1290 results about "Mass center" patented technology

An improved linear oscillating actuator is capable of minimizing the undesired vibrations while moving first and second oscillators in parallel paths. The first and second oscillators carry first and second drive elements respectively for driving connection to individual reciprocating loads. The first and second drive elements project upwardly respectively from the first and second oscillators such that the first drive element is disposed immediately upwardly of the second oscillator and the second drive elements is disposed immediately upwardly of the first oscillator. With this reverse arrangement of the first and second drive elements relative to the first and second oscillators, the individual oscillating systems each including the oscillator, the drive element and the corresponding reciprocating load can have its mass center disposed in close proximity to a mass center of the actuator, thereby enabling to reduce undesired vibrations which would otherwise occur around the mass center of the actuator.

An apparatus for analyzing movement of equipment. The apparatus includes an inertial measurement unit continuously measuring six rigid body degrees of freedom of the equipment and outputting data representative thereof, wherein the inertial measurement unit defines a planar substrate having a single common plane. The inertial measurement unit further includes at least one angular rate gyro and at least one accelerometer sufficient to measure the six rigid body degrees of freedom and each being mounted on the single common plane. The apparatus further includes a processing unit determining the acceleration of the mass center of the equipment, the angular velocity and the angular acceleration of the equipment through a single derivative operation.

The invention relates to a two-freedom-degree regulation self-leveling spreader and a regulation method. In the automatic spreader, an inclination sensor judges a current level degree and a motor drives a main lifting sliding block to move in a horizontal plane, so that the posture of a lifted object is regulated. The spreader uses a wireless handheld device to control the spreader; a manual control mode and an automatic control mode are provided; and an operator can selectively use the control modes according to actual lifting conditions. When the posture regulation operation is finished, the spreader can automatically measure and calculate the weight and the position of a mass center of the lifted object and display the information and the current state information of the spreader on the handheld device. The spreader is mainly applied to the lifting operation requiring precise vertical butt joint in the process of assembling large equipment and has the advantages of avoiding repeated regulation and lifting caused by unclear mass center and dissatisfactory posture of the lifted object after the object is lifted, reducing the potential safety hazard caused by complicated operation processes and simultaneously improving the lifting operation efficiency.

The invention discloses a gait control method and a device for a dual-foot robot. The method comprises the steps of selecting gait control parameters for a starting period, a walking period and a stopping period; acquiring the motion trajectory of the mass center of the dual-foot robot during the walking period when the zero moment point of the dual-foot robot is within a stable area; obtaining the first value of each gait control parameter when the mass center is at the initial moment of the walking period and the second value of the gait control parameter when the mass center is at the ending moment of the walking period; setting a first constraint condition at the ending moment of the starting period by utilizing the first value, and setting a second constraint condition at the starting moment of the stopping period by utilizing the second value; based on the first constraint condition and the second constraint condition, calculating the motion trajectory of the mass center during the starting period and during the stopping period respectively; controlling the walking of the dual-foot robot to enable the motion trajectory of the mass center of the dual-foot robot during walking to meet the motion trajectory of the mass center during the starting period, the walking period and the stopping period respectively. According to the technical scheme of the invention, the stable cohesion of the dual-foot robot during the starting period, the walking period and the stopping period and the walking stability of the dual-foot robot can be ensured.

An apparatus and method for balancing a disk are described. A balance ring may be a circular band for placement along the inner diameter of a disk. On the outer diameter of the balance ring, one or more clamp structures may extend outward to attach the balance ring to the inner diameter of a disk. The inner diameter of the balance ring may have a number of protuberances that, when trimmed, establish a new rotational center of the disk / balance ring coincident with the mass center. The disk and balancing ring may be mounted on a disk balancing system to determine a mass center and trim the protuberances, accordingly, to establish adjust the rotational center of the disk / balance ring to be coincident with the mass center. The protuberances may be trimmed using, for example, laser energy.

The invention discloses a vehicle speed detection method based on a target motion track. The method includes the steps of target segmentation, target tracking conducted on the basis of Kalman filtering and speed calculation, wherein the combination of an inter-frame difference method and a fixed threshold value method is mainly adopted in target segmentation, and a segmentation result is acquired; target tracking conducted on the basis of Kalman filtering is divided into the processes of mass center acquisition, motion model establishment, motion target feature extraction and state vector updating, and therefore the target motion track is acquired; a speed calculation method mainly refers to track related point information acquisition, mapping relation establishment, speed calculation and speed correction, the mapping relation establishment mainly refers to conversion from pixel coordinates in an image to actual distances, in other words, the actual distance, corresponding to an actual coordinate system, of each pixel point in the image is calculated, speed calculation mainly refers to calculation of related information provided by the vehicle track in the mode that the distances are divided by time according to a speed calculation formula and a result is corrected according to the actual condition.

