363 results about "AdaBoost" patented technology

The present invention is directed to a computer automated method of selectively identifying a user specified behavior of a crowd. The method comprises receiving video data but can also include audio data and sensor data. The video data contains images a crowd. The video data is processed to extract hierarchical human and crowd features. The detected crowd features are processed to detect a selectable crowd behavior. The selected crowd behavior detected is specified by a configurable behavior rule. Human detection is provided by a hybrid human detector algorithm which can include Adaboost or convolutional neural network. Crowd features are detected using textual analysis techniques. The configurable crowd behavior for detection can be defined by crowd behavioral language.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

A scalable video bitstream may have an H.264AVC compatible base layer (BL) and a scalable enhancement layer (EL), where scalability refers to color bit depth. The SVC standard allows spatial inter-layer prediction, wherein a residual in the EL is generated which is then intra coded. Another spatial intra-coding mode for EL is pure intra coding (I_NxN). The invention discloses encoding modes wherein the output of enhancement layer decoding is an inter-layer residual. To get the final enhancement layer decoded sequence, the color bit depth inter-layer prediction version of the base layer, which is bit depth upsampled reconstructed base layer information, is added to the inter-layer residual which is decoded from the enhancement layer bit stream.

The present invention discloses an object image detection method, which uses a coarse-to-fine strategy to detect objects. The method of the present invention comprises steps: acquiring an image and pre-processing the image to achieve dimensional reduction and information fusion; using a trained filter to screen features; and sequentially using a coarse-level MLP verifier and a fine-level MLP verifier to perform a neural network image detection to determine whether the features of the image match the features of the image of a target object. The present invention simultaneously uses three mainstream image detection methods, including the statistic method, neural network method and adaboost method, to perform image detection. Therefore, the present invention has the advantages of the rapidity of the adaboost method and the accuracy of the neural network method at the same time.

The present invention leverages spatial relationships to provide a systematic means to recognize text and / or graphics. This allows augmentation of a sketched shape with its symbolic meaning, enabling numerous features including smart editing, beautification, and interactive simulation of visual languages. The spatial recognition method obtains a search-based optimization over a large space of possible groupings from simultaneously grouped and recognized sketched shapes. The optimization utilizes a classifier that assigns a class label to a collection of strokes. The overall grouping optimization assumes the properties of the classifier so that if the classifier is scale and rotation invariant the optimization will be as well. Instances of the present invention employ a variant of AdaBoost to facilitate in recognizing / classifying symbols. Instances of the present invention employ dynamic programming and / or A-star search to perform optimization. The present invention applies to both hand-sketched shapes and printed handwritten text, and even heterogeneous mixtures of the two.

The invention discloses a license plate localization and identification method based on a high-definition image, comprising the following steps of: (1) carrying out one-time downsampling on the original color images, graying the downsampled images and carrying out vertical edge detection and binaryzation on the images, and carrying out license plate rough localization by utilizing vertical edge information to obtain all candidate license plate areas; (2) mapping all the candidate license plate areas into the original images and sending to a trained cascade Adaboost grader so as to remove non-license plate areas; (3) carrying tilt correction on the license plate areas obtained in the step (2); (4) carrying out character segmentation on the license plate areas obtained in the step (3); and (5) identifying segmented characters. The invention can rapidly and effectively extract a plurality of license plates in different sizes from a complicated scene and can effectively improve the character identification accuracy. The license plate localization and identification method has wide application prospect in the aspects of intelligent transportation, parking lot management, residential quarter management, and the like.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

A multi-model cooperative defense method facing deep learning antagonism attack comprises the following steps of: 1) performing unified modeling based on a gradient attack to provide a [Rho]-loss model; 2) according to design of a unified model, for an countering attack of a target model fpre(x), according to a generation result of a countering sample, classifying a basic expression form of an attack into two classes; 3) analyzing the parameters of the model, performing parameter optimization of the [Rho]-loss model and search step length optimization of a disturbance solution model for the countering sample; and 4) for the mystique of a black box attack, designing an experiment based on an adaboost concept, generating a plurality of different types of substitution models, used to achievethe same task, for integration, designing a multi-model cooperative defense method with high defense capability through an attack training generator of an integration model with high defense capability, and providing multi-model cooperative detection attack with weight optimal distribution. The multi-model cooperative defense method is high in safety and can effectively defense the attack of a deep learning model for the antagonism attack.

