32results about How to "Realize multi-angle observation" patented technology

The invention discloses a blood vessel straightening and reconstructing method based on a heart CT image, comprising the following steps: S1, the 3D CT data of the heart and the center line data of blood vessels are obtained; S2, each point on the center line of the blood vessels is extended in the forward and backward directions respectively to obtain a specified number of points, every four adjacent points are connected into a quadrangle, and the quadrangles are combined to generate a surface; S3, the world coordinates of the points on the surface are enabled to correspond to the image coordinates in the 3D CT data of the heart through an interpolation method to obtain corresponding pixel gray, and a gray surface is obtained; and S4, the surface is straightened, projected and mapped to arectangular plane to obtain a straightened reconstructed image of the blood vessels. The method has the advantages as follows: the blood vessels can be presented to doctors more visually to realize multi-level and multi-angle observation; and doctors can make a qualitative or quantitative analysis of the blood vessels more quickly and accurately to find the locations of lesions (such as stenosis,occlusion, aneurysm and vascular wall calcification).

The invention discloses a body joint distributed information consistency estimation method based on interacting multiple models. The method comprises the following steps: initializing a skeleton joint position; estimating joint motion by use of a local sensor; constructing a motion model and an observation model by virtue of a human body joint, and realizing effective estimation on a joint state; estimating information consistency of a target joint between the sensors, i.e., each sensor transmits a joint information vector and an information matrix which are estimated by the sensor and corresponding information contribution and model probability to an adjacent communication sensor node and receives information of the surrounding sensors; by virtue of utilizing an information consistency algorithm and fusing the estimation results of the surrounding sensors, subsequent iteration is performed for multiple times, and convergence of the algorithm and the estimation result is realized; by virtue of constructing a distributed RGBD sensor network, and utilizing the information consistency algorithm, distributed estimation of human body joints is realized; no data fusion center exists in a network, so that robustness of a system for node information mistake and invalidity is improved, and expansion of the sensor network is relatively easily realized.

The invention discloses a rail-mounted multi-dimensional measurement platform which comprises a track, a moving tower, an instrument erection platform and a computer control operating system. The moving tower comprises a digitization walking mechanism, a digitization rotating mechanism, a digitization vertical movement mechanism and a digitization luffer, wherein the digitization walking mechanism is used for enabling the moving tower to move along the track, the digitization rotating mechanism is used for enabling the upper part of the moving tower to move relatively to the lower part of the moving tower, the digitization vertical movement mechanism is arranged in a tower arm which is located on the upper part of the moving tower and capable of changing the height of the instrument erection platform, and the digitization luffer is used for changing.

The invention discloses a polling robot for a cable tunnel. The polling robot comprises a robot body, a walking assembly, monitoring assemblies and multiple telescopic mechanical arms; one end of eachmechanical arm is installed on the robot body, and the other end of each mechanical arm is connected with the corresponding monitoring assembly; the walking mechanism comprises walking supports and walking wheels; the walking wheels are installed on the walking supports which are connected with the robot body. On a robot rail, the polling robot moves, the telescopic mechanical arms drive the monitoring assemblies, and cables can be observed by multiple angles from a short distance.

The invention discloses a color image and depth image multi-feature-based joint data association method. The method comprises the steps of performing data association between a tracking target and target observation for the first time by local sensor nodes through adopting a joint probabilistic data association (JPDA) algorithm; performing data association on the tracking target between the sensor nodes for the second time by a Mahalanobis distance-based Hungarian algorithm; and during the data association for the first time, establishing three thresholds (gamma z, gamma c, gamma d) by utilizing joint point position observation information z, a color image gradient orientation histogram characteristic hc and a depth image gradient orientation histogram characteristic hd by a multi-feature-based target observation candidate set adjustment mechanism to define the size of an observation set. According to the method, the estimation precision and executive efficiency of the JPDA algorithm can be improved.

The invention provides a large-scale scene virtual sky modeling method under the condition of multi-viewpoint multi-view-angle view field displaying. Firstly, three-dimensional realistic modeling of a combined type sky pillar and other individual objects is carried out, then integration of virtual large-scale scenes based on the combined type sky pillar is finished, motion rules of the combined type sky pillar and other motion models are set, and finally viewpoints based on the combined type sky pillar are set. The large-scale scene virtual sky modeling method under the condition of multi-viewpoint multi-view-angle view field displaying effectively achieves multi-viewpoint and multi-view-angle observation and real-time three-dimensional realistic displaying of observation view fields, achieves a continuous and smooth sky background switch-over effect both in the horizontal direction and in the vertical direction, can meet virtual sky modeling requirements of multi-viewpoint and multi-view-angle observation and three-dimensional realistic displaying of view fields in large-scale scene visual simulation.