A bearing system for a turbocharger shaft includes an elongated bearing carrier with two anti-friction ball bearings mounted in its ends and with a radially extending flange at one end that cooperates with stationary housing portions and carries thrust loads of the rotor in both directions. The elongated bearing carrier is supported within the housing by axially spaced elastic supports which permit the rotating assembly to rotate about its mass center and provide a shock and vibration cushion. The elongated bearing carrier and housing cooperate to provide a coolant cavity which communicates with the outside periphery of the elongated bearing carrier between the axially spaced elastic supports, which also act as coolant seals between the elongated bearing cavity and the bearing housing.

The invention provides a measuring system and a measuring method of mass, center of mass and moment of inertia of a rigid body, and the measuring system comprises a measurement control and analysis unit, a six degree-of-freedom motion platform, a six-component force sensor and a mounting platform, wherein the measurement control and analysis unit is used for controlling the attitude or the motion way of the rigid body by sending a motion signal to the six degree-of-freedom motion platform, and analyzing and calculating the mass, the center of mass and the moment of inertia of the measured rigid body according to the motion signal and force and torque sent by the six-component force sensor; the six degree-of-freedom motion platform is used for carrying out motion in the corresponding attitude or the motion way according to the received motion signal; the six-component force sensor is mounted on the six degree-of-freedom motion platform and used for obtaining the force and the torque received by the measured rigid body by acquiring measurement parameters; the mounting platform is fixed on the six-component force sensor and used for mounting the measured rigid body; and the six degree-of-freedom motion platform drives the measured rigid body to carry out the motion through the six-component force sensor and the mounting platform.The measuring system and the measuring method can realize the measurement of the mass, the center of mass and the moment of inertia, and have the advantages of simple steps and small errors.

A device for measuring the mass center of an object consists of weighing sensors, a measuring table, a tribrach, supporting legs and a computer. Three height adjustable supporting legs are arranged below three feet of the tribrach, three weighting sensors are arranged on the three feet, the three weighting sensors are accurately positioned, and the position points are respectively A, B and C which take an equiangular triangle distribution; the measuring table is arranged on the three weighting sensors, and needs leveling during measurement, the table is marked with marking scales, and rectangular coordinates are established; and three protective supporting studs are also arranged between the tribrach and the measuring table. The three points of A, B and C bear different forces when an object to be measured is put on a horizontal table, the 2D coordinates of the mass center of the measured object are obtained by moment balance calculation, and the 3D coordinate of the mass center can be obtained only by measuring the 2D coordinates of the mass center after the measured object is turned by 90 degrees. The mass center can be obtained quickly and reliably by adopting the computer to acquire and process data.

The present invention improves the orbital maneuvering and power generation capabilities of a system of a satellite(s) connected with a conducting tether(s) by spinning the system about its mass center at an angular rate which is relatively high compared to the average orbital rate. An improvement in tether performance is achieved because at many times during rotation the tether is positioned at much better angles with the magnetic field and significantly higher currents are driven through the tether without destabilizing the system. The current can flow either in the direction of the EMF induced in the tether, or in the reverse direction, depending on the tether orientation with respect to the magnetic field and the mission goals. The reverse current is driven by the onboard power sources. Spinning electrodynamic tether systems can also be lighter and simpler in design and more flexible in operation.

The invention relates to a horizontal and vertical coordination control method for trajectory tracking of an intelligent vehicle. For association and coupling characteristics of horizontal and vertical dynamics of the intelligent vehicle, a horizontal and vertical coordination controller for trajectory tracking of the intelligent vehicle is designed. By applying a model prediction control and sliding mode control algorithm, the opening degree of a throttle valve of an engine, the pressure of a main braking cylinder and the deflection angle of a front wheel are cooperatively controlled. In thedesign of a horizontal MPC, the state amount of the vehicle is selected at the formula which is shown in the description, and the state amount (vertical speed vx) is real-time changable vehicle speedoutput by the vehicle after vertical control; vy is a horizontal speed at the mass center of the vehicle; the formulas which are shown in the description are the heading angle and heading angle speedat the mass center of the vehicle; Y and X are a horizontal position and a vertical position under world coordinates. According to a horizontal and vertical coordination control system, the intelligent vehicle efficiently and stably tracks an expectation trajectory at the expected speed. Large-steering operation can be remarkably improved, and the horizontal stability of the intelligent vehicle inthe trajectory tracking process is improved.