The present invention leverages spatial relationships to provide a systematic means to recognize text and / or graphics. This allows augmentation of a sketched shape with its symbolic meaning, enabling numerous features including smart editing, beautification, and interactive simulation of visual languages. The spatial recognition method obtains a search-based optimization over a large space of possible groupings from simultaneously grouped and recognized sketched shapes. The optimization utilizes a classifier that assigns a class label to a collection of strokes. The overall grouping optimization assumes the properties of the classifier so that if the classifier is scale and rotation invariant the optimization will be as well. Instances of the present invention employ a variant of AdaBoost to facilitate in recognizing / classifying symbols. Instances of the present invention employ dynamic programming and / or A-star search to perform optimization. The present invention applies to both hand-sketched shapes and printed handwritten text, and even heterogeneous mixtures of the two.

The invention provides a virtual learning environment natural interaction method based on multimode emotion recognition. The method comprises the steps that expression information, posture information and voice information representing the learning state of a student are acquired, and multimode emotion features based on a color image, deep information, a voice signal and skeleton information are constructed; facial detection, preprocessing and feature extraction are performed on the color image and a depth image, and a support vector machine (SVM) and an AdaBoost method are combined to perform facial expression classification; preprocessing and emotion feature extraction are performed on voice emotion information, and a hidden Markov model is utilized to recognize a voice emotion; regularization processing is performed on the skeleton information to obtain human body posture representation vectors, and a multi-class support vector machine (SVM) is used for performing posture emotion classification; and a quadrature rule fusion algorithm is constructed for recognition results of the three emotions to perform fusion on a decision-making layer, and emotion performance such as the expression, voice and posture of a virtual intelligent body is generated according to the fusion result.

The invention discloses a fast 3D face identifying method based on double-eye passive solid sight, which includes the following steps: 1) a non-contact short shaft parallel binocular stereo vision system is built by applying two high-definition digital cameras; 2) after system calibration is finished, face detection and collection based on a haar-AdaBoost sorting machine is carried out on a preview frame image for obtaining corresponding upper and lower stereoscopic vision graph pairs and estimating a sight difference; image correction is carried out on a face area for obtaining the upper and lower stereoscopic vision graph pairs vertical to the polar lines inside and outside the area; 3) the accurate location on the eyes and a spex nasi is captured by applying a Bayesian and the haar-AdaBoost sorting machines as well as point cloud 3D information for building a benchmark triangle; 4) the corresponding sub pixels in the middle and small areas are matched by applying the pyramidal parallel search solid graph of a phase relevant arithmetic based on a complex wavelet; 5) pose normalizing and hole filling are carried out on the faces under different poses by applying the built benchmark triangle; 6) expression normalization is carried out on different faces based on the suppose that the surface geodesic distance of the face is invariable; 7) the 3D faces after normalization are identified by utilizing the arithmetic. The method has the beneficial effects of: mainly solving the problems of being hard to fast and automatically obtain the passive stereoscopic vision and identifying the 3D point cloud information of the dense and accurate face under different poses and expressions, thus leading the 3D face identifying process to be faster, more hidden, safer and more reliable.

The invention discloses an indoor human body detection tracking and identity recognition system based on multiple sensors, and the system completes the preliminary positioning of a human body through a pyroelectric infrared sensor, and a camera is enabled to move to a range where the human body appears through a steering machine. The system collects the image information of the range through the camera, and transmits the image information to the computer. The computer completes the related calculation related with the human body detection, and controls the steering machine to drive the camera and a moving platform to track the human body. The computer enables the collected image information to be matched with background information, so as to determine the identity of a detected person. The system is mainly used for detecting whether there is a person invading an indoor environment or not, and helping an indoor mobile service robot determine a target person in service. The system mainly controls a camera steering machine holder through the pyroelectric infrared sensor so as to enable the camera steering machine holder to rotate to the range of human activity, and detect and track the human body through visual information. After the human body is detected, the system carries out the identity recognition through Adaboost and a principal component analysis method.

The invention relates to a three-dimensional facial reconstruction method, which can automatically reconstruct a three-dimensional facial model from a single front face image and puts forward two schemes. The first scheme is as follows: a deformable face model is generated off line; Adaboost is utilized to automatically detect face positions in the inputted image; an active appearance model is utilized to automatically locate key points on the face in the inputted image; based on the shape components of the deformable face model and the key points of the face on the image, the geometry of a three-dimensional face is reconstructed; with a shape-free texture as a target image, the texture components of the deformable face model are utilized to fit face textures, so that a whole face texture is obtained; and after texture mapping, a reconstructed result is obtained. The second scheme has the following differences from the first scheme: after the geometry of the three-dimensional face is reconstructed, face texture fitting is not carried out, but the inputted image is directly used as a texture image as a reconstructed result. The first scheme is applicable to fields such as film and television making and three-dimensional face recognition, and the reconstruction speed of the second scheme is high.

