14 results about "Biological motion" patented technology

The invention discloses an intelligent door lock real-time visual analysis method and system based on edge calculation, and relates to the technical field of door locks, and the method comprises the steps: collecting a user face image in real time through a multi-mode sensor integrated with an intelligent door lock, and synchronously obtaining a distance value and dynamic motion information between a face and a camera; judging whether a living body detection and recognition process is triggered or not; when a living body detection and recognition process is triggered, extracting image features, depth information and Doppler frequency shift dynamic parameters of a face region; generating a composite living body feature vector containing a three-dimensional structure, texture details and motion characteristics; and performing dual verification on the generated composite living body feature vector. The method has the advantages that by introducing the Doppler frequency shift detection technology of the millimeter wave radar, the specific dynamic micro-motion characteristics of the living body are creatively fused into the living body authentication system, the defect that traditional living body detection excessively depends on static textures is effectively overcome, and the biological motion fingerprint authentication capacity of the intelligent door lock is improved.

System and method for guiding a user in activating biological motor units (MUs) are disclosed. A method includes presenting instructions for performing a movement associated with activation of MUs, and graphical elements associated with the activation of the MUs. The method includes, in response to detecting an activation of the MUs, determining, based on biopotential sensor data captured during performance of the movement an additional movement to be performed by the user and a change to the graphical elements. The method includes presenting additional instructions for performing the additional movement, and the change to the graphical elements. The method includes, in response to detecting an additional activation of the MUs, in accordance with a determination that additional biopotential sensor data captured during performance of the additional movement satisfies a threshold, associating the additional biopotential sensor data with biopotential-based gestures, and presenting an additional change to the graphical elements.

The present application relates to the technical field of nerve monitoring, in particular to an intraoperative real-time feedback system and method for sacral nerve stimulation, the system comprising: a biological motion sensing unit for real-time monitoring of the body surface contraction movement of the perineum and perianal area and foot movement through a sensor and generating corresponding multi-modal sensing signals; a processing unit for receiving the multi-modal sensing signals and performing synchronization and feature extraction, inputting the extracted features into a pre-trained machine learning model to obtain a judgment result representing the effect of sacral nerve electrode implantation target point and the accuracy of the target point position; a feedback unit for receiving the judgment result and converting it into feedback information for unified display. The present application realizes objective quantitative evaluation through multi-modal signal synchronous perception and fusion, as well as integrated machine learning model, provides intelligent and predictive feedback beyond simple threshold judgment, and realizes precise guidance of electrode implantation.

The present application relates to a kind of multi-target tracking method based on aerial biological motion situation feature auxiliary, belong to radar tracking technical field, this method is constructed by biological three-dimensional space distribution situation matrix according to the three-dimensional space distribution of biological in radar scanning period;Then the shift of the inner product maximum of cyclic convolution calculation matrix is calculated using the three-dimensional situation matrix of two successive scanning periods of radar, biological motion velocity estimation is obtained according to the shift;Finally, the estimated motion situation information and track head position information are combined to predict target state, and the correlation gate is established to assist the correlation tracking of biological target using the predicted position information.In the embodiment, compared with traditional tracking algorithm using simulation experimental data, the effectiveness of the proposed method is verified.

The invention discloses a sea-turtle-imitating amphibious robot path tracking method based on model predictive control, which comprises the following steps of: firstly, establishing a sea-turtle-imitating amphibious robot multi-rigid-body dynamic simplified model containing a water flow dynamic coefficient, and simplifying a control dimension in combination with biological motion characteristics; analyzing and quantifying water flow dynamic parameters through computational fluid mechanics simulation in combination with a steady-state dragging test, a rotating arm test and an unsteady planar motion mechanism; constructing a robot model and an underwater environment in a dynamic simulator; a model predictive control-fuzzy logic cascade controller is designed, an upper layer generates reference force and torque through rolling horizon optimization, and a lower layer maps the reference force and torque into an actuator instruction based on a fuzzy rule; and finally, verifying and evaluating the robustness and tracking precision of the controller in a simulation environment. The method effectively deals with nonlinear water flow dynamic effect, parameter uncertainty and unmodeled environment interference, and has high control precision and strong robustness through U-shaped and 8-shaped path verification.