The invention relates to an integral structure of a triaxial optical fiber gyro inertia measuring unit, which comprises a mounting skeleton, three fiber optic gyro scopes, three accelerometers, a light source, a circuit board and a vibration damper. The mounting skeleton adopts a hollow hexahedron frame structure, each group of mounting holes are symmetrically arranged, and mounting lug bosses are arranged on the positioning end surface of the mounting holes. Three fiber optic gyro scopes form mutual space and are orthogonally arranged on the outer surface of the mounting skeleton, the light source and the circuit board are respectively arranged on the outer surface of the mounting skeleton which is corresponding to the three fiber optic gyro scopes, the three accelerometers form the mutual space and are orthogonally arranged on the inner surface of the mounting skeleton which is corresponding to the three fiber optic gyro scopes and near the geometric center of the mounting skeleton, and the vibration damper is arranged on the outer surface of the mounting skeleton. The measuring unit has the advantages that the quality is light; the degree of deviation between the mass center of an inertia measuring unit and the geometric mounting center is very small; the dynamic testing precision is high; the temperature field distribution of the inertia measuring unit is beneficial for the temperature compensation and control of each component, and the like.

The invention provides a motion control system and method for electrically-driven a hexapod robot, relates to the field of motion control of hexapod robots, and aims to overcome the defects that a robot is usually low in independent flexibility, low in integral adaptability, low in motion control response speed, strong in dependence on the work environment and the like, and to solve the problem that complexity of the control system is increased because of various degrees of freedom. The control system comprises a foot-type module and a wheel-type module, and the control system is carried out according to the following steps particularly: 1, building a hexapod robot modeling module; 2, building a coordinate system calculating module; 3, controlling a servo motor through a motion controller for accurate position movement, and determining variation of the mass center of a robot platform through a posture motion module by applying a robot coordinate transforming matrix; 4, realizing moving forwards, retreat, left turn, right turn and the like of a wheel-type system. The control system and the control method are applied to the field of motion control of the hexapod robot.

The invention discloses a key target identification method for an automobile cruising system. Based on the fuzzy control theory, a multi-target automobile lane changing fuzzy logic controller is designed, a dangerous lane changing automobile is prejudged, and effective identification of a straight lane key target is determined. The tilting motion influence of automobile bend running is considered, an extension Kalman filtering on-line real-time estimation of an automobile mass center side slip angle and a road curvature is achieved, the bend key target identification method is provided, a key target judgment basis is given, and effective identification of the bend key target is achieved.

The invention provides a real-time three-dimensional double-hand gesture recognition method and system based on binocular vision. The real-time three-dimensional double-hand gesture recognition method based on binocular vision comprises the steps that initial calibration and correction are conducted on an image firstly, the outline of a gesture is extracted, two-dimension gesture recognition is conducted on the extracted gesture outline, the mass center of the gesture outline is calculated, stereo matching is conducted on the mass center obtained through calculation, three-dimensional hand gesture recognition is achieved, and corresponding gestures are displayed in a human-computer interaction module based on the three-dimensional hand gesture recognition. According to the real-time three-dimensional double-hand gesture recognition method and system based on binocular vision, binocular vision information can be utilized, and human-computer interaction, based on the three-dimensional space, of double-hand gesture change of a computer is achieved; meanwhile, extremely high real-time performance and extremely high effectiveness can be achieved, and requirements for hardware are lowered; in addition, the man-machine interaction effect is achieved, and the requirements for real-time performance and effectiveness are well met.

The invention relates to a wavefront measuring method based on a Hartmann wavefront sensor. According to the method, light spot array images detected by an array type photoelectric detector in the Hartmann wavefront sensor are used for obtaining the intensity distribution information of each light spot and the mass center position offset relative to the calibration time, the inclination aberration information of a sub wavefront in the corresponding sub aperture can be obtained according to the mass center offset, the high order aberration information of defocusing, astigmatism and the like ofthe sub wavefront in the corresponding sub aperture can be obtained by a phase inversion algorithm according to the intensity distribution information of the light spot, the inclination aberration information and the high order aberration information are combined to form sub wavefronts, and finally, all sub wavefronts are reconstructed by a wavefront reconstruction method or a wave surface split joint method for forming the whole aperture wavefront information. The method has the advantages that the light spot dispersion distribution information which originally puzzles the light spot mass center calculation is utilized, more information quantity of the sub wavefronts in the sub aperture is obtained, the wavefront detection precision of the Hartmann wavefront sensor is favorably improved,or the requirement on the aperture number is favorably reduced.

