295 results about "Movement detection" patented technology

The invention provides an image processing method and device and electronic equipment, and the method comprises the steps: obtaining a continuous frame image, carrying out the motion detection of the continuous frame image, obtaining each motion region in the continuous frame image and the speed of each motion region, determining the target type of each motion region through semantic recognition, determining a priority corresponding to each motion area according to the speed and the target type of each motion area, and performing perception recognition on the motion areas with different priorities by adopting corresponding perception strategies to obtain a perception result; according to the method, perception identification is focused on a dynamic area and differentiated processing is carried out, a large amount of redundant calculation in a static or non-key area is effectively avoided, system calculation resources are saved, hardware loads are reduced, key targets can be ensured to be preferential, the real-time performance and response speed of the system are improved, and vehicle driving safety is ensured.

The invention discloses a wearable knee joint self-powered sensing system and a use method, relates to the technical field of motion monitoring, and solves the technical problem that a motion detection sensor integrating light weight and a self-powered mode is lacked in the prior art. The motor comprises a stator part and a rotor part which are rotationally arranged, a center shaft penetrating through the stator part is arranged on the rotor part, and the stator part and the rotor part are rotationally connected through the center shaft; and a motion state monitoring module and a self-powered module are sequentially and coaxially arranged at the connecting part of the stator part and the rotor part, so that the rotation angle and direction of the knee joint are accurately detected, and key data support is provided for subsequent motion analysis and health monitoring.

The invention comprises a method for controlling a mobile service robot for monitoring the movements of a person, comprising identifying the person, associating the identified person with a stored monitoring profile, capturing the person's movements by means of a motion detection sensor, generating observation points for the captured person, evaluating the captured movements of the person, retrieving position data as coordinates of a map, and automatically outputting information to the captured and identified person via an output unit of the mobile service robot.

The utility model discloses a pallet flattening detection structure, which comprises a base, the top of the base is fixedly connected with a detection frame, the base is provided with a rotating mechanism, the top of the detection frame is provided with a first mounting hole, the top of the detection frame is provided with a detection mechanism, the side wall of the detection frame is fixedly connected with a connecting block, and the connecting block is provided with a second mounting hole. A guide cylinder is fixedly connected to the tail end of the connecting block, a guide block is inserted into the guide cylinder, a protruding block and a wheel frame are fixedly connected to the top end and the bottom end of the guide block correspondingly, a flattening wheel is installed in the wheel frame, threaded pipes are fixedly connected to the four corners of the top of the base correspondingly, and leveling assemblies are installed in the threaded pipes. According to the utility model, the flatness of each position on the surface of the tray can be detected, the position of the detection mechanism or the tray does not need to be manually moved, the detection structure can be leveled to ensure that the detection structure is horizontally placed, and related detection parts are detachable, so that regular maintenance and replacement are facilitated.

The invention discloses a table tennis motion detection system based on pure visual perception. The table tennis motion detection system comprises a table tennis detection and event monitoring module, a human body-racket posture estimation module and a time sequence action recognition and quality evaluation module. The table tennis ball detection and event monitoring module is based on an improved DTTNet model and realizes table tennis ball track detection and event identification such as table touching, net touching and net passing through through multi-frame video stack and deformable convolution; the human body-racket posture estimation module adopts a lightweight detection network and high-resolution posture estimation network combined reasoning structure, outputs human body key point and racket three key point coordinates, and constructs a human body-racket combined kinematics model; the time sequence action recognition and quality evaluation module fuses multi-view video and posture features, classification and quality evaluation of table tennis technical actions are achieved through time sequence boundary matching and multi-scale feature analysis, the table tennis technical action recognition and quality evaluation system has the advantages of being high in detection precision and high in real-time performance, and automatic recognition and quantitative evaluation of table tennis movement can be achieved.

Technical solutions for diagnosing a sensor fault in an actuator incorporating a permanent magnet direct current (PMDC) motor are described, including: measuring, by means of a position sensor, the position of the PMDC motor; determining, based on the measured position, an estimated motor speed; measuring, by means of a current sensor, the current in the PMDC motor; determining, based on the measured current in the PMDC motor, a voltage command for the PMDC motor; determining, based on the measured current and the voltage command and using a motor speed observer, an observed speed of the PMDC motor; determining a differential speed as the difference between the estimated motor speed and the observed speed; determining, based on the differential speed, the sensor fault; and performing an action in response to the determination of the sensor fault.