The invention discloses a method for measuring the motion direction of flagellates under a flowing condition. The method comprises the following steps: step 1, acquiring and processing an image sequence; 2, cutting and aligning the cell image; step 3, preprocessing the cell image; step 4, creating a sector ring detection area; step 5, constructing a time sequence frame; step 6, calculating time sequence difference characteristics; and 7, calculating confidence and determining a motion direction. According to the method for measuring the motion direction of the flagellum under the flowing condition, the technical problem that the flagellum cannot be identified due to poor flagellum imaging quality and instantaneous information loss in a flowing water environment is solved, and high-precision, automatic and continuous measurement of the motion direction of the flagellum is realized through time sequence dynamic characteristic analysis and biological motion characteristic judgment.

This invention provides a method for generating bird-repelling images using dynamic LED simulation of biological movement, relating to the field of airport bird control technology. The method includes: acquiring bird images; determining the escape type based on bird distribution and movement trends in the images; clustering the birds to obtain tracking targets; obtaining the predicted trajectory of the tracking targets based on unscented Kalman filtering; acquiring the reaction parameters of the tracking targets; inputting the reaction parameters into a preset action generation model to obtain a simulated action sequence; obtaining simulated flight speed and action parameters based on the simulated action sequence; calculating the predicted distance between the LED screen and the tracking targets based on the predicted trajectory of the tracking targets; obtaining size adjustment parameters based on the simulated flight speed and predicted distance; and generating bird-repelling images. This method achieves realistic simulation of the natural behavior of birds of prey, with a high degree of intelligence, requiring no manual monitoring. Compared to existing bird-repelling equipment, it has lower operating costs and effectively solves the problems of bird adaptability, high cost, and low efficiency in traditional bird-repelling methods.

The invention discloses a multi-mode biological movement emotion feedback training system for autism spectrum disorder, which comprises a control device, and an interaction device, a display device and an eye movement device which are connected with the control device, a visual training task database is arranged in the control device, and biological movement walking stimulation is arranged in the visual training task database. The interaction device provides feedback for the key response of the testee, and records the training performance of the testee on the biological movement walking stimulation through the control device; the eye movement device monitors and records the autonomous adjustment pupil size executed by the subject following instruction in real time, and synchronously presents the mood degree of biological movement walking stimulation. According to the system, through a multi-mode feedback training mode of integrating extrinsic behaviors and implicit physiological regulation, comprehensive improvement of the emotion recognition ability of autism spectrum disorder patients and high-autism characteristic groups is achieved, and the system has the advantages of being easy and convenient to operate, visual in feedback, quantifiable in effect and the like and is suitable for clinical rehabilitation and scientific research application scenes.

The application discloses a quadruped biological animation generation method and system. The quadruped biological skeleton is divided into virtual pelvic bone nodes, foot end-leg nodes and virtual pelvic bone-spine nodes according to motion levels through an input module, a motion state management module and an animation generation module, whole body kinematics simulation of the quadruped is split into multiple subparts for approximate solution, animation postures of each part of the quadruped are obtained, motion parameters on key bones of different parts are calculated, and the whole body posture matching the current motion state is generated by comprehensively integrating each part. The application helps rapid development of quadruped biological animation production in games by establishing a quadruped biological motion generation model. For quadrupeds with different bone structures, animation effects can be applied and previewed in a short time. Meanwhile, for animators, by adjusting relevant motion parameters, the change effect of gait and motion style can be directly observed in real time, which helps animation designers to control the animation style.