The invention relates to an empty bottle wall defect detection method, which comprises the following steps: shooting two images by using a camera before and after the same empty bottle is rotated for 90 degrees during advancing, then transmitting the images to a CPU of an industrial personal computer to perform analysis on the images, and judging whether the bottle wall has defect. Image processing comprises the following steps: A, scanning edge point pairs on a bottle neck, positioning the bottle wall, and dividing a detection area of the bottle wall to perform subarea processing; B, pre-processing image data in the positioned area by adopting a grey stretching method; C, partitioning the images by adopting a maximum between-cluster variance method to acquire target information; and D, performing connectivity analysis on the partitioned bottle wall images, extracting characteristic data of each defect, and judging whether each detected connected domain has real defect according to the mass center position, posture ratio and area characteristic of the connected domain. The invention discloses a detection device used for the detection method at the same time. The detection method and the detection device are easily applied in detection equipment of an industrial flow line so as to realize automatic high-speed accurate detection on the empty bottle wall defect.

The invention discloses a method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis which belongs to the field of industrial heating furnace flame video monitoring. The method comprises following steps: 1) setting a flame region of interest(ROI) through a human-computer interaction method; 2) extracting a ROI image from a flame monitoring video flow and calculating an average image; 3) pre-treating the ROI average image, including noise smoothing, threshold segmenting, morphological processing, to determine the most probable flame pixel region; 4) extracting flame features from the pre-treated image, comprising flame region area, average brightness, mass center and flame color principal components; 5) synthetically analyzing flame feature, establishing judgment rules, automatically identifying flame burning status and outputting; 6) establishing off-line self-study model by use of historical data, optimizing system parameters, increasing method robustness. The method can be applied for real-time monitoring combustion conditions of gas heating furnace with single-burner or multi-burner and guarantees safety of industrial production.

The invention provides a system for detecting mass, mass center and mass offcenter of a cylinder, and belongs to the measurement technical field. The system for detecting the mass, the mass center and the mass offcenter of the cylinder comprises a main controller, a data acquisition module, a control interface module, a signal conditioning circuit, a motor driving circuit, a distance measuring device, a power module, a lifting motor, four weighting sensors and a lifting platform. The cylinder to be measured is clamped on a tray at one time, the lifting motor is started, the tray is landed on the weighting sensors, the distance measuring device is moved to measure a reference distance of the cylinder, and then data of the sensors are acquired twice in a front and back mode when the cylinder rotates by 90 degrees, and a detecting result of the mass, the mass center and the mass eccentricity of the cylinder can be acquired according to a four-point method. The system for detecting the mass, the mass center and the mass offcenter of the cylinder has the advantages of being compact in structure, large in measuring diameter range, high in measuring accuracy and automation degree, and capable of being used in delivery detection, factory acceptance inspection and quality characteristic detection of cylinder parts or products.

The invention discloses a posture identification method based on near-infrared TOF camera depth information. The posture identification method includes the steps that a depth image is obtained through an SR4000, earlier-stage operation processing is carried out on the depth image, a human body object is obtained and skeletonized, then coordinates of end points of the head, the hands, the feet and the mass center of the human body target are obtained, the heights between the end points and the ground and the skeleton line distances between the end points and the mass center are calculated, the attributes of the end points are identified according to the skeleton line distances and the ground heights, and then posture identification is achieved in cooperation with motion characteristics and the depth information. In this way, the target tracking difficulty and the algorithm complexity are lowered, the identification effective rate and the target division accuracy are improved, and convenience is brought to real-time embedded transplanting. The invention further discloses a device used for implementing the posture identification method.

