1932results about How to "Improve detection rate" patented technology

This invention is related to a flow fluorometric device and method employing a two-photon excitation and / or confocal optical set-up. The optical set-up of this invention is optimal for counting small fluorescent biological particles. The active focal volume is diffraction-limited and consequently much smaller than the volume of the flow channel. The excitation and detection concept has been found very efficient for rejection of the background signal. An objective lens with large numerical aperture for focusing the laser and for collecting the fluorescence is used and this restricts the active volume of measurement to a diffraction-limited volume which approximately corresponds to a volume of femtoliter. This volume is significantly smaller than the detection volume of ordinary flow cytometry.

The present invention relates to a 3D landscape real-time imager. It also relates to methods for operating such an imager. Such an imager comprises: —at least one illuminating part which is designed to scan at least a portion of the landscape at a given range and having an ultra-short laser pulse source emitting at least one wavelength, and an optical rotating block, with a vertical axis of rotation, and controlled such that given packets of pulses are shaped in a pattern of rotating beams sent toward the said at least partial landscape; —at least one receiving part which comprises a set of SPAD detector arrays, each arranged along a vertical direction and rotating at a given speed in synchronism with the optical rotating block of the illuminating part, the detection data of the SPAD detector arrays being combined to acquire 3D imaging data of the said at least partial landscape in a central controller.

A microfluidic device comprises inlets for a sample flow and an out-of-plane focusing sheath flow, and a curved channel section configured to receive the sample flow and out-of-plane focusing sheath and to provide hydrodynamic focusing of the sample flow in an out-of-plane direction, the out-of-plane direction being normal to a plane including the curved channel. Examples of the invention also include improved flow cytometers.

The invention belongs to the technical field of the pattern identification and image processing, and relates to a license plate detection and identification method based on the maximum stable extremal region, which comprises the following steps: extracting the maximum stable extremal region (MSER) to obtain text regions of candidate license plates; adopting one effective feature for description of each extremal region, classifying the extremal regions into 'text' regions and 'non-text' regions with a classifier obtained in prior training, and extracting a license plate from original images based on the characteristics of the structure of the license plate; and describing with the characteristics of the shape context, and completing the character identification through template matching. Since the maximum stable extremal region has the affine invariance, high stability and multi-scale features, and the regions are determined only according to the gray value and are not light-sensitive,the license plate detection and identification method with the maximum stable extremal region as the base is applicable to the complex background, and has the advantages of good stability and high identification rate.

The present invention provides an adaptive, intelligent transform based Analog to Information Converter (AIC) for wideband signals by directly converting an analog signal to information (e.g., features, decisions). This direct conversion is achieved by (i) capturing most of the information of a wideband signal via hardware / software implemented mathematical transformations, (ii) effectively removing unwanted signals such as jammer and interfere from the input signal, and (iii) using novel algorithms for highly accurate decision making and feature extraction (e.g., high probability of detection with low probability of false alarm). The jump in the improvement over today's state-of-the-art is in terms of effective and optimum signal information extraction at high-speed.

A microfluidic device comprises inlets for a sample flow and an out-of-plane focusing sheath flow, and a curved channel section configured to receive the sample flow and out-of-plane focusing sheath and to provide hydrodynamic focusing of the sample flow in an out-of-plane direction, the out-of-plane direction being normal to a plane including the curved channel.

Disclosed is an apparatus and method for searching a base station in a mobile communications system, in which a mobile station acquires slot timing synchronization from a first signal on a primary sync channel (P-SCH) out of the P-SCH and a secondary sync channel (S-SCH) used for base station search, acquires frame timing synchronization (Fsync) from a second signal on the S-SCH, and determines a primary scrambling code group (PSCG) corresponding to the scrambling codes used by the respective base stations. The method comprises calculating and accumulating P-SCH RSSI values from the first signal at every slot and comparing the accumulated P-SCH RSSI values with first and second accumulation thresholds and providing the first and second search commands; and calculating S-SCH channel received signal strength indicator (RSSI) values from the second signal at every slot in one frame, and updating S-SCH RSSI values corresponding to the one frame as energy matrix values; calculating energy hypotheses corresponding to the energy matrix values using the energy matrix values and a predetermined secondary sync code (SSC) table in response to a first search command, and determining energy hypotheses having a value higher than a predetermined threshold as passed hypotheses; and calculating energy values for the passed hypotheses using the determined passed hypotheses and the SSC table in response to a second search command, and determining an energy hypothesis having a maximum energy as the Fsync and the PSCG.