The invention discloses a multi-target tracking method and related equipment, and the method comprises the steps: carrying out the target detection of a current frame, outputting a corresponding target detection frame result, carrying out the state transition operation through a target motion dynamics model, and generating a motion prediction frame corresponding to each potential target object in the current frame; based on the confidence of a target detection frame contained in the detection frame information, according to the target detection frame and the motion detection frame, generating a corresponding cost matrix, the cost matrix being a generalized symmetric intersection-to-union ratio or a symmetric overlapping score; and inputting the cost matrix into a Hungary matching system, generating an identity label corresponding to the target detection frame, and carrying out association matching on the identity label and the current activation track. According to the embodiment of the invention, the multi-target tracking processing efficiency can be improved, and the robustness, precision and application value of a multi-target tracking system in a complex dynamic environment can be remarkably improved. The method can be widely applied to the technical field of computer vision tracking.

The application relates to the field of old-age care equipment, and discloses a state recognition navigation recommendation method based on artificial intelligence and an old-age terminal device. The method comprises the following steps: acquiring terrain features, speed features, gait features and physiological features of a user in multiple walking trips when the user uses an intelligent walking stick, and acquiring map information and a walking destination of the user; wherein the terrain features, the speed features and the gait features are detected by a motion detection component of the intelligent walking stick; through a state recognition-navigation recommendation model, a navigation route and a walking guidance suggestion of the user in the next walking trip are determined according to the terrain features, the speed features, the gait features, the physiological features, the map information and the walking destination in the multiple walking trips; and the walking guidance suggestion comprises matters needing attention information when the user walks. The application can identify and detect the physical state of the old people and improve the nursing effect on the old people.

The invention relates to the technical field of straightening equipment, and discloses an automatic matching straightening machine for shaft workpieces, which comprises a machine body, a plurality of linear sliding rails for a plurality of mechanisms to linearly move are arranged on the machine body, and strip-shaped tooth grooves matched with moving gears are formed in the two sides of the interior of the machine body; one side of the machine body is provided with a PLC (Programmable Logic Controller) control cabinet for calculating input shaft workpiece data information and generating a control signal, and the PLC control cabinet is used for controlling each mechanism on the machine body in an operation process. By adding and arranging the movable detection mechanism, when the shaft workpiece is straightened, the movable detection mechanism adopts a lever type detection structure, can be tightly attached to the surface of the shaft workpiece, sensitively captures bending deformation information of the workpiece, realizes accurate acquisition of deformation, avoids subjectivity and errors of manual detection, and improves the straightening accuracy of the shaft workpiece. And full-length movement detection can be realized along a linear sliding rail, all parts of the shaft workpiece are covered, and the condition of missing detection of a deformation position is avoided.

Devices and associated methods refer to jam detection when the intensity of a reflected signal exceeds a predetermined intensity threshold and an intensity window metric based on historical intensity value(s) has not exceeded an intensity window threshold for longer than a predetermined time threshold. In an illustrative example, a jam detection unit (JDU) might emit a signal and detect a reflection of that signal. The JDU might, for example, compare the intensity of the reflected signal to the intensity threshold. The JDU might, for example, compare the intensity threshold to at least one historical intensity value to determine the intensity window metric. If the intensity value exceeds the intensity threshold and the intensity window metric has not exceeded the intensity window threshold for longer than the time threshold, then the JDU might, for example, generate a jam signal.Several methods can usefully detect jams based on the intensity of a reflected signal.

We provide an anomaly detection system capable of detecting abnormalities in humans. [Solution] An anomaly detection system comprising: a first motion detection unit 301 that detects movements of a person 20 that are greater than a motion threshold using a non-contact sensor 10; a presence location determination unit 302 that, if it has detected movements greater than the motion threshold, determines whether a person is present in a location 30 where the non-contact sensor 10 can detect movements of a person 20 that are less than the motion threshold; a second motion detection unit 303 that detects movements of a person 20 that are less than the motion threshold if it has determined that a person is present in a location 30 where it can detect movements of a person 20 that are less than the motion threshold; and an anomaly determination unit 304 that, if it has not detected movements less than the motion threshold, determines that something is wrong with the person 20.

