595 results about "Mean-shift" patented technology

A method for automatically detecting and tracking multiple targets in a multi-camera surveillance zone and system thereof. In each camera view of the system only a simple object detection algorithm is needed. The detection results from multiple cameras are fused into a posterior distribution, named TDP, based on the Bayesian rule. This TDP distribution represents a likelihood of presence of some moving targets on the ground plane. To properly handle the tracking of multiple moving targets with time, a sample-based framework which combines Markov Chain Monte carlo (MCMC), Sequential Monte Carlo (SMC), and Mean-Shift Clustering, is provided. The detection and tracking accuracy is evaluated by both synthesized videos and real videos. The experimental results show that this method and system can accurately track a varying number of targets.

In an SSD controller reading from flash memory, subsequent to failure of an initial soft-decision decoding attempt based on a nominal LLR, soft-decision re-decoding attempts are made using compensated LLR soft-decision information sets, pre-calculated at respective read-equilibrium points corresponding to mean shifts and variance change in the actual charge-state distributions of the flash memory channel. According to embodiment, soft-decision re-decoding attempts are performed without a retry read, or overlapped with one or more retry reads. By overlapping re-decoding with one or more retry reads, the probability of successful decoding increases, the need for further retry reads diminishes, and throughput is improved. The LLR compensation becomes very effective over a large number of retry reads, improving decoding reliability and achieving close to optimal bit error rates, even in the presence of large channel variation.

A method and apparatus for real-time tracking of a non-rigid target. The tracking is based on visual features, such as color and / or texture, where statistical distributions of those features characterize the target. A degree of similarity (rho(y0)) is computed between a given target (at y0) in a first frame and a candidate target (at y1) in a successive frame, the degree being expressed by a metric derived from the Bhattacharyya coefficient. A gradient vector corresponding to a maximization of the Bhattacharyya coefficient is used to derive the most probable location of the candidate target in the successive frame.

This invention puts forward a method and a system for real time testing and continuous tracking of man-face in a video sequence including the following steps: carrying out a test algorithm to a man-face input video image, then applying a rough and fine two stages of test algorithm to verify the tested face, applying an object following algorithm to follow the verified one and verifying it by verifying the followed regions, which realizes a real time test to a positive and vertical man-face by a test method based on AdaBoost statistic hierarchical sorter and Mean shift and a square pattern property.

A computer-interfaced camera system identifies and tracks groups of socially interrelated people. The system can be used, for example, to track people as they wait in a checkout line or at a service counter. In a preferred implementation, each recorded camera frame is segmented into foreground regions containing several people. The foreground regions are further segmented into individuals using temporal segmentation analysis. Once an individual person is detected, an appearance model based on color and edge density in conjunction with a mean-shift tracker is used to recover the person's trajectory. Groups of people are determined by analyzing inter-person distances over time.

The invention relates to a color image three-dimensional reconstruction method based on three-dimensional matching, comprising the following steps of: (1) simultaneously and respectively taking an image from proper angles by using two color cameras; (2) respectively calibrating the internal parameter matrixes and the external parameter matrixes of the two cameras; (3) carrying out polar line correction and image transformation according to calibrated data; (4) working out matching cost for each pixel point in the two corrected images by applying a self-adaption weight window algorithm and acquiring an initial parallax image; (5) marking the reliability coefficient of the pixel initial matching result by adopting matching cost reliability detection and left and right consistency verification; (6) carrying out color segmentation on the images through a Mean-Shift algorithm; (7) carrying out global optimization by a selective confidence propagation algorithm on the basis of color segmentation and pixel reliability classification results to obtain a final parallax image; and (8) working out the three-dimensional coordinates of actual object points on the images according to the calibrated data and the matching relation, thereby reconstructing the three-dimensional point cloud of an object.

A method of coronary vessel segmentation and visualization includes providing a digitized coronary image, placing a plurality of seed points along an estimated centerline of a coronary vessel, selecting a seed point and constructing a cyclic graph around the seed point in a plane perpendicular to the centerline at the seed point, performing a multi-scale-mean shift filtering in the perpendicular plane to estimate image gradient values, detecting a vessel boundary using a minimum-mean-cycle optimization that minimizes a ratio of a cost of a cycle to a length of a cycle, constructing a sub-voxel accurate vessel boundary about a point on the centerline, and refining the location of the centerline point from the sub-voxel accurate boundary, where the steps of constructing a sub-voxel accurate vessel boundary and refining the centerline point location are repeated until convergence.

