12310 results about "Targeted detection" patented technology

Video is processed by maintaining a background model for the video, detecting a target in the video, detecting if the target is a stationary target, and classifying the stationary target as an insertion in the background model or a removal from the background model.

The present invention describes a system and method of OAM diverse signal processing using classical beams for applications in which OAM signal character is controlled such as optical tagging and applications in which OAM signal character is not controlled such as clutter mitigation and interference cancellation for target detection, identification etc. This is accomplished by transmitting a source beam having a prescribed state with one or more non-zero OAM components, reflecting the beam off a ‘tagged’ or ‘untagged’ target and receiving the return beam in the direct return path to measure the one or more OAM components to identify the target. OAM processing provides additional degrees of processing freedom to greatly enhance the processing capabilities to detect and identify both ‘tagged’ and ‘untagged’ targets.

A collision sense and avoidance system and method and an aircraft, such as an Unmanned Air Vehicle (UAV) and / or Remotely Piloted Vehicle (RPV), including the collision sense and avoidance system. The collision sense and avoidance system includes an image interrogator identifies potential collision threats to the aircraft and provides maneuvers to avoid any identified threat. Motion sensors (e.g., imaging and / or infrared sensors) provide image frames of the surroundings to a clutter suppression and target detection unit that detects local targets moving in the frames. A Line Of Sight (LOS), multi-target tracking unit, tracks detected local targets and maintains a track history in LOS coordinates for each detected local target. A threat assessment unit determines whether any tracked local target poses a collision threat. An avoidance maneuver unit provides flight control and guidance with a maneuver to avoid any identified said collision threat.

A method for delivering radiation therapy to a patient using a three-dimensional planning image for radiation therapy of the patient wherein the planning image includes a radiation therapy target includes the steps of: determining a digitally reconstructed radiograph from the planning image; identifying a region of the target's projection in the digitally reconstructed radiograph; capturing a radiographic image corresponding to the digitally reconstructed radiograph; identifying a region in the captured radiographic image; comparing the region of the target's projection in the digitally reconstructed radiograph with the identified region in the captured radiographic image; and determining a delivery of the radiation therapy in response to this comparison.

A system and method for imaging target detection includes scanning a target area to produce an image of the target area and discriminating a target by identifying image pixels of similar intensity levels, grouping contiguous pixels with similar intensity levels into regions, calculating a set of features for each region and qualifying regions as possible targets in response to the features; discriminating the background by identifying image pixels of similar intensity levels, grouping contiguous pixels of similar intensity levels into regions, calculating a set of features for each background region and qualifying background regions as terrain characteristics in response to the features and analyzing the qualified terrain characteristics and qualified target candidates to determine and prioritize targets.

Imaging systems and methods optimize illumination of objects for purposes of detection, recognition and / or tracking by tailoring the illumination to the position of the object within the detection space. For example, feedback from a tracking system may be used to control and aim the lighting elements so that the illumination can be reduced or increased depending on the need.

A technique for video processing includes: receiving video from a scene; detecting moving pixels in the video; detecting line segments or motion blocks in the video based on the detected moving pixels; identifying targets in the video based on the detected line segments or motion blocks; tracking targets in the video based on the identified targets; and managing the tracked targets in the video.

A target object detection apparatus for identifying a target object by using at least a camera and a wireless tag provided on the target object which exists outside of the target object detection apparatus, comprising: a target detector for reading a first identification information documented in the wireless tag; an image processor for extracting a first image information of the target object imaged by the camera; a personal identifier for identifying an imaged target object by comparing the first image information extracted by the image processor and a second image information specific to the target object; and an integration processor for determining a third identification information of the target object based on at least a second identification information identified by the personal identifier and the first identification information read by the target detector.

The invention discloses a multi-stage target detection method and model based on CNN multistage characteristic fusion; the method mainly comprises the following steps: preparing a related image data set, and processing the data; building a base convolution nerve network (BaseNet) and Feature-fused Net model; training the network model built in the previous step so as to obtain a model of the corresponding weight parameter; using a special data set to finely adjust the trained detection model; outputting a target detection model so as to make target classification and identification, and providing a detection target frame and the corresponding precision. In addition, the invention also provides a multi-class target detection structure model based on CNN multistage characteristic fusion, thus improving the whole detection accuracy, optimizing model parameter values, and providing a more reasonable model structure.