The invention discloses an integrated control method for distributed control of an electric automobile. The integrated control method comprises the following steps of according to automobile speed, a steering wheel rotating angle and a steering wheel rotating angular speed, obtaining an expected yaw angular speed and an expected mass center sideslip angle by a signal processing layer by referring to a module; in an integrated control layer, according to the actual value of the yaw angular speed and the expected yaw angular speed, deciding a rear wheel additional yaw torque required for realizing control of the stability of the automobile; according to the actual valve of the mass center sideslip angle and the expected mass center sideslip angle, deciding the front wheel additional rotating angle required for realizing control of the stability of the automobile; in a control distribution layer, according to a target driving torque of a driver and the rear wheel additional yaw torque, reasonably distributing four-wheel driving force, and according to a target front wheel rotating angle of the driver and the front wheel additional rotating angle, correcting the front wheel rotating angle; and controlling the yaw stability by an executing layer through a hub motor. The integrated control method disclosed by the invention has the characteristics that the handling safety stability of the automobile is high, and the steering comfortability of the driver is improved.

The invention provides a method for detecting vision localization of a QFP element and relates to the field of vision localization and detection of the QFP element. The method aims at solving the problems that a traditional method for detecting the QFP element is high in requirement for accuracy of a suction nozzle suction element, image gradation values are not even, pins are broken in an image, and the overall morphology algorithm adopted to pin classification and repair is long in consumed time and poor in real-time performance. The technology mainly adopted by the method is that an image of the element to be detected is obtained, the binary image is scanned, connected regions are marked, the marked connected regions are divided and clustered, a mass center fitting boundary of each connected region is obtained, and then the rectangularity and the rotation angle of each connected region are calculated. The method for detecting vision localization of the QFP element is mainly used for pin detection and rotation angle detection of the QFP element.

The invention belongs to the technical field of vehicle active safety, and particularly provides a rollover warning method and a rollover warning device for a heavy vehicle. The rollover warning method and the rollover warning device are low in cost, are free of influence on heavy vehicle load and mass center height, and can warn impending rollover accidents of the heavy vehicle in the next period of time in advance. The method solves the problem that an existing heavy vehicle rollover warning method can warn a vehicle rollover risk in a static threshold value mode but cannot warn an impending rollover accident to a driver in advance. The rollover warning method adopts a classical Kalman filtering technology to simplify a rollover warning model in a combination mode, the motion state of the heavy vehicle is accurately estimated, and then a TTR algorithm is utilized for predicting the rollover risks in the next period of time. The warning algorithm has better universality, and meanwhile prevents inaccurate or invalid warning caused by the changes such as the load, center-of-gravity position and rotary inertia of the heavy vehicle.

The invention discloses a method for detecting an unstructured road boundary on which an intelligent vehicle runs. The method comprises the following steps of: analyzing and processing frame data of a vehicle-mounted 64 line laser radar to obtain frame two-value raster data, expanding and corroding the frame two-value raster data to fill small space between data of barriers on the same side of a road and keeping the whole outline unchanged; solving the outline of each barrier target, storing in a chain code mode and solving the mass center of the outline; performing K means clustering on the barrier targets, wherein a sample is the solved mass center, the targets comprise barrier targets on the left side of the road and barrier targets on the right side of the road; and training by using a support vector machine (SVM), wherein the sample is the outline points of the classified barrier targets, thus obtaining a classifier, and finally solving a straight line section which describes theroad boundary according to the classifier, the maximum interval conditions and the raster data. In the method, data involved in calculation is reduced as much as possible; and the method is high in real-time property, and the solved road boundary accuracy rate is high.

The object of the invention is to provide a safe and reproducible compressor impeller fastening for high speed turboengines, which, moreover, possesses more accurate concentricity. This is achieved, according to the invention, in that both the hub cone (9) and the shaft cone (11) each have a mean diameter (23, 24) and these mean diameters (23, 24) are arranged at an axial distance (25) from the mass center of gravity (14) of the compressor impeller (4), said distance corresponding at least to half the mean diameters (23, 24). On the shaft side of the hub cone (9), the through bore (8) of the hub (6) is designed at least partially as a cylindrical bore (16).

The invention discloses a quantum communication ATP (array transform processor) precise tracking system with an optical axis self-calibrating function and a calibrating method thereof, aiming at overcoming the problem that the center of the quantum light emitting optical axis and the visual field center of the precise tracking camera are inconsistent owning to emitting vibration, on-track weight loss, thermal gradient and the like. The precise tracking system consisting of a pyramidal prism, a quick directing mirror, a CMOS (complementary metal-oxide-semiconductor) camera, a quantum emitting module, a color-separating piece and the like is adopted, and a path of strong light of other wavelength is introduced in the quantum emitting module by an optical fiber combiner and is used as a self-calibrating light. Before the instrument works, the self-calibrating light is introduced in the camera to form images by a track selector; the position of the mass center of light spot is calculated and is used as the visual axis center during tracking external target. The established inter-satellite or satellite-ground optical link can lead the ATP system to capture and precisely track the target at the receiving end and to exactly send the quantum signal to the receiving end along the optical link simultaneously, thus ensuring to successfully realize the spatial scale quantum communication.

