47results about How to "Reduce search area" patented technology

The present invention discloses a rapid fingerprint identification method based on the singular point topology structure, and the rapid fingerprint identification method can fast process and identifythe fingerprint images in the automated fingerprint identification system by using singular point topology structure in fingerprints. The present invention classifies the fingerprint database accordingto the classification property and position stability of the singular point in fingerprint images, and selects the most reliable singular point as a reference point to build the singular point topolo gy structure of fingerprints and a module to identify; the present invention firstly detects the authenticity of singular points in a fingerprint image, and then classifies the database according tothe relative position of singular points to build a topology structure adjacent to the singular point; and the topology structure can be used to build the fingerprint module to speed up the comparisonprocess of the fingerprints; the rapid matching of fingerprints in the automated fingerprint identification system is a difficulty of the fingerprint recognition technology; the rapid fingerprint identification method, on one hand, can guarantee the recognition performance, on the other hand, can significantly improve the recognition speed of the automated fingerprint identification system, and can widen the scope of application; moreover, the method reforms the prior system slightly.

The invention discloses a satellite communication in motion rapid capturing method; the method comprises the following steps of 1, performing system initializing; 2, establishing a coordinate system;3, carrying out pre-adjustment of antenna pointing; 4, carrying out coarse capture of an antenna; and 5, carrying out accurate alignment of the antenna. The method is simple in steps, reasonable in design and convenient to implement, and pre-adjustment of antenna pointing is realized by utilizing the position and speed information of a carrier detected by a GPS module, so that the target communication satellite can be rapidly captured under different motion states of the carrier, the accurate alignment of the antenna and the target communication satellite is realized, the capture and fine alignment time is short, the stability of the antenna relative to the inertial space is ensured, the rapid response capability of the communication in motion system is improved, and the method is high inpracticability.

The invention is a method for quickly measuring pedestrians on the road ahead based on a vehicle-mounted binocular camera, and discloses a binocular pedestrian detection and ranging method suitable for an automatic driving system. Methods Through the pedestrian detection method based on learning, the pedestrian detection model is trained, and the pedestrian detection model is used to detect pedestrians in the binocular scene. Calculate the matching points of the points selected in the left image detection results in the right image through the color features and scale invariant features, and calculate the disparity value between the matching pairs. The accurate parallax value of the detection result is obtained by finding the median value of the parallax, and the distance between the pedestrian and the camera is calculated according to the geometric relationship between the camera coordinate system and the image coordinate system. Method Aiming at the problems of slow calculation speed and inaccurate distance measurement in the existing methods based on binocular pedestrian detection and distance measurement, the road columnar model is used to speed up the detection speed, and multi-feature point matching is used to improve the accuracy of pedestrian distance measurement in road scenes. accuracy.

The invention discloses a method for extracting vehicle tracks based on unmanned aerial vehicle images, comprising step 1: detecting vehicles based on a Haar classifier; step 2: screening suspected candidate vehicles based on position prediction; step 3: similarity based on 4-channel color histograms Determine the target vehicle; Step 4: Vehicle trajectory extraction; The innovative combination of multi-color histogram similarity of the present invention for target vehicle screening has a high degree of discrimination between the same vehicle and other vehicles; the vehicle trajectory extraction method described in When vehicle tracking is interrupted, it can automatically resume tracking.

The present invention relates to a face detection and tracking method based on FPGA. Firstly, video is collected, and then skin color threshold detection is performed, and the collected video data is converted from YUV format into a binary image, and then spatial filtering is performed to determine skin color pixels, and then Time filtering, to obtain the average value of the pixels of the current frame, to further determine the skin color pixels, and then to filter other skin color interference, to perform face tracking, to obtain real-time face detection results, and finally to use VGA for real-time display. The invention overcomes the cost of existing human face detection and the real-time problem of detection and tracking, the algorithm is relatively simple, the accuracy, speed and real-time performance are high, and the system cost is low.

The invention discloses a natural scene text detection method and system based on a self-heuristic strategy. A two-layer cascade filtering mechanism is established to judge the text area and the background area. Considering that the text area has dark background and light text in the grayscale natural scene image Or two modes of light background and dark characters, the contrast type of the text area is judged so as to unify the contrast of the text area in the grayscale natural scene image into the mode of dark background and light text; As the seed text, a self-heuristic search strategy is constructed for each seed text in its adjacent area, and the trained deep neural network is used to detect missing text in the form of a sliding detection window to improve the recall rate of text detection. Finally, the adjacent text is Words are separated into units. The natural scene text detection method and system disclosed by the present invention have high practical value for realizing automatic understanding of natural scene text semantics.

The invention discloses a determination method of variable granularity of integer ambiguity of a single-frequency receiver in the absolute positioning, belonging to the technical field of satellite navigation and positioning and relating to a method for carrying out the single-point precise positioning by the single-frequency receiver in a satellite navigation positioning system with the utilization of the satellite carrier phase. The determination method is based on the utilization of the single-point static positioning LAMBDA algorithm to calculate the float solution and the distribution variance of the integer ambiguity, firstly carries out the rough integral mapping of the float solution to complete the roughening of the integral domain of search space, then utilizes the rough integral granularity to change the search region and carries out the search of the integer ambiguity according to search conditions to obtain the integral domain of the integer ambiguity; then the rough integral granularity is continuously reduced, the process is repeated till the rough integral granularity is equal to 1, then the search of the integer ambiguity is completed, and the precise carrier phase integer ambiguity is obtained. The use of the invention can rapidly, conveniently and reliably realize the carrier phase high-precision positioning of the single-frequency receiver and can be applied in the low-cost and high-precision navigation positioning system.

In a method for identifying an individual, an individual is recognized using a camera, an individual being positively identified only if the position of the eyes of the individual is identified in a viewing direction-recognizing unit.

The invention relates to a cooperative construction method for enhancing a realistic table-tennis system based on real rackets. The method comprises the following steps of: detecting and tracking a real table-tennis racket by utilizing the color characteristics according to a video image acquired by the system; designing and realizing the virtual-real three-dimensional registration of a virtual scene and a real scene, mapping the virtual scene to a video image coordinate system of the real rackets, participator users and real environment; designing and realizing the collision detection between a virtual table-tennis ball and objects, such as the real rackets, a virtual table-tennis table, a virtual table-tennis net, and the like according to the motion information of the real rackets and confirming and representing the motion trajectory of the virtual table-tennis ball after collision; and providing a finite state machine and a message-processing mechanism, controlling the conversion of various states of the table-tennis system in the operation process and ensuring a plurality of users to have the same table-tennis motion experience. The cooperative construction method can be widely applied to the fields, such as interactive digital entertainment, sports research, training simulation, remote education and training, and the like.