Method for controlling an electronic device with a remote control (1), wherein the method comprises the following steps: - Detection (22) by the remote control (1) of a movement of the remote control (1); - Determine (23, 24) by remote control (1) a command associated with the detected motion; and - Sending (25) the specified command from the remote control (1) to the electronic device, the method further comprising: - Putting (20) the remote control (1) into a motion detection state, wherein putting (20) the remote control (1) into a motion detection state includes: - Pressing a button (2) on the remote control (1), whereby the remote control (1) remains in the motion detection state as long as the button (2) is pressed.

Vehicle device for digital validation of a resident parking permit, characterized in that it includes a GPS module for position determination, a radius logic for calculating the distance to the registered residential address, a communication interface for data transmission via mobile network, an optical status indicator for displaying the parking status, and a motion detection unit for determining the parking condition.

The invention comprises a device and a method for detecting and evaluating the movements of a person, comprising detecting a person by means of a motion detection sensor, generating an observation point model of observation points for the detected person, determining poses, evaluating the observation points by means of an observation point evaluation module, wherein the motion detection sensor provides data to at least one other process node via at least one data channel and / or receives data from at least one other process node.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for motion detection using a communication channel carrier signal. In one aspect, a method includes, for each of one or more motion detection processors, performing operations comprising: for each of one or more communication channels, wherein each communication channel has a center frequency that is different from the center frequency of each other communication channel: determining mean power levels from two or more power samples at the center frequency, determining a difference between the mean power levels of the two or more power samples at the center frequency, and determining whether physical motion is occurring in a monitored area based on the difference between the mean power levels.

Methods and systems for improved impact detection in a device, such as a head-wearable device, are disclosed. The methods and systems relate to accurately detecting impact events such as falls or vehicular crashes to reduce false positives and enable a swift, appropriate emergency response. A method includes detecting use of the device by a user, for instance, confirming that a head-wearable device is being worn. The method further includes detecting a change in at least one of an orientation or a movement of the device within a threshold time period. An impact is then determined based on the confirmed use of the device and the detected change in its orientation or movement. This approach distinguishes genuine emergencies from non-critical events like dropping the device, thereby improving accuracy and conserving power by intelligently activating additional sensors only when a potential impact is detected.

The application relates to the technical field of new energy charging, in particular to a charging alignment device which comprises a charging plug, a moving module, an alignment module, a mounting seat, a guide cone, a guide cone fixing plate, a guide cylinder and a horizontal movement detection switch, the guide cone fixing plate is connected with the mounting seat, the charging plug is mounted on the guide cone fixing plate, the guide cone is arranged on the guide cone fixing plate and is distributed on the two sides of the charging plug, the end of the guide cone exceeds the end surface of the charging plug by a certain distance, the side of the guide cylinder facing the guide cone exceeds the end surface of the charging female seat by a certain distance, the guide cone is matched with the guide cylinder, the horizontal movement detection switch is arranged on one side of the mounting seat, the horizontal movement detection switch is connected with the moving module, and the high-precision automatic alignment of the charging plug and the charging female seat is realized through the mechanical guidance of the guide cone and the guide cylinder and the combination of the horizontal movement detection switch.

The embodiment of the invention provides a cooling bed movable rack automatic centering system and method.The system comprises a plurality of rack adjusting units, a movable detection device and a central controller, the central controller is in communication connection with the rack adjusting units and the movable detection device, and the rack adjusting units are arranged on a cooling bed movable beam; the movement detection device is used for detecting information of a movable rack on the rack adjusting unit, and the central controller is used for receiving the information of the movable rack, analyzing the dislocation state of the movable rack and controlling the rack adjusting unit to adjust the movable rack when the movable rack is dislocated. The rack dislocation can be automatically identified and accurate centering can be completed under the condition of non-stop or transient stop, so that production accidents caused by rack dislocation are fundamentally eliminated.

The application discloses a kind of composite vision, hearing multimodal lip detection method and device and equipment.The method comprises: synchronously collecting voice data and face data;Multi-modal neural network model based on the voice data and face data is constructed;The multi-modal neural network model is trained using the way of double decoder joint optimization;According to the trained multi-modal neural network model, the speech of human body and face key point are predicted according to the face lip corresponding to the speech.This application uses key point detection algorithm to extract the face key point of face image and aggregate face features.On the other hand, considering the change of facial features and voice features, the change of mouth shape is represented by extracting more rich features by fusing the two, so that the vivid image is more lively.