The invention discloses a barrier detection method in the vegetation environment based on multispectral and 3D feature fusion. The method comprises that 3D point cloud data is collected, and color and near-infrared images are collected at the same time; 3D point cloud data is registered with multispectral data to obtain multispectral 3D point cloud; a grid map is established, and candidate barrier grids are obtained via a height threshold; the scale of the near-infrared image is adjusted to normalize the infrared light intensity; the near-infrared intensity value and the visible light intensity of RGB color information within the grids are combined and serve as feature information, and 2D feature is obtained via calculation; and the candidates barrier grids are processed and filtered by utilizing a Gaussian mixture model to obtain a final barrier detection result. According to the method, influence caused by change of illumination condition is reduced by normalizing the infrared light intensity, and multispectral 3D features are sued to realize effective barrier detection.

The present invention provides a neural network-based face detection model training method, a neural network-based face detection method, a neural network-based face detection model training system and a neural network-based face detection system. The training method includes the following steps that: the loss function of the bias network layer of a prediction face frame is calculated according to the bias information of the prediction face frame relative to a default face frame and the bias information of a real face frame relative to the default face frame; the loss function of the confidence network layer of the prediction face frame is calculated according to the confidence of the default face frame; the error of the two loss functions is calculated, and is fed back to a neural network, so that the weight of the neural network is adjusted; iterative training is repeated until convergence appears, so that a face detection model can be obtained, and therefore, the prediction face frame can contain a face more accurately. The detection method includes the following steps that: a face image to be detected is inputted to a trained face detection model, bias information and confidence are outputted; corresponding prediction face frames are calculated according to the bias information; and a prediction face frame corresponding to confidence greater than a preset confidence threshold or the highest confidence is selected as a face detection result.

The invention discloses a multi-target detection method based on short-time Fourier transform and fractional Fourier transform, which belongs to the technical field of the radar target detection. The method comprises the following steps that the short-time Fourier transform is firstly used for conducting the primary detection on a signal, then a binaryzation method is used for processing a primary detection result, phase position of the signal is kept in the processing, the fractional Fourier transform is used for detecting a signal after being restored by the short-time Fourier transform, by adopting multiple methods for combined processing, advantages of overcoming phenomenon that a strong signal side lobe presses a weak signal main lobe, improving the signal-to-noise ratio of the signal to be detected, and solving the problem of the large false alarm possibility which is caused by adopting traditional method to detect the signal at the low signal-to-noise ratio can be realized; and meanwhile, an image contrast method and a gradual elimination method are adopted, multiple strong signals and weak signals with different or identical frequency modulation rates can be detected by utilizing the space and power strength information of the signal, so that the detection probability and the calculation efficiency can be further improved, easiness in project realization is realized, and the method is worth of being adopted and popularized.

This invention relates to a selecting method for up-line random access leading sequences, in which, the lead includes one or multiple ZC root sequences, if a base station needs a ZC root sequence, then the base station with wider covering sphere returns the sequence index with smaller CM value, if the station needs multiple ZC root sequences, then terminals far away from the base station selects the sequence index with smaller CM value or its corresponding expansion sequence.

A system and method for identifying defects in a workpiece are provided. The system includes a sensor for non-destructive testing. The system also includes a movable arm carrying the sensor and being pivotally attached to a base. The movable arm includes at least one pivotable joint between the base and the sensor, and is capable of being moved such that the sensor acquires data indicative of a workpiece as the sensor travels proximate to the workpiece. A data acquisition system is capable of communicating with the sensor to create an image of at least a portion of the workpiece based on the data acquired by the sensor.

The invention discloses a living body human face detecting method based on a near-infrared and visible-light binocular camera, and belongs to the field of the receiver vision and security. The featurethat video and most paper cannot present an image under the infrared camera is used for effectively preventing the attack of a fake human face in the video, and the texture difference and the color difference of the real human face and the picture human face under the near-infrared camera and the visible light camera are used, a trained classifying model is capable of effectively distinguishing whether the human face is from the real human face or the fake human face in a picture. The accuracy of the living body detection of the method is high. The method is capable of effectively preventingthe attack of the fake human face in common means, such as the video and picture. Compared with a traditional algorithm, the accuracy is greatly improved, the safety is guaranteed, a user does not need to make a corresponding action or expression by cooperating with a machine, and the user experience is improved.