The present invention provides an improved system and method for object detection with histogram of oriented gradient (HOG) based support vector machine (SVM). Specifically, the system provides a computational framework to stably detect still or not moving objects over a wide range of viewpoints. The framework includes providing a sensor input of images which are received by the “focus of attention” mechanism to identify the regions in the image that potentially contain the target objects. These regions are further computed to generate hypothesized objects, specifically generating selected regions containing the target object hypothesis with respect to their positions. Thereafter, these selected regions are verified by an extended HOG-based SVM classifier to generate the detected objects.

The invention discloses a method for measuring the three-dimensional position and the stance of an object with a single camera. The method comprises the following steps of: acquiring an image of a target to be measured by utilizing a single camera; confirming the real-time three-dimensional position and stance information of the target to be measured by accurately identifying marking points on the target to be measured; selecting a suitable camera according to a detection scene and a range and calibrating the camera to acquire inner and outer parameters of the camera; designing target marking points according to the target to be measured and reasonably arranging the marking points; then, detecting the target, identifying characteristic points according to the image shot by the camera, and matching the detected characteristic points with the marking points; and finally, solving the three-dimensional position and stance information of the target to be measured according to the corresponding relation between the measuring points and the object marking points. Whether a non-rigid object is deformed or not can also be detected by using the method. In the invention, the single camera is adopted to realize three-dimensional measurement, acquire the information of the target in a three-dimensional space, such as space geometrical parameters, position, stance, and the like, decrease the measuring cost and the size of a measuring system, and facilitate the operation.

The invention discloses an object detection and tracking method of fusing laser point clouds and images. The method comprises the steps of: S1, respectively collecting laser point cloud data and imagedata of an object, carrying out first object detection according to the collected point cloud data to obtain a first object detection result, and carrying out second object detection according to thecollected image data to obtain a second object detection result; S2, carrying out fusion judgment on the first object detection result and the second object detection result on the basis of Bayesiandecision to obtain final object detection result output; and S3, carrying out object tracking according to a final object detection result. The method has the advantages of a simple and highly-efficient realization method, high object detection and tracking accuracy, high environment adaptability and fault tolerance, stability, reliability and the like.

The invention relates to a self-adaptive background modeling and moving target detecting method which comprises the following steps: establishing an initial background, extracting a moving target binary mask, updating a self-adaptive background and detecting a moving target: firstly, determining the pixel gray value of the initial background by using an inter-frame difference method; successively, carrying out binarization treatment on a difference image by using a self-adaptive threshold valve when a difference image is obtained by a current frame image minus a background image and post-treating of morphological filtering and the like to obtain the moving target binary mask; then, carrying out dynamic update on the gray value of a pixel which is not corresponding to the moving target binary mask in the background image by adopting an region-based background updating method; and finally, carrying out logic 'and' operation by using the moving target binary mask and the current frame input image to detect the moving target. The invention can effectively establish the reliable initial background and carry out real-time dynamic update on the background to solve the problem that the detection accuracy of the moving target is influenced by background disturbance and illumination change.

A method for estimating unknown parameters (pan angle (ψ), instantaneous tilt angle (τ) and road geometry of an upcoming road segment) for a vehicle object detection system. The vehicle object detection system is preferably a forward looking, radar-cued vision system having a camera, a radar sensor and an processing unit. The method first estimates the pan angle (ψ), then corrects the coordinates from a radar track so that pan angle (ψ) can be treated as zero, and finally solves a least squares problem that determines best estimates for instantaneous tilt angle (τ) and road geometry. Estimating these parameters enables the vehicle object detection system to identify, interpret and locate objects in a more accurate and efficient manner.

The invention relates to a rapid target detection method based on a convolutional neural network, and relates to the computer vision technology. The rapid target detection method comprises the following steps: training convolutional neural network parameters by utilizing a training set; solving the problem of max-pooling losing feature by using an expander graph and generating a discriminative complete feature graph; regarding the full-connection weight of the convolutional neural network as a linear classifier, and estimating the generalization error of the linear classifier on the discriminative complete feature by using a probable approximately correct learning framework; estimating the required number of the linear classifiers according to the generalization error and the expected generalization error threshold value; and finally, completing the target detection on the discriminative complete feature graph by using the linear classifiers on the basis of a smooth window. The detection efficiency and the target detection precision are obviously improved.

A technique for video processing includes: receiving video from an overhead view of a scene; detecting moving pixels in the video; detecting line segments in the video based on detected moving pixels; identifying targets in the video based on the detected line segments; tracking targets in the video based on the identified targets; and managing tracked targets in the video.

