313 results about "Cascading classifiers" patented technology

A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.

A method and system is presented for detecting humans in images of a scene acquired by a camera. Gradients of pixels in the image are determined and sorted into bins of a histogram. An integral image is stored for each bin of the histogram. Features are extracted fom the integral images, the extracted features corresponding to a subset of a substantially larger set of variably sized and randomly selected blocks of pixels in the test image. The features are applied to a cascaded classifier to determine whether the test image includes a human or not.

The invention discloses an automatic screening system and an automatic screening method using a thin-prep cytology test. The system comprises an image acquisition module, an image segmentation module, a target recognition module and a comprehensive analysis module. The method provided by the invention respectively adopts a three-point evolutionary uniform sampling method to guarantee the reliability of automatic focusing, the coarse-to-fine segmentation algorithm to improve the segmentation accuracy of pathological cell nucleuses, a series of filters to rapidly filter various impurities, and a cascade classifier training method to greatly reduce the false positive rate, and uses relative features to conduct comprehensive analysis. The method disclosed by the invention has the advantages of high sensitivity over pathological cells, high specificity over normal cells, high recognition speed and high automation degree, so that the diagnostic accuracy can be improved and the workload of a cytopathologist is reduced at the same time.

In one embodiment of the present invention, a graphics processing unit (GPU) is configured to detect an object in an image using a random forest classifier that includes multiple, identically structured decision trees. Notably, the application of each of the decision trees is independent of the application of the other decision trees. In operation, the GPU partitions the image into subsets of pixels, and associates an execution thread with each of the pixels in the subset of pixels. The GPU then causes each of the execution threads to apply the random forest classifier to the associated pixel, thereby determining a likelihood that the pixel corresponds to the object. Advantageously, such a distributed approach to object detection more fully leverages the parallel architecture of the PPU than conventional approaches. In particular, the PPU performs object detection more efficiently using the random forest classifier than using a cascaded classifier.

The invention discloses a self-adaptive cascade classifier training method based on online learning, which comprises the following steps: (1), preparing a training sample set with a small quantity of samples, and training an initial cascade classifier HC(x) in a cascade classifier algorithm; (2), using the HC(x) for traversal of image frames to be detected, extracting areas with sizes identical to the sizes of the training samples one by one, calculating a feature value set, classifying the areas with the initial cascade classifier, and judging whether the areas are target areas, thereby completing target detection; (3) tracking the detected targets in a particle filtering algorithm, verifying the target detection results through tracking, marking detection with errors as a negative sample for online learning, obtaining different attitudes of real targets through tracking and extracting a positive sample for online learning; and (4) carrying out online training and updating for the initial cascade classifier HC(x) in a self-adaptive cascade classifier algorithm when an online learning sample is obtained, thereby gradually improving the target detection accuracy of the classifier.

An adaptive automobile meter detection method based on character segmentation cascade classifier which processes threshold segmentation, morphology and connected components analysis on the original image; extracts the pointer based on the contour analysis method, establishes a pointer information list; constructs a character segmentation cascade classifier by combining a HOG/SVM character segmentation classifier, a character filter and a CNN digit classifier. The character segmentation cascade classifiers is used to identify the digit character area of the automobile meter. Region analysis is performed to extract tick marks based on the center of the digit character area. The angular position corresponding to the tick mark is determined. The response value corresponding to the pointer is determined by establishing the Newton interpolation linear description relationship between the pointer angle and the response value and then the meter is classified as pass or fail. The invention is suitable for the field of visual inspection of automobile meter pointers.

The invention discloses a method for constructing a cardiovascular disease diagnosis model, a system and the diagnosis model. The cascade classifier is trained to get the ear detection model. VGG, GoogleNet and ResNet neural network models are used to extract ear features. The spatial pyramid is used to integrate the features of ear extracted from neural network model, and the depth heterogeneousfeature map of each neural network model is obtained. Feature preprocessing of depth isomerism feature map; Training to obtain SVM classifier model; The SVM classifier model and the three trained neural network models are integrated by Bagging learning to obtain the cardiovascular disease diagnosis model. The cardiovascular disease diagnosis model constructed by the invention can comprehensively and scientifically carry out cardiovascular disease diagnosis and prediction, has high precision, and can be widely applied in the field of automatic processing of medical data.

The invention discloses an enterprise industry classification method. According to the method, main business keywords of enterprises are effectively extracted by utilizing semi-supervised learning-based image split clustering algorithm, the extracted keywords are used as features on the basis of a gradient enhancement decision-making tree, and a training cascade classifier is used for classifyingthe enterprises according to industries, so that the problem that artificial classification is tedious is solved. The method specifically comprises the following steps of: 1) extracting main businesskeywords of enterprises by utilizing a word vector and a semi-supervised image split clustering algorithm, getting rid of junk words and constructing a keyword library; and 2) inputting the extractedkeywords which are taken as features into a training cascade classifier, the enterprises are classified by each level of classifier, and the unclassified enterprises are classified according to the next level of classifier. According to the method, keywords can be automatically constructed, updated and classified, the problem of classifying millions and millions of enterprise industries is solved,and the problem of artificial labelling is effectively solved.

