CAS Institute of Automation | Date: 2014-04-29
This invention involves an image matching method based on the cascaded binary encoding. The stated method includes: Procedure S1, using the hashing look-up with multiple hashing tables to coarsely filter candidate key-points in the image to produce a candidate subset of key-points; Procedure S2, projecting the candidate subset into a high-dimensional Hamming space; Procedure S3, a Hamming distance-memory address hashing table is built, and the optimal matching key-point is discovered by querying this hashing table. The image matching method proposed in this invention has high processing speed and matching quality, which can be used for efficient and accurate image matching.
CAS Institute of Automation | Date: 2014-04-28
The disclosure relates to a method for detection of the horizontal and gravity directions of an image, the method comprising: selecting equidistant sampling points in an image at an interval of the radius of the sampling circle of an attention focus detector; placing the center of the sampling circle of the attention focus detector on each of the sampling points, and using the attention focus detector to acquire attention focus coordinates and the corresponding significant orientation angle, and all the attention focus coordinates and the corresponding significant orientation angles constitute a set _(p); using an orientation perceptron to determine a local orientation angle and a weight at the attention focus according to the gray image information, and generating a local orientation function; obtaining a sum of each of the local orientation functions as an image direction function; obtaining a function M_(CGCS)(), and further obtaining the horizontal and gravity identification angles.
Samsung and CAS Institute of Automation | Date: 2016-07-22
A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.
Wang F.-Y.,CAS Institute of Automation
IEEE Transactions on Intelligent Transportation Systems | Year: 2010
Parallel control and management have been proposed as a new mechanism for conducting operations of complex systems, especially those that involved complexity issues of both engineering and social dimensions, such as transportation systems. This paper presents an overview of the background, concepts, basic methods, major issues, and current applications of Parallel transportation Management Systems (PtMS). In essence, parallel control and management is a data-driven approach for modeling, analysis, and decision-making that considers both the engineering and social complexity in its processes. The developments and applications described here clearly indicate that PtMS is effective for use in networked complex traffic systems and is closely related to emerging technologies in cloud computing, social computing, and cyberphysical-social systems. A description of PtMS system architectures, processes, and components, including OTSt, Dyna CAS, aDAPTS, iTOP, and TransWorld is presented and discussed. Finally, the experiments and examples of real-world applications are illustrated and analyzed. © 2006 IEEE.
Wang Z.,CAS Institute of Automation
Optics Express | Year: 2015
The calibration of computer vision systems that contain the camera and the projector usually utilizes markers of the well-designed patterns to calculate the system parameters. Undesirably, the noise and radial distortion exist universally, which decreases the calibration accuracy and consequently decreases the measurement accuracy of the related technology. In this paper, a method is proposed to remove the noise and radial distortion by registering the captured pattern with an ideal pattern. After the optimal modeled pattern is obtained by registration, the degree of freedom of the total calibration markers is reduced to one and both the noise and radial distortion are removed successfully. The accuracy improvement in a structured light scanning system is over 1024 order of magnitude in the sense of mean square errors. Most importantly, the proposed method can be readily adopted by the computer vision techniques that use projectors or cameras. © 2015 Optical Society of America.
Wang F.-Y.,CAS Institute of Automation
IEEE Intelligent Systems | Year: 2010
Internet use and cyberspace activities have created an overwhelming demand for the rapid development and application of Cyber-Physical-Social Systems (CPSS), raising compelling technological, economic, and social implications. This inaugural department begins by addressing the philosophical and scientific foundation of CPSS. Any study of CPSS must be conducted with a multidisciplinary approach involving the physical, social, and cognitive sciences and that AI-based intelligent systems will be key to any successful construction and deployment. © 2010 IEEE.
Shen S.,CAS Institute of Automation
IEEE Transactions on Image Processing | Year: 2013
In this paper, we propose a depth-map merging based multiple view stereo method for large-scale scenes which takes both accuracy and efficiency into account. In the proposed method, an efficient patch-based stereo matching process is used to generate depth-map at each image with acceptable errors, followed by a depth-map refinement process to enforce consistency over neighboring views. Compared to state-of-the-art methods, the proposed method can reconstruct quite accurate and dense point clouds with high computational efficiency. Besides, the proposed method could be easily parallelized at image level, i.e., each depth-map is computed individually, which makes it suitable for large-scale scene reconstruction with high resolution images. The accuracy and efficiency of the proposed method are evaluated quantitatively on benchmark data and qualitatively on large data sets. © 1992-2012 IEEE.
Zhang Z.,CAS Institute of Automation |
Tao D.,Intelligent Systems Technology, Inc.
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2012
Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal . It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. Experimental results suggest that the SFA-based approach 1) is able to extract useful motion patterns and improves the recognition performance, 2) requires less intermediate processing steps but achieves comparable or even better performance, and 3) has good potential to recognize complex multiperson activities. © 2012 IEEE.
Ningxia Yinchuan Dahe Cnc Machine Co. and CAS Institute of Automation | Date: 2014-01-08
A reciprocating servo control device for a mainshaft of a honing machine includes a bed body, a mainshaft mechanism of the honing machine mounted on the bed body, a driving system for hydraulic reversing and a control system, where the driving system for hydraulic reversing of the honing machine includes a mainshaft hydraulic cylinder (10) and a mechanical-hydraulic servo valve for controlling the reciprocation of the mainshaft hydraulic cylinder (10), a valve body (12) of the mechanical-hydraulic servo valve is connected to a piston rod (11) of the mainshaft hydraulic cylinder (10) via a connecting mechanism, one end of a connecting member (5) is connected to a spool (14) of the mechanical-hydraulic servo valve, and the other end is connected to a converting mechanism which is controlled by a servo driving and control system. The reciprocating servo control device for a mainshaft of a honing machine adopts a mechanical position closed-loop with numerical control and a hydraulic position closed-loop composed of a linear mechanical-hydraulic servo valve, to achieve numerical control of speed, position and reversing of the mainshaft hydraulic cylinder (10) of the honing machine, thus a simple structure, reliable control, low price and easy adjustment, operation and maintenance can be realized.
CAS Institute of Automation | Date: 2014-04-08
A system for testing performance of mobile Radio Frequency Identification tags, comprising: a test device including a mobile car and a test channel; the test channel comprises a magnetic label on a ground for labeling a test driving route of the mobile car and a framework fixed on to the ground and provided with a reading device for the RFID tags; a magnetic recognition device is provided at a bottom of the mobile car to identify to the magnetic label and the mobile car is driven along the test driving route; the plurality of RFID tags are fixed on under-test goods loaded on the mobile car; a testing equipment configured to control the reading device to identify the RFID tags fixed on under-test goods; wherein the RFID tags are fixed on to under-test goods which are loaded on the mobile car. The performance test experiment of identifying RFID tags is repeated to get the best recognition rate by adjusting the status of the reader and reader antennas and the speed of the mobile car. According to the present disclosure, individual customization on the position and angle of the reader antennas placed with and the moving speed of under-test goods may be obtained to identify all the RFID tags on the fixed position of the goods so as to provide a reference for using the RFID tags in the manufacturing lines and the logistics systems.