The invention discloses a method for conducting real-time tracking on faces by a monocular camera. The method comprises the steps that firstly, the camera is opened so as to search for whether the faces exist around the camera or not, images collected by the camera are transmitted to an image processor, the image processor calls an image processing program to conduct image compression, three AdaBoost cascade connection strong classifiers based on Haar characteristics are loaded on the image processing program, skin color detection is carried out on all the compressed images, a detected window is used for detecting the faces with multiple angles through the three AdaBoost cascade connection strong classifiers, after the faces are detected, real-time tracking is carried out on face targets, the difference between the central point coordinates of a face target area and the central point coordinates of the whole images is compared, the camera is adjusted to enable the central point coordinates of the face images to be approximately aligned with central point coordinates of the images, and real-time tracking on the faces is achieved. The method has the advantages that the tracking method is simple, the calculated amount is small in the tracking process, the hardware structure is simple, and real-time tracking of the face targets can be well achieved.

The present invention is directed to a computer automated method of selectively identifying a user specified behavior of a crowd. The method comprises receiving video data but can also include audio data and sensor data. The video data contains images a crowd. The video data is processed to extract hierarchical human and crowd features. The detected crowd features are processed to detect a selectable crowd behavior. The selected crowd behavior detected is specified by a configurable behavior rule. Human detection is provided by a hybrid human detector algorithm which can include Adaboost or convolutional neural network. Crowd features are detected using textual analysis techniques. The configurable crowd behavior for detection can be defined by crowd behavioral language.

The invention provides a power transmission line gallop risk early-warning method based on Adaboost. The method comprises the following steps that internal reasons of gallop of power transmission lines are classified, and statistics is carried out on meteorological feature factors in historical gallop accidents of the power transmission lines according to the classification result; according to the information of a power transmission line to be predicted, the class, in the classification result of the internal reasons of gallop, corresponding to the power transmission line is selected, the meteorological feature factors under the conditions of the historical gallop accidents of the class are recorded to form a training sample set, a classifier is formed with an Adaboost ensemble learning algorithm, forecast data of the meteorological feature factors of the gallop of the power transmission line serve as input, and a gallop early-warning result of the power transmission line is obtained through the classifier; according to the early-warning result, the early-warning level of the gallop of the power transmission line is obtained through judgment. According to the power transmission line gallop risk early-warning method based on Adaboost, the internal reasons and the external reasons influencing the gallop of the power transmission line are comprehensively considered, the historical gallop information and the weather forecast information of the power transmission line are made full use of, and the method meets the actual conditions better; the algorithm in use is high in generalization ability, easy to encode and high in early-warning result accuracy.

The invention discloses a method for identifying a modulation mode of a communication signal. The method comprises the following steps that: a network side receives a communication signal, constructs and stores characteristic parameters of the communication signal according to the characteristics of the received communication signal; the network side processes the constructed characteristics parameters of the communication in a GDA mode, and stores the processed characteristic parameters; and the network side judges the processed characteristic parameters in a mode of a decision tree judgmentclassifier of an AdaBoost, and identifies the modulation mode of the received communication signal. Due to the adoption of the method, the problem that the conventional identification method has low identification accuracy in a low signal-to-noise ratio is solved; and a higher correct identification rate is achieved.

The invention discloses an Adaboost face detection method based on a new Haar- like feature. The Adaboost face detection method based on a new Haar- like feature includes the following steps: (1), training phase: utilizing a camera to collect face feature and non-face feature image samples, extracting the face feature set and non-face feature set to conduct training, constructing rectangle features which can distinguish face samples and non-face samples and a corresponding weak classifier, obtaining a strong classifier of face and non-face through training, repeating the training process from the second step to the third step, and obtaining a complete face detector, (2), detection phase: scanning the image and extracting all the detected child windows, and obtaining sub-image set to be detected, calculating the integration figure value of all rectangles of all sub-images, conducting detection with the classifier through training, merging all the detection results, outputting the detected face position. The weak classifier of the Adaboost face detection method based on the new Haar- like feature is more specific and more accurate and can effectively improve the detection efficiency of the face.

The invention discloses a pedestrian detection method and a pedestrian detection device. The method comprises the following steps of: collecting a pedestrian image, preprocessing the image, and extracting a region of interest from the preprocessed image; pre-positioning a pedestrian region in the region of interest by adopting an Adaboost cascade classifier; and positioning the pedestrian region in the pedestrian region pre-positioned by the Adaboost cascade classifier by adopting a support vector machine (SVM). By the technical scheme, the technical problem that the fallout ratio in the prior art is high.