A movable type multi-dimensional measuring platform comprises a movable chassis, a rotary telescopic boom, a working platform, a two-dimensional rotating table and a computer control operation system. The movable chassis is the basis of the measuring platform and used for achieving free rotation of the whole measuring platform. The rotary telescopic boom is installed on the movable chassis and can rotate in a slewing mode and move in a telescopic mode. The working platform is located at the tail end of the rotary telescopic boom, and the two-dimensional rotating table is hung on the bottom of the working platform and can freely rotate in the directions of azimuth and pitching. The computer control operation system is capable of controlling the movement of the rotary telescopic boom, the working platform and the two-dimensional rotating table. The measuring platform has the advantages of being mobile, flexible and convenient to move. The measuring platform can carry out observation tests on intended targets of different places, and can accurately control the observation distance and observation precision.

The invention discloses a sensor network based mobile robot and static sensor task cooperation method, which comprises the steps that a dynamic distributed sensor network is built, and consistency estimation is carried out on acquired human body articulation point distributed information; color image and depth image based multi-feature joint data association is performed after consistency estimation is carried out on the human body articulation point distributed information; distributed DTW human body behavior intension recognition is carried out based on human body behavior characteristics; on the basis of a behavior recognition result, a mobile robot participates in a bidding service by using a contract net method and provides robot services in allusion to specific behaviors of a user; when an estimation error of a static sensor for a certain articulation point of the human body exceeds a set value, a request for a close-range checking task is initiated, an adjacent mobile robot bids for the task and executes the task, and close-range observation for a specific target is realized. The sensor network based mobile robot and static sensor task cooperation method provides close-range observation in allusion to an observation blind area on the one hand, and provides corresponding intelligent services for special behaviors of the human body on the other hand.

The invention relates to a multi-angle remote sensing automatic observation system based on an unmanned aerial vehicle. The multi-angle remote sensing automatic observation system comprises a multi-angle cradle head, a multi-angle cradle head controller, an air line planning module, a data processing module and a control system. The multi-angle cradle head is fixedly installed on the unmanned aerial vehicle. The multi-angle cradle head controller is arranged on the multi-angle cradle head and in communication connection with the control system. An observation instrument is arranged on the multi-angle cradle head. The air line planning module is connected with the control system. The data processing module is connected with the observation instrument and the control system. The multi-angle cradle head comprises a pitching plate, a pitching vertical plate, a transverse rolling plate, a transverse rolling vertical plate, a cloud platform support and a cloud platform. The multi-angle remote sensing automatic observation system based on the unmanned aerial vehicle is convenient to carry, capable of conducting automatic observation and high in observation efficiency and adaptability.

The invention discloses a microscopic dynamic monitoring device and a repairing method for a ceramic historical relic painting layer micron-scale crack. The device is formed by connecting a work bench, an ultra depth-of-field microscope, a repairing table, a tripod, a rotating shaft, an adjusting frame screw and a lens. When the ceramic historical relic painting layer micron-scale crack is repaired by the device, a cultural relic is arranged on the rotating shaft; a lens of the ultra depth-of-field microscope is adjusted to amplify a historical relic painting layer; the micron-scale crack is positioned through an image processor; the lens is adjusted by rotating the tripod, so that the image processor clearly displays the crack and then fixes the cultural relic; the crack is repaired with a reattachment repairing agent; and the whole repairing process is recorded and taken. According to the microscopic dynamic monitoring device disclosed by the invention, the painting layer micron-scale crack can be accurately positioned; the crack size can be accurately measured; multi-angle and multi-azimuth observation is achieved; an image and a video in the repairing process can be collected in real time; data and image collection is visual and accurate; and the repaired crack is completely closed and fitted.

