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.
CAS Institute of Automation | Date: 2016-10-10
The invention discloses a wearable molecular imaging navigation system comprising: a multi-spectral light transceiver configured to transmit a multi-spectral light to a detected subject in a detection region and acquire an emitting light regarding the detected subject and acquire a reflecting light regarding the detected subject; an image processor configured to receive the reflecting light and the emitting light from the multi-spectral light transceiver, execute a three-dimensional reconstruction and fusion process on the reflecting light and the emitting light to obtain a fusion image; a wireless signal processor configured to enable a wireless communication; and a wearable device, configured to receive the fusion image from the image processor via the wireless signal processor, display the fusion image and control the multi-spectral light transceiver and the image processor based on instructions received.
Huawei and CAS Institute of Automation | Date: 2017-06-14
Embodiments of the present invention provide a method for parsing a question in a knowledge base. The method includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions. In the embodiments of the present invention, uncertain inference is performed by using observed predicates and hidden predicates, and a natural language question can be converted into a formal query statement. In addition, an uncertain inference method can be applied to a knowledge base in any field, and has field extensibility. Therefore, it is unnecessary to manually configure a conversion rule for a knowledge base.
CAS Institute of Automation | Date: 2014-05-26
A pruning robot system, which comprises: a signal tag device (2) for detecting and storing information of trees and crops and positioning information, and assisting positioning; a robot (1) comprising a central processing device (10) for storing and analyzing data information of each part of the robot (1) and issuing action instructions to each part of the robot (1), and a positioning and navigating device (11) for positioning and navigating the robot (1), and for planning a path and providing obstacle-avoiding navigation for the robot (1) according to an electronic map; a cloud platform terminal (3), which is in connection and communication with the central processing device (10) of the robot (1) and is used for storing data of trees and crops as well as detection data of the robot (1), and for planning a path for the robot (1) through computing and experimenting according to the information data; a map building device (4) for building a three-dimensional electronic map corresponding to the plantation through field-detection by the robot (1). The pruning robot system realizes positioning in the plantation, robot (1) path planning, pruning information collection and automatic pruning.
Huawei and CAS Institute of Automation | Date: 2017-03-29
A method for parsing a question in a knowledge base includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions.
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.
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.