Disclosed is a video recording device including a camera module configured to acquire a video of the surroundings of a vehicle, a motion detection sensor configured to detect a motion of a nearby object, a first memory configured to store the video, and a controller configured to control the storing of the video and including a second memory configured to store a computer program for storing the video and a processor configured to execute the computer program, wherein, when the computer program is executed by the processor, the controller is configured to determine whether to store the video based on mobile key detection and motion detection.

The invention discloses a power transmission line six-bundle conductor portable wiring device verification device and method, and the device consists of a simulation conductor supporting unit, a load applying unit, a motion detection unit, and a data processing unit. The tension environment of a real line is simulated through a tension adjusting mechanism composed of a stepping motor, a trapezoidal lead screw and a tension sensor; the load applying unit simulates the weight of an operator through a standard weight and a symmetric bearing frame, and cooperates with a pressure sensor and an attitude sensor to monitor the structural stability. The verification method covers rated load, overload and sliding smoothness tests; the running speed uniformity deviation is accurately calculated through a formula by collecting the running stroke, the rotating speed of the power wheel and the attitude angle. According to the invention, the working condition of the six-bundle conductor is verified, the bearing safety and the operation stability of the wiring device can be comprehensively evaluated, and reliable technical guarantee is provided for high-altitude comprehensive inspection operation.

The utility model relates to the technical field of on-line detection of quality of various steel wire ropes of offshore platforms, and provides an offshore platform steel wire rope movement detection device which comprises a video detection assembly and an electromagnetic detection assembly which are used for steel wire rope detection and further comprises a support assembly which comprises a bottom plate, a magnetic attraction part, supporting legs, a supporting plate, a pressing wheel and a wheel carrier. The magnetic attraction component is embedded in the bottom surface of the bottom plate, two supporting legs are arranged at the two ends of the top surface of the bottom plate in pairs, a supporting plate is arranged at the top ends of the supporting legs, and the video detection assembly and the electromagnetic detection assembly are arranged on the supporting plate; the wheel frame is arranged in the middle of the top face of the bottom plate. A pressing wheel is rotationally arranged at the top end of the wheel frame. Video detection and electromagnetic detection technologies are combined, so that the detection accuracy is up to 95% or above; steel wire rope detection work is carried out online in time, the damage discovery period is shortened, preventive maintenance is carried out, the service cycle is prolonged as much as possible on the premise of ensuring the safety of the steel wire rope, and the steel wire rope replacement cost caused by premature scrapping is reduced.

This invention discloses a snap-fit ​​assembly method and a snap-fit ​​itself. The snap-fit ​​includes an upper universal joint, a vertical connecting post, a lower mounting body, and left and right opposing rollers disposed on both sides of the lower mounting body. During assembly, the left and right opposing rollers and the vertical connecting post are first assembled onto the lower mounting body. Then, the upper universal joint is assembled onto the vertical connecting post and pre-tightened, allowing the lower mounting body to rotate circumferentially relative to the upper universal joint. Subsequently, the lower mounting body is driven to rotate one revolution around the vertical connecting post, and the rotation path is divided into multiple circumferential detection intervals. The rotational resistance value of each interval is obtained, and the presence of local jamming points is determined based on a preset upper resistance limit and the resistance difference between adjacent intervals. When local jamming points exist, the upper universal joint is adjusted until continuous rotation is achieved. Simultaneously, axial movement detection and roller idle rotation detection are combined to determine the assembly state, reducing problems such as local tightness, looseness, and inconsistent roller guidance during snap-fit ​​rotation.

The invention belongs to the technical field of pressure gauge quality detection, and particularly relates to a pressure gauge movement detection device which comprises a conveyor and a rack. A group of bearing assemblies are uniformly distributed on the surface of the conveying belt; an electric telescopic rod and a detection sleeve are arranged on the rack; the output end of the electric telescopic rod is connected with a mounting seat I and a mounting seat II; a servo motor and a control part are arranged on the mounting seat I; a visual sensor is arranged on the mounting seat II; one side of the detection sleeve is provided with an air connection port; and the air receiving port is communicated with an air supply pipe. Through cooperation of the conveyor, the servo tightening mechanism and the visual sensor, online automatic operation of the whole process of conveying, positioning, connecting, inflation and visual detection is achieved, and a traditional manual operation mode is effectively replaced. The visual sensor is used for capturing and analyzing pointer response in real time and automatically comparing the pointer response with a set air pressure value, the movement performance is rapidly judged, and subjective errors and efficiency bottlenecks of human eye observation are overcome.