The invention discloses an artificial intelligence device capable of monitoring agriculture and forestry diseases and insect pests and relates to the technical field of agriculture and forestry. The artificial intelligence device comprises a trunk and a first fixing sleeve. One side of the first fixing sleeve is fixedly connected with a fixing plate, and the top and the bottom of one side of the fixing plate are fixedly connected with supporting rods correspondingly; a square frame is rotatably connected between the opposite sides of the two supporting rods through connecting shafts, and the inner surface of the square frame is fixedly connected with two rotating devices; the opposite sides of the two rotating devices are mutually engaged through annular grooves, and the other sides of therotating devices are fixedly connected with probes. According to the artificial intelligence device capable of monitoring the agriculture and forestry diseases and insect pests, the probes can be driven to rotate certain angles simultaneously through the relation that the annular grooves in one sides of the two rotating devices are mutually engaged, then power can be provided for rotating of therotating devices through cooperation of a motor, first gears and a second gear, and thus the situation of the agriculture and forestry diseases and pests can be automatically monitored.

The invention provides a GNSS-R-based fire monitoring system comprising a GNSS satellite transmitting a direct signal, and a temperature sensing device, a GNSS-R receiver, a data storage system, a data discrimination system and an alarm system that are connected in sequence, wherein the temperature sensing device receives a first reflected signal and acquires the peak value and signal-to-noise ratio data of the delayed Doppler waveform; the GNSS-R receiver receives the data, the direct signal and a second reflected signal; the data storage system extracts position information and time information from the direct signal; the data discrimination system receives the above data and information, and judges according to the peak value and signal-to-noise ratio data of the delayed Doppler waveform; the alarm system determines that the alarm sounds in fire area according to the determination result. The invention also provides a monitoring method. The invention uses the direct signal and reflected signals of GNSS, and adopts a temperature sensing device that is extremely sensitive to the forest temperature, so that the forest fire can be determined in real time.

The invention relates to a sealed electromagnetic furnace chamber and relative dual-watch window door, which can baffle electromagnetic wave from human body, wherein back half part of the electromagnetic furnace is fixed in one furnace chamber whose opening is hinged with a furnace door which has a chamber, and the front half part of the electromagnetic is inserted into the chamber of the furnace door. When the furnace door is open, the front half part is exposed to cook food, the front upper part of the furnace door is incline, the front and incline faces of the furnace door are respectively mounted with a watch window to watch the furnace condition. The front of a water accumulation table at the bottom of the furnace chamber is inserted with a water box. The furnace chamber and the furnace door can be made on microwave oven. The invention fixes the electromagnetic furnace in a sealed space formed by a furnace chamber and a furnace door, to baffle the electromagnetic wave from user, with simple watch on the furnace condition.

The invention discloses a boiling phenomenon judgment device based on deep learning and an optical reflection structure, the device comprises a real-time image acquisition device, a data caching device and a machine learning device, wherein the real-time image acquisition device is used for acquiring a video stream in liquid in real time and sending the video stream to the data caching device; thedata caching device is used for storing the video stream data in the liquid acquired by the real-time image acquisition device; the machine learning device is used for extracting the video stream data in the data caching device, analyzing and processing the video stream data and judging the boiling grade of the liquid according to an analysis and processing result, used for carrying out self-optimization based on updated data of the data caching device. On the basis of artificial intelligence training, the judgment efficiency and accuracy of liquid boiling are improved, and judgment is not affected by the chemical property of a solution or the external environment.

The invention provides an electronic arthroscope with an adjustable imaging angle. The electronic arthroscope comprises an endoscope image control box, an image monitor and an endoscopic module, the endoscopic module is in data transmission with the endoscope image control box, and the endoscope image control box is in data transmission with the image monitor; image data acquired by the endoscopic module is processed by the endoscope image control box and then is visually displayed through the image monitor; the endoscopic module comprises a lens assembly, a lens barrel and an adjusting assembly. The imaging angle can be conveniently adjusted, multi-angle observation of the focus position can be achieved, and the problem that a traditional arthroscope is single in visual angle is solved. Compared with a traditional arthroscope, the arthroscope has the advantages that the cost is greatly reduced, the arthroscope can serve as a disposable consumable, disinfection is not needed, the risk of infection caused by incomplete disinfection of the traditional arthroscope is avoided, disinfection and sterilization are not needed before each operation, and the operation preparation time is greatly shortened.

The invention discloses an electric heating constant-temperature incubator convenient to observe, and relates to the technical field of electric heating constant-temperature incubators. A box body is arranged to be spherical and is kept stable through a right-angle supporting frame, and a heating module can heat the interior of the box body by adopting the existing technical means of the electric heating constant-temperature incubator; an arc-shaped observation window is vertically formed in the side wall of the spherical box body, compared with the observation window of an existing electric heating constant-temperature incubator, the area is larger, observation at more angles can be achieved, and a better observation view can be provided.