This invention discloses a path tracking method for a turtle-inspired amphibious robot based on model predictive control, comprising the following steps: First, a simplified multi-rigid-body dynamics model of the turtle-inspired amphibious robot with hydrodynamic coefficients is established, and the control dimension is simplified by combining biological motion characteristics; hydrodynamic parameters are quantified through computational fluid dynamics simulation, combined with steady-state towing tests, rotating arm tests, and analysis of unsteady planar motion mechanisms; a robot model and underwater environment are constructed in a dynamics simulator; a model predictive control-fuzzy logic cascaded controller is designed, where the upper layer generates reference forces and torques through rolling time-domain optimization, and the lower layer maps them to actuator commands based on fuzzy rules; finally, the method is verified in a simulation environment to evaluate the robustness and tracking accuracy of the controller. This method effectively copes with nonlinear hydrodynamic effects, parameter uncertainties, and interference from unmodeled environments. Validated through U-shaped and figure-eight path tests, it demonstrates high control accuracy and strong robustness.

The invention discloses a human body detection method, device and equipment based on a dual-technology sensor, and a medium, and the method comprises the steps: carrying out the synchronous collection, feature decoupling extraction and feature fusion of a millimeter wave radar and a pyroelectric infrared signal, and carrying out the real-time classification of an end side through a decision tree model; the system can intelligently judge whether a human body exists or not according to inherent micro-motion-thermal radiation coupling fingerprints of a target instead of an isolated single-mode threshold value, fusion features contain the double physical essence of whether the target has biological motion and a heat source or not, and the fusion features are more accurate. Therefore, only one interference source (for example, the fan only has micro-motion and no heat source, and the heater only has heat source and no micro-motion) can be effectively eliminated, the false alarm rate caused by main environment interference sources such as green plant shaking, curtain swinging and fan rotation is reduced, and the detection accuracy is improved.

The present application relates to a kind of biological source-seeking robot, belong to biological bionic robot technical field, comprising: biological bearing unit, for accommodating biological and transmitting its movement information;Perception and support unit, set in biological bearing unit below, for collecting movement data and providing support;Mobile execution unit, supported in perception and support unit below, for realizing omnidirectional movement;Control system, perception and support unit receive the movement data of perception and support unit and solve, conversion and generation mobile execution unit's drive instruction.It also includes environmental perception auxiliary unit, installed in support frame, for collecting environmental data and with the data fusion of movement solving module, correct drive instruction.The present application utilizes the rotation of spherical cabin body driven by the movement of ball-in-biological, through the attitude data of perception and support unit solving, drive omnidirectional wheel chassis to carry out autonomous source-seeking detection, and it is suitable for the target source-seeking and detection scene of complex terrain and other dangerous or unknown environment.

The invention provides an intelligent detection method for feeding behaviors of penaeus vannamei in a recirculating aquaculture system and a model building method, and belongs to the technical field of aquaculture monitoring. Comprising the following steps: acquiring an image data set of ingestion of penaeus vannamei in different appetite states shot in a field environment, and dividing the image data set into a training set and a test set; performing frame extraction on the video data in batches, and extracting an optical flow graph after preprocessing; the method comprises the following steps of: constructing a double-flow neural network OptiPulse-ShrimpNet capable of capturing the feeding behavior of the prawns; and training and testing the model. The model established by the invention can automatically adjust the space-time perception field according to the dynamic characteristics of the prawn ingestion movement, accurately capture weak biological movement signals in the overwater high-angle shooting view angle, automatically track the long-time behavior track of more than 30 minutes, and solve the behavior intensity characteristic parameters of the ingestion key stage.

This invention belongs to the interdisciplinary field of artificial intelligence methods and biomimetic technology, and relates to an AI-based method for acquiring the control logic of biomimetic robots. From the perspective of biomimetic robot control logic, its advantage lies in the fact that existing biomimetic robots merely mimic biological movement postures, making it difficult to achieve the energy-efficient, high-efficiency, and low-noise movements of living organisms, thus failing to meet current task requirements. Therefore, an AI-based method for acquiring the control logic of biomimetic robots is designed. This method uses artificial intelligence to obtain the control logic of biomimetic robots from real biological movement processes, aiming to improve the overall performance of biomimetic robots. Biomimetic robots that acquire control logic using this method can move more energy-efficiently and with lower noise, better meeting the needs of various current tasks and enhancing their practical value.