The invention discloses a video-analysis-based smoke detecting method, which is realized by taking a digital camera as a sensor and under support of a digital signal processing chip. The method is characterized by comprising the following steps: collecting digital video by utilizing the digital camera; screening out a foreground part containing a movement part; screening out an area with likeness by using a support-vector-machine detector; analyzing high-frequency signal change by applying wavelet transform, and screening out a digital image of which the background is in gradually fuzzy change; and screening out digital images with smoke texture characteristics by using an Adaboost cascade classifier pairs. By combining moving object extraction by background modeling, grey area screening by a support-vector-machine (SVM) classifier, high-frequency signal change analysis by wavelet transform, the smoke texture characteristic cascade classifier and other methods, the method greatly improves the accuracy and efficiency of smoke detection, reduces the false alarm rate and has high robustness and higher practicality.

The invention discloses a wearable human body falling detection device which is composed of embedded type multi-sensor hardware and falling detection software, wherein human body posture change is measured by the embedded type multi-sensor hardware through an acceleration sensor and a tilt angle sensor, and the falling detection software is used for judging whether the abnormal behavior of falling occurs; when falling occurs, a notice is given to a far end for medical assistance through the General Packet Radio Service (GPRS) and the Global Position System (GPS); a measured human body posture signal is filtered by the falling detection software and then multiple characteristic quantities are extracted; training of multiple SVM parameters and the weighting coefficient of each SVM of the diversity AdaBoost-SVM integrated algorithm is carried out on the characteristic quantities to form an SVM integrated classifier; finally data acquired in real time are input into the falling detection software for detection. According to the wearable human body falling detection device, the embedded diversity AdaBoost-SVM classifier can be used for providing help when an emergency occurs to the aged who are outside, and therefore the device has broad market prospect and great application value.

The invention discloses an adaptive noise intensity video denoising method which is based on motion detection and is embedded in an encoder. The method comprises the following steps: (1) taking a sum of regularization frame differences in a neighborhood as an observed value, dividing input pixels into a static pixel and a dynamic pixel and using filters in different supporting domains for the two kinds of the pixels, wherein a filtering coefficient is adaptively determined according to noise intensity and an image local characteristic; (2) taking a single DCT coefficient or the sum of the several DCT coefficients as the characteristic, using AdaBoost as a tool to construct a cascade-form classifier and using the classifier to select a static block; (3) establishing a function model of connection between DCT coefficient distribution parameters of the video noise intensity and the static block and using the model to estimate the noise signal standard difference. By using noise intensity estimation embedded in the video encoder and a noise reduction technology provided in the invention, few computation costs can be used to acquire the parameters and the information needed by noise filtering. A time efficiency is good. Because a reliable clue is used to determine whether the pixels accord with a static hypothesis, the filter of the invention can effectively filter the noise and simultaneously maintain marginal sharpness of the static image. And motion blur caused by filtering in a motion area can be avoided.

The invention relates to a target identification method based on training Adaboost and a support vector machine, relating to the technical field of image processing. The target identification method comprises the following steps: extracting haar characteristics of an original sample and using the haar characteristics for training to obtain a cascading classifier based on the Adaboost and the SVM (support vector machine) and then carrying out target identification on an image to be identified by using the cascading classifier to obtain a final identification result. The target identification method can accurately and rapidly identify targets such as people, vehicles and the like.

An information processing apparatus includes the following elements. A learning unit is configured to perform Adaptive Boosting Error Correcting Output Coding learning using image feature values of a plurality of sample images each being assigned a class label to generate a multi-class classifier configured to output a multi-dimensional score vector corresponding to an input image. A registration unit is configured to input a register image to the multi-class classifier, and to register a multi-dimensional score vector corresponding to the input register image in association with identification information about the register image. A determination unit is configured to input an identification image to be identified to the multi-class classifier, and to determine a similarity between a multi-dimensional score vector corresponding to the input identification image and the registered multi-dimensional score vector corresponding to the register image.

The invention discloses a sight tracking system suitable for human-computer interaction and based on a system on programmable chip (SOPC). The system comprises a simulation camera, an infrared light source and an SOPC platform. The camera inputs a collected simulation image into the SOPC platform, the simulation image is stored to be a digital image through a decoding chip, a hardware logic module is adopted to achieve an Adaboost detection algorithm based on the haar characteristic, detection of a human eye area is conducted on the image, a random sampling consistency oval fitting method is further utilized to conduct pupil accurate location to further obtain a sight vector, and a sight vector signal is transmitted to a computer through a universal serial bus (USB) to achieve human-computer interaction. The system achieves human eye area detection and pupil center extraction through hardware, finally achieves human-computer interaction, has good accuracy and real-time performance and achieves device miniaturization.