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.

A computer implemented method and system for detecting interest sections in a still image are provided. One or more sub images of the still image is subjected to segmentation. A gray scale version of interest sub images and/or a binary image version of the interest sub images are matched with a predefined template for filtering the interest sub images. Multiple prospective image sections comprising one or more of prospective interest sections and prospective near interest sections are determined by performing discriminative feature analyses of the filtered interest sub images using a gabor feature filter. The discriminative feature analyses are processed by a boosted cascade of classifiers. The boosted cascade of classifiers detects the interest sections in the still image from the prospective interest sections and the prospective near interest sections. The detected interest sections are subjected to a support vector machine classifier for further detecting interest sections.

The invention discloses a face detection method and device adopting a cascade classifier, relating to the field of video monitoring. The face detection method comprises the following step of: carrying out face detection on rectangular windows with different positions and sizes in a current image to be detected by adopting a light type cascade-structure classifier to detect face windows, wherein each level of the light type cascade-structure classifier is a weak classifier. For a large quantity of windows to be detected in one image, relative to a scheme that a cascade-structure classifier is bound to eliminate partial non-faces after computing the results of all weak classifiers of a strong classifier, each weak classifier of the light type cascade-structure classifier can eliminate the partial non-faces, and therefore faster detection speed can be achieved, and the real-time detection of faces is further realized on megapixel high-definition videos.

The invention discloses an urban road traffic state detection method combined with a support vector machine (SVM) and a back propagation (BP) neural network. The method comprises the following steps of: 1) monitoring traffic characteristic parameters of a road section in real time, and extracting the traffic characteristic parameters to obtain a test sample set, wherein the traffic characteristic parameters comprise a vehicle average speed v (m/s), a vehicle flow size f (veh/s), time occupancy s and travel time t (s); and 2) inputting the test sample set into two layers of cascade classifiers of SVM1-SVM2/BP, wherein the step 2) comprises the following substeps of: 2.1) training the two layers of cascade classifiers by applying an SVM1 training function, and inputting into an SVM1 classification function together with test sample data, judging whether the SVM1 classification function is in a smooth state, if so, determining that the current state is the smooth state, otherwise, entering the substep 2.2); and 2.2) performing vote combination classification on the test sample set by the second layer of SVM2 and BP network classifier, and judging whether the test sample set is in a busy state or a congestion state. By the method, the accuracy can be effectively improved.

The invention discloses a face detection method based on a picture geometric structure, comprising a training process of face models and a detecting process of face images. The method comprises the following: the step of the training process of face models is divided into a step of training sample normalization, a step of feature extraction, a partitioning step of dividing a sample by adopting a block with a proper size, a step of drawing all differential values acquired by operations into a feature column vector to submit to a classifier for learning, a learning process of a fall type support vector machine and a classification against a sample picture in each window by using a cascade classifier; and the step of the detection of face images is to mark a detected face. The face detection method solves the problem generally existed in the field that the prior art aims at the local structure of a picture but can not completely and accurately express global information of the picture, and can detect a face quickly and accurately.

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.

The invention discloses a work method of an identification and early-warning system based on pedestrians and bicycle riders in front of a vehicle. An offline training module selects positive and negative samples of the upper half of the body from a video shot by the practical vehicle, an Adboost algorithm is used for training to obtain a cascaded classifier for identifying the upper half of the body, the cascaded classifier is provided for an online detection module, the online detection module uses a CCD camera to collect images, a video collection card is used for conversion, and an improved multi-scale scanning method is used for preprocessed images to obtain a subwindow; and the online detection module selects an identified target frame, and transmits the target frame to a collision early-warning module, and the collision early-warning module uses a monocular visual range-finding geometric model to calculate the horizontal distance X and the vertical distance D between a target and the vehicle, the vertical speed Vy of the target and the vertical collision time TTC; and such information and the speed of the vehicle u are integrated to determine the danger degree of the target, a driver is prompted timely, and accidents can be reduced o protect the pedestrians and bicycle riders.

The invention provides a method and a system for intelligently analyzing vehicle behaviour. The corresponding method comprises the steps of collecting a sample set containing vehicles and a background sample set which does not contain vehicles, selecting predetermined Haar rectangular features to conduct offline training through an AdaBoost algorithm, and obtaining a cascade classifier which can find out vehicles from complicated backgrounds; obtaining video resources, and detecting video resources through the cascade classifier to identify vehicles in images; constructing a vehicle detector with identified vehicles serving as identified positive samples, tracking all vehicles through an optical flow method, and obtaining motion trails of all vehicles; and detecting traffic signs in video resources, combining traffic signs to analyze motion trails of vehicles, and determining whether vehicles violate rules. By the aid of the method and the system, vehicles can be tracked in complex scenarios and dynamic videos, and whether driving of vehicles violates rules can be determined.