The invention belongs to the technical field of remote sensing image processing, and particularly relates to a remote sensing image building change detection method, which comprises the following operation steps: (1) reading an image and preprocessing the image; (2) making a sample data set; (3) constructing a network model based on an attention mechanism and a feature pyramid; (4) selecting a training sample to train the network model; (5) selecting a verification sample to verify the network model; and (6) classifying by using the trained model, and outputting a final change detection result. According to the method, a feature pyramid network is introduced, an attention mechanism is used in the multi-scale feature fusion process of all levels, and features are enhanced layer by layer tobe used for target detection of different scales; through application of deformable convolution and cavity convolution, the network obtains the feature expression capability of automatically adaptingto object deformation, the feature size is reserved while the receptive field is expanded, multi-scale information is obtained, the false alarm rate is effectively reduced, and the detection precisionis improved.

Disclosed is a method and system for object detection and tracking. Spatio-temporal information for a foreground / background appearance module is updated, based on a new input image and the accumulated previous appearance information and foreground / background information module labeling information over time. Object detection is performed according to the new input image and the updated spatio-temporal information and transmitted previous information over time, based on the labeling result generated by the object detection. The information for the foreground / background appearance module is repeatedly updated until a convergent condition is reached. The produced labeling result from objection detection is considered as a new tracking measurement for further updating on a tracking prediction module. A final tracking result may be obtained through the updated tracking prediction module, which is determined by the current tracking measurement and the previous observed tracking results. The tracking object location at the next time is predicted. The returned predicted appearance information for the foreground / background object is used as the input for updating the foreground and background appearance module. The returned labeling information is used as the information over time for the object detection.

A technique for video processing includes: receiving video from an overhead view of a scene; detecting moving pixels in the video; detecting line segments in the video based on detected moving pixels; identifying targets in the video based on the detected line segments; tracking targets in the video based on the identified targets; and managing tracked targets in the video.

The invention discloses an active vision human face tracking method and tracking system of a robot; the tracking method comprises the steps that: (1) the mobile robot acquires an environment information image and detects a human face target through an active camera; and (2) after the human face target is detected, the robot tracks the human face target, and maintains the human face target in the center of the image through the active camera and the movement of the robot. The tracking system comprises the active camera, an image tracking module, a movement tracking module, a hierarchy buffer module and a state feedback module. The invention realizes the automatic human face detection and tracking by the robot, overcomes the limitation of a smaller image vision angle and establishes a perception-movement ring of the mobile robot based on active vision by combining the image tracking with the movement tracking, so that the movement scope for human face tracking is expanded to 360 degrees, the all-sided expansion of the tracking scope is ensured. A two-layer buffer region ensures the tracking continuity, so that the human face target is always maintained in the center of the image.

Disclosed herein are diagnostic assays using surface enhanced Raman spectroscopy (SERS)-active particles, including liquid-based assays; magnetic capture assays; microparticle-nanoparticle satellite structures for signal amplification in an assay; composite SERS-active particles useful for enhanced detection of targets; and sample tubes and processes for using the same.

The invention discloses a bend target identification system and method based on multi-sensor fusion, which mainly aims at a problem of front target detection of a vehicle at the bend of expressway. The lane line is divided into a straight line portion of the near view field and a curve portion of the far view field. For information acquisition of a camera, lane line fitting and tracking at the near view field are completed by using Hough transform and Kalman filtering, and curve fitting at the far view field is completed by using a BP neural network. For information acquisition of radar, information of a static object group is extracted, and curve fitting is performed by using the BP neural network. through space-time alignment, the lane line information acquired by vision and the lane line information acquired by the radar are fused to determine a travelable region of the lane where the vehicle is located, and finally a bend target identification algorithm based on the fusion of the camera and the millimeter wave radar is provided by combining the travelable region and the lane line type so as to realize detection for targets at the bend.

An automatic image annotation method for weakly supervised semantic segmentation. The object border is located by an image object detection method, and the semantic label is given. The object border and the semantic label are regarded as a kind of weak supervised semantic label of image level. By using traditional image segmentation method, the whole object region is segmented out, and the segmentation template for training classification network is generated. Then, the segmentation template is used as a supervisory signal to train the classification network. Finally, the trained classification network is used to segment the test image semantically. The technical proposal of the invention utilizes an object detection method to obtain a border and a semantic tag of an object in an image, utilizes a traditional image segmentation method to segment an object region, and combines the semantic tag to serve as a training sample for weak supervision semantic segmentation. The method to automatically generate training samples for weak supervised semantic segmentation, solves the problem of time-consuming and laborious manual labeling of a large number of images.