The invention belongs to the crossing field of computer vision and intelligent robot, and discloses a new multi-feature multi-sensor method for a mobile robot to track a moving body. The method comprises the following steps: 1, coarsely positioning a body carrying a passive tag around a radio frequency identification (RFID) system by using the RFID system; 2, initially positioning the body in an image by using an adaptive template matching algorithm based on head and shoulder features; 3, accurately positioning the body in the image by using a multi-feature-based mean-shift algorithm; 4, predicting the moving state of the body by using a extended Kalman filter algorithm; 5, screening the acquired target position information by using a double-layer collaboration positioning mechanism; and 6, controlling the robot to move along with the body by using a robot following control algorithm. By the method, bodies with different poses can be tracked, the problem that the tracking is influenced when a target suddenly turns and is shielded is solved, and the robot can accurately, stably and continuously track the moving body.

A method locates an object in a sequence of frames of a video. A feature vector is constructed for every pixel in each frame. The feature vector is used to training the weak classifiers. The weak classifiers separate pixels that are associated with the object from pixels that are associated with the background. The set of weak classifiers are combined into a strong classifier. The strong classifier labels pixels in a frame to generate a confidence map. A ‘peak’ in the confidence is located using a mean-shift operation. The peak indicates a location of the object in the frame. That is, the confidence map distinguishes the object from the background in the video.

A method tracks a moving object in a video acquired of a scene with a camera. A background model is maintained for each frame, and moving objects are detected according to changes in the background model. An object model is maintained for the moving object, and kernels are generated for the moving object. A mean-shift process is applied to each kernel in each frame to determine a likelihood of an estimated location of the moving object in each frame, according to the background models, the object model, and the mean shift kernels to track the moving object in the video.

A system and method for detecting and tracking humans, such as pedestrians, in low visibility conditions or otherwise. A night vision camera periodically captures a an infrared image of a road from a single perspective. A pedestrian detection module determines a position of a pedestrian in the frame by processing the captured image. The pedestrian detection module includes a support vector machine to compare information derived from the night vision camera to a training database. A pedestrian tracking module estimates pedestrian movement of the detected pedestrian from in subsequent frames by applying filters. The tracking module uses Kalman filtering to estimate pedestrian movement at periodic times and mean-shifting to adjust the estimation. An output display module interleaves detection frames and tracking frames in generating output video for the display.

The invention provides a method for converting a two-dimensional video into a three-dimensional video automatically. The method comprises the following steps of: firstly, performing Gauss modeling on the background of a static scene with a mobile object to reestablish a static background and segment an approximate foreground region out; secondly, performing geometrical classification on each pixel of a background image by using monocular geometrical information and a classifying studying algorithm and obtaining a depth map according to a classification result; segmenting the image of the foreground region by using a mean shift algorithm; performing edge detection, edge connection and endpoint elimination on the image to obtain a precise foreground region; and fusing the precise foregroundregion with the depth map of the background to obtain the depth map of each frame. The synthesis algorithm of a right view comprises the steps of first reestablishing the background in the right viewand then repairing holes by using the right view background. By the method, the obtained left and right views are projected on three-dimensional display equipment, so that an excellent three dimensional (3D) effect can be automatically achieved and the manpower is not required.

The invention provides a face detecting and tracking method and a device. The method comprises the steps of inputting a face image or a face video, preprocessing the face image or the face video in an illumination mode, detecting a face by usage of an Ada Boost algorithm, confirming an initial position of the face, and tracking the face by the usage of a Mean Shift algorithm. According to the face detecting and tracking method and the device, a self-adaptation local contrast enhancement method is provided to enhance image detail information in the period of image preprocessing, in order to increase robustness under different illumination conditions, face front samples under different illumination are added to training samples and accuracy of the face detection is increased by adoption of the Ada Boost algorithm in the period of face detection, in order to overcome the defect that using color of the Mean Shift algorithm is single, grads features and local binary pattern length between perpendiculars (LBP) vein features are integrated by adoption of the Mean Shift tracking algorithm in the period of face tracking, wherein the LBP vein features further considers using LBP local variance for expressing change of image contrast information, and accuracy of the face detection and the face tracking is improved.

A method and a system for spatial scalable region of interest transcoding of JPEG2000 coded video frames for video surveillance systems are shown. Based on a user defined ROI the method transcodes HD frames into images in moderate resolution with a ROI in HD resolution.The transcoder extracts all packets belonging to the ROI or the lower resolution levels of the background from the JPEG2000 bitstream. Non-ROI packets of higher resolution levels are replaced by empty packets. The ROI is tracked using a mean shift algorithm to guarantee that always the correct image details are extracted in high resolution.Since the transcoding is performed by extracting and replacing packets of the codestream, an expensive re-encoding of the code-stream is not required. Thus, the transcoding technique is of low complexity and shows a short processing time.Combining the transcoding technique with mean shift tracking leads to a powerful video transcoding technique.