The invention relates to an environment detection method in an unmanned vehicle target search system, which comprises the following steps of S1, creating an unmanned vehicle global environment map andan onboard camera field of view coverage map; S2, performing combined environment search on a target to be searched at a current position, extracting and evaluating edge regions to determine the target point position of the unmanned vehicle in the next step; S3, generating a collision-free desired path, controlling the unmanned vehicle to reach the target point position; and S4, determining whether the target to be searched is located at the target point position, and completing the environment detection if so, or returning to the S1 if not. The method realizes the autonomous environment detection based on edge region guidance in an unknown environment and realizes efficient search for the target to be detected in an unknown region, and a planned travel path realistically reflects the driving characteristics of the vehicle.

A method for determining whether an radio frequency identification (RFID) device is detected, includes: (a) selecting a plurality of different antenna patterns from a predetermined multiplicity of antenna patterns; (b) determining a plurality of binary results; (c) selecting, from a plurality of predetermined methods, a method for forming a logical combination; and (d) determining that the identification device is detected by forming a logical combination of the plurality of binary results according to the selected method. Each binary result is responsive to whether a respective communication link provides a respective signal having a respective amplitude exceeding a respective threshold. Each communication link is operative in accordance with at least one of the selected antenna patterns.

The present invention encompasses a physical or virtual, computational, analysis, fusion and correlation system that can automatically, systematically and independently analyze collected sensor data (upstream) aboard or streaming from aerial vehicles and / or other fixed or mobile single or multi-sensor platforms. The resultant data is fused and presented locally, remotely or at ground stations in near real time, as it is collected from local and / or remote sensors. The invention improves detection and reduces false detections compared to existing systems using portable apparatus or cloud based computation and capabilities designed to reduce the role of the human operator in the review, fusion and analysis of cross modality sensor data collected from ISR (Intelligence, Surveillance and Reconnaissance) aerial vehicles or other fixed and mobile ISR platforms. The invention replaces human sensor data analysts with hardware and software providing two significant advantages over the current manual methods.

There is provided a fall detection system for use in detecting falls by a user, the fall detection system comprising a processing unit configured to determine context information about the user and / or the environment in which the user is located, and to increase the sensitivity of a fall detection algorithm used to detect falls by a user in the event that the determined context information indicates that the user is or may be at an increased risk of falling, the increase in sensitivity occurring while the increased risk of falling is indicated by the determined context information.

An apparatus and method for detecting a foreign object in a wireless power transmitting system are provided. In a case in which a foreign object is not detected prior to charging, an attempt to detect a foreign object detection during charging is performed, and when a foreign object is not detected while a power signal is being received, power is limited based on a temperature sensor.

The invention relates to a defect detection method of an irregular shape metal working surface based on depth learning, By preprocessing the collected surface images of metal machining, image enhancement, YOLOv3-based network architecture, Deep learning network suitable for defect detection is built. The samples are labeled manually and the deep learning network is trained with labeled samples toobtain defect detection model. Finally, the defect detection model is used to detect the surface image of metal machining, and the defect detection results are obtained. Compared with the prior art, the network structure in the invention has good adaptability to the detection of small objects and small targets, and unifies the four basic steps of the candidate region generation, the feature extraction, the classification and the position refinement of the target detection into the same depth network framework, thereby improving the running speed and making the detection more accurate.

A method for detecting an eventual channel intended to a designated user equipment among n channels received by the designated user equipment during a given duration, each channel received during the duration carrying encoded data masked with an identifier associated to a user equipment. The method includes a selecting phase having a demasking step demasking the received masked encoded data of each channel with the identifier of the designated user equipment, a decoding step decoding the demasked encoded data of each channel to obtain a set of digital decoded data for each channel, a calculating step calculating, from each set of digital decoded data, a global information representative of a confidence in digital data received on the physical channel, and a detecting step detecting the channel from all the global information.

The invention discloses a method for detecting the error of a program control flow and intends to overcome the difficulties in increasing the detection rate of the errors of the control flow by the conventional method and solve the difficult problem with the detection of the control flow inside basic blocks and among processes. The method comprises the following steps according to the technical scheme of the invention: firstly, identifying basic blocks and confirming the routing relation among the basic blocks; then, confirming the maximum required number of detection commands of the internal control flow of each basic block according to the requirements of the internal control flow and the constitutive characteristics of the basic blocks; designing the labels for the basic blocks on that basis, and distributing the unique static label to each basic block; then, inserting the detection commands into the head part, inner part and tail part of each basic block in the program respectively, re-assembling and re-linking the assembler of the inserted detection commands of the control flow, and generating an executable program for achieving the detection of the error of the control flow.

