62 results about "Motion intensity" patented technology

The invention discloses a ViT model lightweight method for video action recognition, which comprises the following steps of: performing motion estimation in a data processing stage, calculating to obtain motion intensity and time redundancy scores of tokens, and performing window division on video frames according to the scores. Afterwards, a window-global token merging strategy is adopted to effectively merge redundant tokens, the first three layers of the model process local information through adaptive window merging, and from the fourth layer, the model repeatedly executes global merging according to the depth of the layers so as to realize gradually enhanced feature representation; therefore, the number of tokens is reduced, the complexity of the ViT model in space-time self-attention calculation is reduced, and the problem of high calculation resource consumption caused by space-time information redundancy of the current ViT model in a video task is solved. Calculation overhead and energy consumption can be remarkably reduced in tasks such as video action recognition, action detection and time sequence event understanding, and meanwhile the characterization capacity of a key dynamic area is kept.

This invention pertains to the field of mobile device authentication and discloses a dynamic context-aware continuous authentication method for mobile devices. It constructs a two-dimensional behavior quantizer based on motion intensity and interaction density to define the physical boundaries of pure motion, pure interaction, and hybrid scenarios in real time. A gating unit controlled by MI / ID signals is introduced to automatically generate masks in extreme scenarios such as pure motion or pure interaction to suppress ineffective attention calculations for missing modalities, enabling full feature interaction only in hybrid scenarios. A deterministic mapping rule from physical context state to network sparsity is established. Based on the real-time calculated MI / ID physical metrics, the system directly indexes the corresponding sparse sub-paths in the pre-trained multi-pruning rate network, achieving millisecond-level zero-overhead state switching while ensuring security.

The invention particularly relates to a self-adaptive closed-loop brain-computer interface neural feedback training system, and relates to the technical field of brain-computer interfaces and neural feedback. A multi-modal feature extraction module; a coefficient fusion module; and a feedback training module. In the invention, a high-precision crystal oscillator clock is adopted to realize time synchronization of electroencephalogram, eye movement and behavior signals, fusion distortion caused by signal dislocation is thoroughly eliminated, and the three types of signals respectively cover cognitive states, visual attention and motion characteristics to form complementary state evaluation dimensions; a refined quantization algorithm is designed for each mode, wherein instantaneous artifacts are eliminated through extreme value screening of the electroencephalogram coefficient, the pixel diameter is calibrated into the physical diameter through the eye movement coefficient so as to eliminate imaging interference, and the large-amplitude movement intensity and high-frequency posture micro change are considered in the behavior coefficient.

The application relates to the technical field of image recognition, in particular to a children autism spectrum disorder stereotyped behavior recognition system based on video images. The system screens target pixel points from pixel points; determines a motion intensity index according to a trajectory point sequence of the target pixel points; converts the trajectory point sequence of the target pixel points into a motion vector sequence; determines direction similarity according to direction similarity between vectors; clusters the vectors based on the direction similarity, and identifies a target cluster; determines a motion regularity index according to the number of vectors in the target cluster and the direction similarity; determines a saliency index in combination with the motion intensity index; clusters the target pixel points based on the saliency index, and sets a region of interest; determines an enhancement weight according to the density of the target pixel points in the region and the saliency index; and determines a total enhancement demand value in combination with the gray scale and gradient features of the pixel points in the region; and reversely maps the total enhancement demand value into a gamma correction parameter, so that the accuracy of recognition is improved.

The embodiment of the invention provides a video processing method and device, equipment and a medium. The method comprises the steps of determining a scene type corresponding to a to-be-processed video, and determining a target feature extraction strategy of the to-be-processed video based on the scene type; determining a motion feature corresponding to the to-be-processed video based on the target feature extraction strategy, and determining the motion intensity of the to-be-processed video based on the motion feature; determining a filtering parameter of the to-be-processed video based on the motion intensity, and filtering the to-be-processed video based on the filtering parameter to obtain filtered video data; and determining a spatial transformation parameter corresponding to the to-be-processed video based on the filtered video data, and performing inter-frame transformation on the to-be-processed video based on the spatial transformation parameter to obtain a stable video sequence. The method is used for achieving the effect of effectively improving the stability and the visual quality of the video in a complex dynamic scene.

The application relates to the fields of edge computing and video analysis, and discloses an edge video perception analysis method and system based on codec metadata, specifically, a terminal-side device extracts physical features, target scale, texture entropy and motion intensity, from a video, and pre-prunes a search space of resolution, code rate and frame rate; an edge device constructs an explicit analysis mapping model, performs fine-grained dynamic precision prediction, and solves an online optimization problem to lock an optimal configuration; the terminal-side device executes the optimal configuration, a video stream is uploaded to the edge device for inference tracking, and inference results and update states are fed back to the terminal-side device, thereby forming a millisecond-level adaptive closed-loop control; the application perceives video content features in an approximate zero-cost manner, and establishes a deterministic physical constraint between the features and the configuration, so that resource scheduling can be quickly and accurately guided.

This application relates to methods for operating a multi-modal sensor device and associated apparatus. The invention provides a BMD that has multiple device modes depending on the operating conditions of the device, such as motion intensity, device placement, and / or activity type, which are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods are provided for tracking physiological metrics using the BMD. In some embodiments, the process and the BMD apply time-domain analysis to data provided by the sensors of the BMD when the data has high signal (e.g., high signal-to-noise ratio), and apply frequency-domain analysis to the data when the data has low signal, which facilitates improved accuracy and speed of biometric data.