The invention provides a face authentication method and device, and belongs to the field of image processing and pattern recognition. The method comprises the following steps: extracting Gabor texture features of an acquired face image sample pair through a Gabor filter, and separating real parts from virtual parts of the extracted Gabor texture features to obtain a plurality of feature graphs; summarizing the plurality of obtained feature graphs through an LBP (Local Binary Pattern) statistical histogram to serve as face feature expression of the face image pair; performing feature selection on the face feature expression of the face image sample pair through an AdaBoost (Adaptive Boosting) algorithm; and performing feature dimension reduction, feature judgment processing and the like on the face feature expression of the face image sample pair subjected to the feature selection through a PCA (Principal Components Analysis) algorithm and an LDA (Linear Discriminant Analysis) algorithm in sequence. Compared with the prior art, the face authentication method provided by the invention has the advantages of full extraction of sample texture information, low sample quantity demand, short algorithm time and low space complexity.

The invention discloses a rapid facial expression recognition method based on an ELM self-encoding algorithm. The rapid facial expression recognition method comprises the steps of: step 1, training an Adaboost-based face region detection classifier and performing face detection; step 2, preprocessing a detected face region, including clipping, size normalization and histogram equalization processing; step 3, adopting an ELM-AE algorithm based on an auto-encoder and an extreme learning machine as a feature extraction algorithm, and performing feature extraction on a facial expression image after preprocessing; step 4, and constructing a facial expression classifier based on the extreme learning machine, inputting vectors of feature extraction into the facial expression classifier, and regarding an output result as a mood of a face. The rapid facial expression recognition method can extract primary information and perform dimensionality reduction more quickly and efficiently. When in facial expression recognition classification, the ELM just needs to adjust a parameter of a neuron, the recognition is short in operating time and high in accuracy rate, and the rapid facial expression recognition method is efficient and rapid in learning speed.

The invention discloses a pedestrian image detection method based on sparse coding and a neural network. The method comprises the steps: preprocessing the samples in a sample data set, and extracting the features of an aggregation channel; constructing a BP-AdaBoost strong classifier model and training; preprocessing video frames, and scaling the video frames with different scales to obtain an image pyramid; utilizing the quick image feature pyramid calculating method to integrate with a sliding window detection method to calculate the window images to obtain the features of the aggregation channel, and utilizing the trained strong classifier to perform classification; and when the detection result of the window images is a positive sample, outputting the detection window, and fusing all the detection windows to obtain an accurate positioning window. The pedestrian image detection method based on sparse coding and a neural network is high in the calculating speed and the accuracy when the training samples are large.

The invention relates to the field of computer vision, and refers in particular to a detection and recognition method of human face in video under low-light conditions. The system aims at the specific problem of recognizing human face under low-light conditions, and is designed to satisfy the video system with a recognition function of human face under low-light conditions. An algorithm of the system consists of three steps: 1. preprocessing the video image of human face under low-light conditions, based on fuzzy theory; 2. training with a classifier, based on human face detection algorithm of Adaboost; 3. recognizing human face in modeling Video, based on feature fusion. The result of recognizing human face can finally be obtained. Actually, the method can be embedded in FPGA to be used in the video camera monitoring system or cameras with the recognition function of human face. The method has the advantages of good in stability, high in recognition rate, high in speed of calculation, effective in recognizing face feature under low-light conditions, applicable to various systems, such as night vision monitoring system and verifying system of identity under low-light conditions, and strong in practicality.

The invention provides an audio visual emotion recognition method based on a multi-layer boosted HMM (Hidden Markov Model), which belongs to the field of automatic emotion recognition. An MBHMM (Multi-layer Boosted Hidden Markov Model) sorter comprises three layers of overall sorters, and each layer of overall sorters is formed by combining a plurality of continuous HMM component sorters from left to right. Three characteristic flows, namely voice, facial expression and shoulder motion in an emotion video, are used as inputs of the layers of overall sorters respectively; when the overall sorters are trained, the weight of each sample is updated continuously by an AdaBoost method, and an emphasis is laid on the sample that the overall sorters of the former characteristic flow difficultly recognize when the current layer of overall sorters is trained by using some characteristic flow by the AdaBoost method. Compared with the existing recognition method, with the adoption of the method, the classification accuracy is improved obviously.