The invention relates to an anti-overlap method for tracking a moving target based on mean shift and belongs to the image processing technology field. The method comprises the following steps: constructing a mean shift model and a Kalman filter model; pre-estimating by utilizing a Kalman filter to obtain the initial position of searching each frame mean shift; obtaining the outline of an object by an image difference method; and defining whether similar factors can shade the object or not. When the similar factors shade the object, the position of the object in current frame is predicted and serves as a starting point for predicting the next frame by attaching different weights to color information and movement information respectively, according to the difference of mobile status of the object. Accordingly, the linear prediction of target position replaces the function of Kalman filter. Experiments prove that the method can realize the tracking of a quickly moving object and has good robustness for shading.

A head-up display device includes a light source, a display unit for producing display virtual images including an alarm display image, a mirror for reflecting the light to show the alarm display image in a field of front view of a driver, at least one on-vehicle device that the driver operates, a visual-line shift detecting means and a display position shifting means. The mirror reflects the light representing the alarm display image so that a driver can see the alarm display image in a display area that is set on one of a front windshield and a combiner in front of the driver and in a field of front vision of the driver. The visual-line shift detecting means detects a visual line shift of the driver from a usual forward visual range of the driver toward the on-vehicle device that the driver operates. The display position shifting means shifts positions of the display area to a position between the usual forward visual range and a portion / part, of the on-vehicle device at operation, which the driver watches during the operation when the visual-line shift detecting means detects the visual line shift from the usual forward visual range toward the on-vehicle device.

A method tracks a moving object in a video acquired of a scene with a camera. A background model is maintained for each frame, and moving objects are detected according to changes in the background model. An object model is maintained for the moving object, and kernels are generated for the moving object. A mean-shift process is applied to each kernel in each frame to determine a likelihood of an estimated location of the moving object in each frame, according to the background models, the object model, and the mean shift kernels to track the moving object in the video.

The invention discloses a method for selecting an autonomous landing area of an unmanned aerial vehicle (UAV) under a complex environment based on visual SLAM, which is used for solving the technical problem of poor practicability of the existing UAV landing area control method. According to the technical solution, the method comprises the steps of obtaining an image sequence via an overlooking monocular camera carried by a UAV mobile platform, calculating the pose of the UAV in real time via an SLAM algorithm and establishing a sparse point cloud map, and meshing the point cloud map to construct a two-dimensional grid height map; then dividing the grid map according to the height in combination with a Means shift image segmentation algorithm, and finally screening an area that is farthest from a potential obstacle and is suitable for landing of the UVA according to the landing height requirement. According to the method, the pose of the UAV is calculated by adopting the monocular visual SLAM and estimated in real time, the two-dimensional grid height map is constructed, and the area suitable for landing of the UVA is screened. The method, which does not depend on a landmark, has good practicability.

A method for segmentation of 2D structures in CT and MR images is provided. The method is based on 2D ray propagation by mean-shift analysis with a smoothness constraint. Ray propagation is used to guide an evolving curve due to its computational efficiency and shape priors are incorporated for robust convergence. The method includes the steps of receiving 2D image data; visualizing the 2D image data on a display device; selecting a structure in the 2D image data by placing a seed in the structure; initializing a plurality of rays from the seed to form a curve; determining a speed function of each of the rays; evolving the curve by propagating the rays based on the speed function of each of the rays; converging the rays on a boundary of the structure; and segmenting the structure when all of the rays have converged on the structure's boundary.

A system and method for automatic scale selection in real-time image and video processing and computer vision applications. In one aspect, a non-parametric variable bandwidth mean shift technique, which is based on adaptive estimation of a normalized density gradient, is used for detecting one or more modes in the underlying data and clustering the underlying data. In another aspect, a data-driven bandwidth (or scale) selection technique is provided for the variable bandwidth mean shift method, which estimates for each data point the covariance matrix that is the most stable across a plurality of scales. The methods can be used for detecting modes and clustering data for various types of data such as image data, video data speech data, handwriting data, etc.

The present invention discloses a method of automatically detecting and tracking a face by an electronic capturing device that alternatively uses a face detecting algorithm to quickly locate a face in a frame based on a skin color model and a face tracking algorithm to locate a face in subsequent frames by a nonparametric technique and a mean shift algorithm. If the face tracking algorithm cannot track and locate a face correctly, the face detecting algorithm will be used again to detect a face position in another new frame until the face position is located successfully, and then the face tracking algorithm will be used again for detecting and locating the face position in subsequent frames. After this method has detected a face position, a variable focal lens is used to slowly and smoothly refocus the frame including a face region, so as to obtain a clear face image.