The invention belongs to the technical field of a wireless sensor network system, and discloses a wireless sensor network data transmission method based on a LEACH protocol. By setting an energy threshold Va, a data transmission process is divided into whole-network cluster head election and in-cluster cluster head election; when energy is smaller than the energy threshold Va in all cluster heads, a whole-network election method is adopted, so that each node in a region has the chance to become a cluster head; and when energy is greater than the energy threshold Va in all the cluster heads, in-cluster election is carried out, new in-cluster cluster heads are selected according to constraint conditions of residual energy, a node density and a distance to an in-cluster mass center, a structure of a cluster is unchanged, and a non-cluster-head node is elected in the cluster to be used as a new cluster head. According to the invention, by an optimal cluster head rate of a wireless sensor network, all subsequent simulation experiments can be carried out, and various practice scenes can be more accurately and reliably simulated.

The invention discloses a high-voltage power transmission line inspection robot mechanism, which comprises front paws, a front arm, a mass center adjustment structure, a rear arm and rear paws, wherein the front paws and the rear paws are respectively connected to the tail ends of the front arm and the rear arm and clamped with a power transmission line; the paws comprise gear pairs and worm wheel and worm combined structures; the structures of the two arms are the same, and each of the two arms comprises a horizontal rotation pair and three vertical rotation pairs; the mass center adjustment structure comprises a box body, rotary drum moving platforms and flexible ropes; two ends of the upper surface of the box body are respectively connected with the vertical rotation pairs at the front ends of the front arm and the rear arm; the two rotary drum moving platforms are symmetrically arranged on the box body; one end of each flexible rope is connected with the vertical rotation pair at the rear of each arm; and the other end of each flexible rope is wound on each rotary drum of the mass center adjustment structure. The mechanism is compact in structure; due to a pressing wheel structure, the mechanism can automatically adapt to an angle of the line; when the line is suspended on one arm, the flexible ropes are used for bearing the weight of a robot, so that the requirement on the rigidity of the arms is reduced, and the mass of the arm part of the robot can be effectively reduced; and the mass center is easy to adjust.

The invention discloses a measuring device and method for the vibration of a flexible cantilever on the basis of machine vision. The measuring device comprises a fixed bracket, the flexible cantilever, a camera bracket, a CCD (Charge Coupled Device) camera, a lens, a plurality of LED (Light-Emitting Diode) light-emitting tubes and a PC (Personal Computer), wherein one end of the flexible cantilever is fixed on the fixed bracket; all the LED light-emitting tubes are arranged on the upper surface of the flexible cantilever in sequence; the top of the fixed bracket is provided with the camera bracket; the CCD camera is fixed on the camera bracket and is provided with the lens; and an output port of the CCD camera is connected with the PC. The CCD camera measures each frame image of the vibration of the LED light-emitting tubes, and conveys the images to the PC; and the PC processes a detected image sequence, extracts the position of the mass center of the light spots of the LED light-emitting tubes and acquires the vibration displacement of all the LED light-emitting tubes and parameters for reflecting the low-frequency vibration of the flexible cantilever structure. The measuring device and method disclosed by the invention has the advantages that the non-contact effect is achieved, the measuring range is wide and the vibration characteristic of a measured object is not changed and the like, and can be widely applied.

The invention discloses a CNN and selective attention mechanism based SAR image target detection method. An SAR image is obtained; a training data set is expanded; a classification model composed of the CNN is constructed; the expanded training data set is used to train the classification model; significance test is carried out on a test image via a simple attention model (a spectral residual error method) of image visual significance to obtain a significant characteristic image; and morphological processing is carried out on the significant characteristic image, the processed characteristic image is marked with connected domains, target candidate areas corresponding to different mass centers are extracted by taking the mass centers of the connected domains as the centers, and the target candidate areas are translated within pixels in the surrounding to generate an target detection result. According to the invention, the CNN and the selective attention mechanism are applied to SAR image target detection in a combined way, the efficiency and accuracy of SAR image target detection are improved, the method can be applied to target classification and identification, and the problem that detection in the prior art is low in detection efficiency and accuracy is solved mainly.