The invention relates to a significant target detection method based on an FCN (fully convolutional network) and a CNN (convolutional neural network). The method comprises the following steps: firstly, extracting the deep semantic information by use of the FCN, wherein a fixed size of an input image is not needed, end-to-end prediction is performed, and the training complexity is reduced. Accuracy optimization is performed by adopting the CNN and extracting local features to obtain a rough detection result of the FCN. In the invention, the semantic information in an image can be extracted accurately and efficiently, and the improvement of significant target detection accuracy in a complex scene is promoted.

The invention discloses an image target detection method based on DC-SPP-YOLO, which comprises the following steps: firstly, preprocessing a training image sample by using a data enhancement method,constructing a training sample set, aSelecting a prior candidate box for target boundary box prediction by using a k-means clustering algorithm; Then, improving the convolutional layer connection modeof the YOLOv2 model from layer-by-layer connection to dense connection, introducing a space pyramid pooling between the convolutional module and a target detection layer, and establishing DC-SPP-YOLOtarget detection model; And finally, constructing a loss function by using an error quadratic sum between the predicted value and the real value, and iteratively updating model weight parameters to converge the loss function to obtain the DC-SPP-YOLO model for target detection. The invention considers the gradient disappearance caused by deepening convolution network and the insufficient use of multi-scale local region features of YOLOv2 model, and constructs a DC-SPP-YOLO target detection model based on improved convolution layer dense connection and spatial pyramid pooling. the target detection accuracy is improved.

The invention discloses a target detection method and system based on multi-scale feature fusion in an image. The method comprises the steps that firstly, zooming of different scales is carried out byutilizing the to-be-detected picture, and an image pyramid is constructed; secondly, a set of multi-scale detection templates covering most of the sample dimensions is obtained by utilizing a statistical clustering method; thirdly, based on the multi-scale detection template, scale self-adaptive target context construction is performed; fourthly, multi-scale depth features are fused; fifthly, thenon-maximum value restrain based on soft judgment is carried out. The invention is advantageous in that the image multi-resolution sparse pyramid, the multi-scale detection template and the templatescale self-adaptive context, multi-scale depth feature fusion and the like are constructed, full mining and fusion utilization of the depth features are achieved, and the target detection performancecan be improved.

The invention relates to a sea surface micromotion target detection and feature extraction method based on short-time fractional Fourier transform (STFRFT) and belongs to the technical field of radar signal processing and detection. The method comprises the following steps: 1) sea peak identification: dividing sea clutters into sea peak sequences and sea clutter background sequences free of sea peaks; 2) sea clutter data screening: selecting the sea clutter background sequences corresponding to the minimal mean power as data to be detected; 3) FRFT domain micromotion target detection: taking the FRFT domain signal amplitude values as detection statistical quantities and comparing the detection statistical quantities with the thresholds; 4) optimal FRFT domain filtering: extracting multi-component micromotion signals by using a narrow bandpass filter; and 5) setting an optimal time window length and estimating micromotion features in the STFRFT domain. The method can automatically adapt to suppress sea clutters to improve the signal-to-clutter ratio, can effectively isolate and extract the multi-component micromotion signals, provides a new approach to sea surface weak target detection and feature extraction, and is significant in promotion and application.

The invention relates to a full automatic target detecting and tracking system in the computer vision field, wherein, an input module is responsible for collecting digital images shot by a binocular camera to be taken as system input, the obtained digital images are input into a feature extraction module and feature analysis is carried out to one image to obtain a plurality of characteristic points to be taken as the subsequently processed images. By matching the characteristic points of two images, the parallax of the two images is calculated, and by combining the pre-informed external and internal parameters of the camera, the lower coordinate of a camera coordinate system of the characteristic points can be calculated; furthermore, by the relationship between a world coordinate system and the camera coordinate system, the coordinate of the world coordinate system of the characteristic points can be known. A clustering module clusters the characteristic points into an aggregation for expressing target position, while a trajectory analysis module estimates the target position on a time sequence to obtain the motion trajectory of the target. The invention can effectively and steadily detect the targets in a designated area, track the targets and calculate the motion trajectories of the targets.

The method for efficient target detection from images robust to occlusion disclosed by the present invention detects the presence and spatial location of a number of objects in images. It consists in (i) an off-line method to compile an intermediate representation of detection probability maps that are then used by (ii) an on-line method to construct a detection probability map suitable for detecting and localizing objects in a set of input images efficiently. The method explicitly handles occlusions among the objects to be detected and localized, and objects whose shape and configuration is provided externally, for example from an object tracker. The method according to the present invention can be applied to a variety of objects and applications by customizing the method's input functions, namely the object representation, the geometric object model, its image projection method, and the feature matching function.