The invention discloses an object-oriented remote sensing inversion method of a leaf area index of a crop, comprising the following steps of: acquiring multispectral remote sensing data; calculating a biomass spectral index NDVI (Normalized Difference Vegetation Index), a crop nutrient spectral index BRI and a water sensitive spectral index NDWI (Normalized Difference Water Index) of a crop colony by utilizing the acquired multispectral remote sensing data; carrying out object-oriented segmentation and encoding according to the biomass spectral index NDVI, the crop nutrient spectral index BRI and the water sensitive spectral index NDWI of the crop colony by utilizing a mean shift algorithm; sequentially carrying out the original spectral mean calculation of pixels on objects according to an encoding sequence to obtain a spectral index SAVI (Soil-Adjusted Vegetation Index) sensitive to the LAI (Leaf Area Index), and carrying out texture structure calculation; building a regression model of ground LAI observation data, the spectral index SAVI sensitive to the LAI and the texture structure calculation; and carrying out inversion calculation on the object without the ground LAI observation data by utilizing the regression model to obtain the LAI of the object without the ground LAI observation data.

The invention relates to a method for detecting and tracking an infrared small target in a complex background. In consideration of problems of low SNR (Signal Noise Ratio), great noise and instability of tracking based on single feature of an infrared image, the method provided by the invention comprises the following steps of: firstly, extracting an interested target region as a detection result by using variance weighted comentropy, creating a target template according to gray level and textural features, and implementing the aim of tracking the infrared small target through Mean Shift algorithm. With the method, the problem of instability of tracking based on single feature in complex background is effectively avoided, and the availability of the method is checked in tracking experiments of a plurality of infrared video sequences.

An image processing method can be performed on a video image that includes an initial frame and a plurality of subsequent frames. An object is located within the initial frame of the video image and a histogram related to the object is generated. A foreground map that includes the object is also generated. For each subsequent frame, a mean shift iteration is performed to adjust the location of the object within the current frame. The histogram related to the object and the foreground map can then be updated.

A cost effective method for detecting, classifying and tracking the pedestrian present in front of the vehicle by using images captured by near infrared (IR) camera disposed on the vehicle, the said method comprises the processor implemented steps of: detecting the road to focus of attention for filtering the region of interest (ROI) objects in the said image by estimating the ground region characterized by identifying smooth regions connected to bottom most part of the image; eliminating the non-ground objects based on their distance to ground; filtering the non-ROI objects based on the shape of such objects by computing the signal to noise ratio (SNR) which is a measure of regularity of the component based on its periodicity of its contour for each of such non-ROI objects; eliminating the non-vertical objects by computing inertial moment relative to x and y axis with respect to the centre of mass of such non-vertical objects; classifying the pedestrians in the analyzed frame of the image based their shape; and tracking the movement of the classified pedestrian using mean shift algorithm.

The invention relates to a method for segmenting a remote sensing image and belongs to the technical field of processing of the remote sensing image. The method comprises the following steps of: according to color feature, textural feature and the position information of a pixel point, generating a feature vector which serves as an initial input vector; segmenting the remote sensing image by using mean shift filtering; and adaptively determining weights of the color feature and the textural feature by using constructed cluster validity indexes to effectively improve the segmenting accuracy ofthe remote sensing image. The invention also discloses a method for searching the remote sensing image by using the method for segmenting the remote sensing image. The search of the remote sensing image is finished by using a new region representation and matching method. Compared with the prior art, the invention has higher search accuracy, particularly for search of a small target region.

The invention discloses a visual attention and mean shift-based target detection and tracking method. The method comprises the following the steps: firstly, extracting the salient region of a first frame image in an image sequence by using a visual attention method, and removing interferences of background factors to obtain a moving target; then, changing fixed bandwidth of a kernel function in a traditional mean shift method into dynamically changed bandwidth, and tracking the detected moving target by using an improved mean shift method. Shown by an experimental result, the visual attention and mean shift-based target detection and tracking method disclosed by the invention is suitable for infrared and visible image sequences, and better in tracking effect. Moreover, the positional information of the moving target also can be provided by the visual attention and mean shift-based target detection and tracking method disclosed by the invention, and thus, possibility is provided for accurate positioning of the target. The visual attention and mean shift-based target detection and tracking method has a broad application prospect in the military and civil field of night vision investigation, security and protection monitoring, and the like.