAN. Then, optimize RBF parameters such as central position, width and weights based on PSO. The simulation results show that the new method has better approximation ability, the shorter time and the higher precision.
Light Detection and Ranging (LIDAR) sensor is an advanced technology of 3D-measurement with high accuracy. The processing of 3D point cloud data collected via LIDAR sensor is of topical interest for 3D target *** ...
详细信息
ISBN:
(纸本)9781424438631;9781424438624
Light Detection and Ranging (LIDAR) sensor is an advanced technology of 3D-measurement with high accuracy. The processing of 3D point cloud data collected via LIDAR sensor is of topical interest for 3D target *** this paper,a new approach of imagery generation and target recognition based on 3D LIDAR data is presented. The raw 3D point cloud data are transformed and interpolated to be stored in 2D matrix. The target imagery is generated and visualized by means of height-gray mapping principle proposed in *** different poses of target,the affine invariable moments of target imagery are selected as features for recognition because of its invariance in rotation,scaling,translation and affine *** neural network algorithm and support Vector Machine (SVM) algorithm are utilized as method of target classification and recognition. The recognition results by two algorithms are compared against and analyzed detailedly. The new method had been applied into target recognition in outdoor *** types of targets are classified and the rate of correct recognition is greater than 95%. Through outdoor experiments,it can be proven that this new method is applied to the field of 3D target recognition effectively and stability.
An elaborately designed software architecture is put forward based on fuzzy sets theory (FST), which is specialized in multiple sensor fusion and mechanism failure diagnosis. Besides, when confronted with multiple fau...
详细信息
An elaborately designed software architecture is put forward based on fuzzy sets theory (FST), which is specialized in multiple sensor fusion and mechanism failure diagnosis. Besides, when confronted with multiple fault signals, fusion parameters can be dynamically adapted based on principles of fuzzy soft clustering so as to promote immune ability in artificially mechanical systems. The key point in this new approach lies in its power on faults detection, which requires no prior information on the state vectors of the sensors and system behavior, and no supplemental machine learning operation is required. The proposed algorithm combines principles of artificial immune system and the classical technique in fuzzy theory, which will consist of two main portions. In the first part a traditional data fuse structure is constructed, the sensor signals will be fed into it to implement the fuzzy aggregating algorithm.
Kalman filter is introduced into the neuro-fuzzy deducing system (NFDS) operation to attenuate disturbances in measurement data. Both of Lidar and infrared radar data sets will be engaged into data fusion, because the...
详细信息
Kalman filter is introduced into the neuro-fuzzy deducing system (NFDS) operation to attenuate disturbances in measurement data. Both of Lidar and infrared radar data sets will be engaged into data fusion, because there will exist defective data points within both of which owing to the respectively distinct running mechanism. Data confidence estimator of NFDS derived from contextual information (CI) theory; command center (CC) and yaw-pitch-distance information fusion algorithms, within whose running process both radar data sets are filtered and fed into specified system to extract confidence degree of radar sensors.
Inductor-Disconnected-Discharge (IDD) behavior of the Boost Converter is analyzed, an Equivalent-Resistance-Analysis Method (ERAM) is proposed, which can convert the IDD behavior of the Boost Converter into that of an...
详细信息
ISBN:
(纸本)9780769537443
Inductor-Disconnected-Discharge (IDD) behavior of the Boost Converter is analyzed, an Equivalent-Resistance-Analysis Method (ERAM) is proposed, which can convert the IDD behavior of the Boost Converter into that of an equivalent Simple-Inductive-Circuit (SIC). According to the energy equivalence, the equivalent inductor-current of the equivalent SIC is obtained. It is indicated that the Equivalent Inductor-Current (EIC) is much more than the maximal inductorcurrent of the Boost converter, the ignition in the case of IDD may occurs even if the inductor-current of the Boost converter is much lower than that of the SIC, furthermore, the EIC is strengthened with increase of the output capacitance. The proposed analysis method is verified by experiment results.
This intelligent analysis instrument is equipped TFT LCD as displaying terminal. First, timing and logic requirements of a typical TFT LCD are introduced. Hardware circuit between microprocessor S3C2410 and TFT LCD mo...
详细信息
This intelligent analysis instrument is equipped TFT LCD as displaying terminal. First, timing and logic requirements of a typical TFT LCD are introduced. Hardware circuit between microprocessor S3C2410 and TFT LCD module are designed. Then, based on Windows CE, developing software driver code mainly focus on setting related registers of displaying interface and adjusting the position of displaying area. Thus, system will be displayed fluently and stably. Practice has proved that the TFT LCD hardware and software design is an effective solution for the application.
A method for measuring focal length based on Talbot effect is put forward, which suits determining focal length of long-focus lens. The variation of Moiré fringes occurs after typical phase object of measuring le...
详细信息
暂无评论