A robust means of watermarking a digitized image with a highly random sequence of pixel brightness multipliers is presented. The random sequence is formed from ‘robust-watermarking-parameters’ selected and known only by the marker and / or the marking entity. A watermarking plane is generated having an element array with one-to-one element positional correspondence with the pixels of the digitized image being marked. Each element of the watermarking plane is assigned a random value dependent upon a robust random sequence and a specified brightness modulation strength. The so generated watermarking plane is imparted onto the digitized image by multiplying the brightness value or values of each pixel by its corresponding element value in the watermarking plane. The resulting modified brightness values impart the random and relatively invisible watermark onto the digitized image. Brightness modulation is the essence of watermark imparting. Detection of an imparted watermark requires knowing the watermarking plane with which the watermark was imparted. Regeneration of the watermarking plane requires knowledge of the robust-marking-parameters used in its formulation. This is generally only known to the marker and / or marking entity. Once regenerated, the watermarking plane is used together with a verifying image located in a ‘visualizer’ to demonstrate the existence of the watermark. The process of watermark detection is enhanced by application of a blurring filter to the marked image before detection is attempted.

A method and system detects candidate targets or objects from a viewed scene by simplifying the data, converting the data to gradient magnitude and direction data which is thresholded to simplify the data. Horizontal edges within the data are softened to reduce their masking of adjacent non-horizontal features. One or more target boxes are stepped across the image data and the number of directions of gradient direction data within the box is used to determine the presence of a target. Atmospheric attenuation is compensated. The thresholding used in one embodiment compares the gradient magnitude data to a localized threshold calculated from the local variance of the image gradient magnitude data. Imagery subsets are containing the candidate targets may then be used to detect and identify features and apply a classifier function to screen candidate detections and determine a likely target.

Methods and systems for detecting wall breach in inflatable prostheses rely on intrusion of a body fluid or inflation medium to electrically alter a signaling circuit. In one embodiment, an open portion of a circuit is closed to enable or modify a transmitted signal. In another embodiment, electrical current is generated to power an electrical transmission.

The invention relates to a rapid video concentration abstracting method. The conventional video concentration technology is poor in detection rate and tracking rate to a moving target, and cannot effectively concentrate the video length. The rapid video concentration abstracting method is characterized in that a server side detects and tracks the moving target in a pretreatment video, judges according to the length of the video or the number of the detection targets in the video, cuts the video into multiple concentration segments, performs collision detection and rearrangement on the target tracks in each concentration segment, and then, records the concentration segment information and enters in an index file; and a client side analyzes the index file stored in the server side, obtains the treated concentration segments, renders the concentration segments frame by frame to form a video sequence, and dynamically regulates the target density in the played concentrated video. According to the method, the target tracking continuity is excellent, profile region is complete, the detection rate is high, the false detecting rate is low, and the target density at each time point of the concentrated video is substantially consistent.

A wireless power transfer system includes a power transmitter (101) arranged to provide a power transfer to a power receiver (105) via a wireless inductive power signal. A parasitic power loss detector (207) is arranged to detect a parasitic power loss for the power transfer, and a user indicator (209) is arranged to initialize a user alert in response to the detection of the parasitic power loss. The system comprises an input (211) for receiving user inputs; and a controller (213) which is arranged to initiate an adaptation of a parasitic power loss detection operation performed by the parasitic power loss detector (207) to detect parasitic power losses if a user input meeting a criterion is not received. Each of the individual features may be implemented in the power transmitter (101), the power receiver (105), or may e.g. be distributed between these. The approach may allow improved foreign object detection in a wireless power transfer system.

The invention discloses a target detection method which comprises the following steps of: acquiring a to-be-detected image, wherein the to-be-detected image is subjected to multi-layer convolution extraction of features in a neural network to generate a feature map; loading modified structural parameters in a neural network model, and generating corresponding anchor box coordinates on the basis ofthe structural parameters, wherein the preset structural parameters comprise a reference dimension of an anchor box, an anchor box scale and a length-width ratio of the anchor box; generating candidate box coordinates on the basis of a region nomination subnet, taking a corresponding region on the feature map according to the candidate coordinates, and by pooling of a ROI (Region Of Interest), obtaining corresponding features; and on the basis of the features, determining prediction box coordinates, and on the basis of the prediction box coordinates, determining a target object position. Theinvention further discloses a target detection device and a computer readable storage medium. According to the invention, a case of generating an optimized prediction box to determine a target objectis implemented, a small target can be detected, and a detection rate for the target is improved.