The invention discloses a method for performing multi-visual-angle face detection by means of integral channel features. The method is mainly characterized in that three LUV color channels in ten ACF channels are improved for obtaining a gray scale single channel, thereby forming an eight-channel characteristic and realizing quicker feature extraction; four-stage Adaboost cascaded classifier training is performed on the extracted features, thereby forming a cascaded strong classifier which comprises 4096 weak classifiers; and image detection is performed by means of the cascaded classifier and a quick feature pyramid method for quickly and accurately detecting faces. According to the method of the invention, detecting blocks are acquired by means of successive sliding of a sliding window on a characteristic pyramid according to a step length; the detecting blocks are classified by means of the trained Adaboost classifier; overlapped window elimination is performed on the detecting blocks which comprise the faces through a non-maximum suppression method; a final face detection window is kept and detection precision is improved.

The invention discloses a pedestrian detection method based on combined features. A certain number of training samples which are the same in size comprise positive samples which comprise pedestrians and randomly intercepted negative samples which do not comprise the background of the pedestrians. Statistical structure gradient features of the training samples are extracted and then delivered to a support vector machine to train, and a classifier is obtained, and then a cascade structure is used to train an n-layer cascade classifier, an offline cascade classifier is obtained to be as a final classifier which distinguishes the pedestrians, the pedestrians in a photo or a video are detected by the final classifier and marked out. The pedestrian detection method based on the combined features can accurately describe the pedestrians and calculate simply, and can balance detection accuracy and detection speed well.

The invention relates to an urban road traffic condition detection method based on the voting of a network sorter, which comprises the following steps: 1) monitoring traffic characteristic parameters in real time, and extracting the traffic characteristic parameters so as to obtain test sample sets, wherein the traffic characteristic parameters comprises average vehicle speed v(m/s), vehicle flow f(veh/s), time occupancy ratio s, and travel time t(s); 2) respectively carrying out classification by a SVM (support vector machine)classifier, a BP(beeper) neural network, and a SVM-BP (support vector machine-beeper) cascade classifier in the method of combining the voting of the SVM classifier, a BP neural network, and a SVM-BP cascade classifier; if the three categories are same, sorting the test samples into the category; or if two categories are same, comparing the sum of two weights of the same category with the weight of different categories so as to determine large weights as the classification results; or if the three categories are different, taking the results recognized by the classifiers with the highest weights as the results after the mergence. The urban road traffic condition detection method provided by the invention can efficiently enhance the accuracy.

The invention provides a pedestrian detection method based on saliency information. The method comprises an offline training step and an online detection step; the online detection step comprises calculating a salient map of an image to be detected, extracting a detection child window from the image and calculating the corresponding saliency of the detection child window according to the salient map, calculating corresponding features in the detection child window, detecting the corresponding features in the detection child window through a cascade classifier, and simultaneously distributing adjustment coefficients for the cascade classifier according to the corresponding saliency of the detection child window. According to the method, the saliency information is introduced to be served as auxiliary information for pedestrian detection to participate in the process of image identification on the basis of the existing AdaBoost classifier. In most cases, pedestrians are different from the surrounding environment in terms of color, shape and profile, the saliency information of the child window is adopted for correcting detection results of the classifier, the detection rate can be effectively improved, and the false detecting rate can be reduced.

The invention belongs to the field of recognizing types of vehicles through computer image processing, and relates to a method and system for detecting and recognizing a feature and a brand of a vehicle in a static image by means of a digital picture processing technique. A method for detecting the vehicle in the static image is combined with a vehicle logo detecting method which is based on an AdaBoost framework in the method. The method and system for detecting and recognizing the feature of the vehicle in the static images comprises a training part and a detecting part. The training part includes the following steps of manufacturing a vehicle logo sample, collecting an image containing the vehicle logo from the Internet, positioning the vehicle logo, and extracting the vehicle logo image based on position information; calculating a sample feature, constructing 5 different rectangular features with each rectangular feature corresponding to one Haar feature; training a cascade classifier, inputting the training sample acquired from the last step and conducting training, and finally connecting strong classifiers and multiple corresponding weak classifiers obtained in training in series. The detecting part includes the following steps: loading the image to be detected, converting the image into a grey-scale image and conducting histogram equalization, loading the vehicle logo classifiers which include threshold values of the strong classifiers and the weak classifiers and rectangular feature information corresponding to the selected features, conducting cascade vehicle logo detection with the detected image firstly passing the detection of the former strong classifiers. If the detected image is not the vehicle logo image, the detected image can be excluded at the front end, and only the vehicle logo can finally pass the detection of the strong classifiers at various different levels.