12235 results about "Targeted detection" patented technology

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 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.

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.

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.

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.

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 surveillance video character identity identification system and a surveillance video character identity identification method fusing facial multi-angle features. The surveillance video character identity identification system comprises a target detection module, a multi-angle face identification module and an identity matching module, wherein the target detection module is used for converting a section of surveillance video into a keyframe set containing people; the multi-angle face identification module is used for converting the keyframe set containing people into a face image sequence with angle value tags; and the identity matching module is used for completing feature vector similarity matching of the face image sequence with the angle value tags and an image sequence in an identity library, and finding out proximate identity output as an identification result. The surveillance video character identity identification system and the surveillance video character identity identification method can integrate multi-angle feature information of a face in the surveillance video, thereby improving precision of identity identification when character attitudes in the surveillance video are of great randomness.

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.

The invention provides an infrared images method for detecting targets at sea, which relates to a method for detecting the targets at sea. The invention aims to provide the method for detecting the targets at sea, which not only can well inhibit sea clutters to obtain reasonable image segmentations, but also can extract out the fractal characteristics at a high speed to remove false targets so as to achieve effective detections. The method comprises the following steps: performing preprocessing on the obtained infrared images; performing self-adapting iteration threshold segmentation; detecting whether the part of a sea-sky line has a region of interest (ROI); extracting the ROI at the background part of the sea-sky line; extracting the ROI at the background part of a non-sea-sky line; and combining the regions of interest to obtain an image of interest to be further processed, and extracting the fractal characteristics of each ROI to perform target detections. The method can quickly and effectively segment out the regions of interest in the infrared images, and not only reduces the amount of calculation to extract out the fractal characteristics at a higher speed because the extracted regions of interest is far smaller than the original images, but also can remove the false targets appearing in the threshold segmentation through the fractal characteristics.

The invention provides an MS-KCF (MobileNet-SSD-kernelized correlation filters) based rapid and stable detection method of a human face in an image sequence. To solve the problem about detection of the human face with larger angle change and very severe shielding in the image sequence, a new automatic DTD (detection-tracking-detection) mode integrating rapid and accurate target detection model MSand rapid tracking model KCF is provided, that is, an MS-KCF human face detection model is provided. The method comprises steps as follows: S1, establishing an MS detection network; S2, detecting a target by use of the MS network; S3, updating the tracking model to predict the position of the next frame of human face target; S4, updating an MS detection network after tracking several frames, and performing redetection and positioning on the human face target; S5, comparing and analyzing experiment results. Experiments prove that the MS-KFC model guarantees the detection stability of the humanface with larger angle change and very severe shielding in the image sequence, and besides, the detection speed is greatly increased.