The utility model relates to the technical field of packaging machinery, in particular to an automatic film sticking machine. A first guide rail is arranged at the upper part of the rack; the portal frame is provided with a film pasting machine head, the lower portion of the portal frame is provided with a first sliding block, the first sliding block is matched with the first guide rail, and the portal frame is driven by a front-back moving mechanism to move front and back; the front-back movement detection device is arranged on one side or two sides of the rack and is used for detecting whether the materials are in place or not; a left-right moving mechanism is further arranged between the portal frame and the film pasting machine head and used for left-right moving of the film pasting machine head. Left-right movement detection devices are arranged on the two sides of the film pasting machine head and used for detecting whether the film pasting machine head moves left and right in place or not. The portal frame can move back and forth on the rack and is matched with the detection device to achieve dynamic tracking film pasting. Through precise control of the chain transmission system and the first driving device, the portal frame can move front and back, parallel operation of material conveying and film pasting procedures is achieved, and the limitation that traditional equipment needs to be shut down for film pasting is broken through.

Disclosed in the present application are a drive device used for oral cleaning, a brush handle assembly, and an oral cleaner. The drive device at least comprises a drive body and a motion detection component. The drive body extending along a first axis comprises a stationary assembly and a rotating assembly, the rotating assembly being rotatably mounted on the stationary assembly, the stationary assembly at least partially surrounding the rotating assembly, and an accommodation chamber being formed in the stationary assembly. The motion detection component located in the accommodation chamber comprises a motion detection assembly and a motion feedback assembly, the motion feedback assembly being connected to the rotating assembly and rotating along with the rotating assembly, the motion detection assembly being directly connected to the stationary assembly, and the motion detection assembly determining a motion position of the rotating assembly by means of the motion feedback assembly. The present application can improve the control effect on oral cleaners, thereby improving the use experience of users.

A microwave motion detection system and lighting applications are disclosed. Time slicing and Pulse Width Modulation (PWM) techniques are used to improve efficiency in microwave motion detection sensors. Systems employing motion detection may control the detection of irrelevant motion with shielding and changing the power of the microwave motion detection sensor. Distance-based zones may be designated, and motion may be detected in particular zones. Different device operation may be performed based on motion detection in different zones. In lighting applications, varying device operation may include varying the direction, amount, or duration of light output. Device operation, when motion is detected, may also be based on the time of day, user preference, and power status parameters.

Disclosed herein is an information processing system including a position indicator, and an information processing device including a position detection sensor, in which the position indicator includes a first transmission circuit that transmits a signal to the position detection sensor, a motion sensor that outputs motion detection information, and a second transmission circuit that transmits the motion detection information to the information processing device. The information processing device includes a position detector that detects a position of the position indicator, a reception circuit that receives the motion detection information, and a processor that causes the information processing device to detect that the position indicator has moved, detect a motion pattern of the position indicator from the motion detection information received by the reception circuit, and perform the function.

Robot teaching device (1) for teaching a robot (30a, 30b) a series of tasks performed by an operator (20) on a task object (21a, 21b), the device (1) comprising: a motion detection unit (10) that detects motion data (100) indicating a position and attitude of the operator (20) or the task object (21a, 21b); a feature size detection unit (11) that detects feature size data (110, 110A) indicating a degree of influence of a movement of the operator (20) on the task object (21a, 21b); a priority period determination unit (12) that determines a period during which the operator (20) considers a movement essential for the series of tasks from periods during which the motion data (100) are detected as a priority period based on the feature size data (110, 110A). 110A) determined;and a training data generation unit (13) that generates training data (130) to be input into the robot (30a, 30b), wherein the training data (130) is generated on the basis of the motion data (100) such that a movement of the operator (20) in the priority period is reproduced, while a movement of the operator (20) in periods that differ from the priority period is not reproduced.

An example method is for use in connection with a media device and a motion-detecting device mounted to the media device, and includes: obtaining motion data associated with the motion-detecting device; providing the obtained motion data to a trained classifier, wherein the trained classifier is configured to use at least motion data as runtime input data to generate at least device type data as runtime output data; responsive to providing the obtained motion data to the trained classifier, receiving from the trained classifier corresponding device type data generated by the trained classifier; using at least the received device type data to identify a device type of the media device; using at least the identified device type of the media device as a basis to select a set of configuration parameters for the motion-detecting device; and causing the motion-detecting device to be configured according to the selected set of configuration parameters.