The application discloses a video key information extraction method, a video question and answer method, equipment and a medium. The video key information extraction method comprises the following steps: calculating the degree of motion intensity of pixels in a video frame sequence to obtain a motion amplitude value corresponding to each video frame in the video frame sequence; calculating a clustering weight corresponding to each video frame based on the motion amplitude value corresponding to each video frame; performing weighted clustering on each video frame based on the clustering weight corresponding to each video frame, and taking a video frame corresponding to a cluster center point of each cluster as a centroid video frame; selecting a video frame with an image similarity between each centroid video frame satisfying a preset condition to obtain a key video frame; and performing image information extraction on each key video frame to obtain key information corresponding to the video frame sequence. Clustering can better process video frames with different importance, obtain more accurate and reliable centroid video frames, and then more accurate key information can be extracted.

The invention provides a multi-scene disaster risk early warning method and device fusing multi-source vision and deep learning and a storage medium, and relates to the field of disaster early warning, and the method comprises the steps: calculating the motion intensity of each image frame in a fused video; obtaining a dynamic intensity threshold value of each time window; based on the motion intensity of each image frame in each time window and the dynamic intensity threshold value of the corresponding time window, performing cutting extraction on the corresponding fusion video of each time window, and obtaining a video clip for dividing a scene boundary; inputting the obtained video clips into a pre-trained disaster classification model to obtain disaster category vectors; inputting the fused video and the disaster category vector into a pre-trained disaster risk identification model to obtain a disaster category result and disaster risk possibility data; and based on the disaster category result and the disaster risk possibility data, performing disaster early warning in combination with disaster risk grading. By adopting the early warning method provided by the invention, rapid and efficient early warning of disasters can be realized.

The invention discloses a landscape lighting intelligent adjusting system based on tone and motion state fusion analysis, and relates to the technical field of digital information processing. The method is used for solving the problems of multi-modal data logic conflict and control signal step. The method comprises the following steps: firstly, executing frequency domain transformation and differential operation on acquired space-time sequence data to generate normalized tone and motion intensity; then, calculating a cooperative gain coefficient and a dispersion index, and quantifying a scene active level and a data deviation; then, calculating a credibility weight based on the dispersion, and executing fusion iterative operation on a preset parameter and a historical state to generate a target control parameter; and finally, generating a pulse width modulation digital sequence in smooth transition by using a linear interpolation algorithm, and outputting a control instruction. According to the system, high-reliability fusion of multi-source data and adaptive smoothing of lighting effect control are realized.

This invention discloses an adaptive temperature control method based on motion state perception, comprising the following steps: Step 1, the motion sensing module senses the user's motion intensity and transmits the motion intensity data to the main control module; Step 2, the main control module determines the motion intensity level based on the motion intensity data, matches a target heating level based on the motion intensity level, and sends a target heating level command to the heating module; Step 3, the heating module adjusts the temperature to the target temperature range according to the target heating level command. An adaptive temperature control system based on motion state perception is also disclosed, comprising a motion sensing module, a main control module, and a heating module; the temperature control system of this invention can automatically match the heating level temperature according to the motion intensity, so that the user does not need to manually adjust the temperature during exercise.

The invention provides a video coding intelligent code rate control method, electronic equipment and a storage medium, and relates to the technical field of video transmission. The method comprises the following steps: acquiring an image of a current GOP; determining the average code rate and the maximum code rate of the image of the current GOP; performing motion detection on the image of the current GOP to obtain a region of interest and motion intensity; and controlling the code rate according to the average code rate, the maximum code rate, the region of interest and the exercise intensity. According to the method, code rate features and motion detection information of GOP are fused, accurate, efficient and adaptive code rate adjustment can be realized, and the method can adapt to complex and changeable application scenes.

The application relates to the technical field of video content auditing, and discloses a video content auditing system based on a large model, which comprises the following steps: information such as the display order and the decoding order relationship of a coded video stream, a motion vector, a coded block spatial position and a video frame center position is extracted through a data acquisition unit; a local offset calculation unit is used to perform time domain difference operation on the motion intensity, and the time sequence offset caused by compression is quantized; a torque diagram generation unit is used to fuse the local offset, the direction symbol and the space vector torque, and construct a frame-level directed heterogeneous torque diagram; a feature processing unit is used to stack multiple torque diagrams into a three-dimensional feature input convolutional neural network, and output a time anchor point of an event occurrence; finally, an auditing execution unit determines an auditing window according to the time anchor point and a frame rate, intercepts an original video segment, and generates visual information to mark manual auditing.

The invention relates to the technical field of video content auditing, and discloses a video content auditing system based on a large model, which comprises the following steps of: extracting information such as a relationship between a display sequence and a decoding sequence of an encoded video stream, a motion vector, an encoded block space position and a video frame center position through a data acquisition unit; a local offset calculation unit is used for carrying out time domain differential operation on the motion intensity, and time sequence offset caused by compression is quantified; the local offset, the direction symbol and the space vector moment are fused through a torque diagram generation unit, and a frame-level directed disparity torque diagram is constructed; stacking multiple frames of torque diagrams into three-dimensional features by a feature processing unit, inputting the three-dimensional features into a convolutional neural network, and outputting a time anchor point when an event occurs; and finally, the auditing execution unit determines an auditing window according to the time anchor point and the frame rate, intercepts the original video clip and generates visual information to mark manual auditing.

The invention relates to the technical field of wearable devices, and provides a wearable device control method and device, a medium, a wearable device and a program product, and the wearable device control method comprises the steps that the exercise intensity of a user is acquired, and the user wears the wearable device; acquiring a contact condition between a user and the wearable device; and determining control parameters of the wearable device at least according to the contact condition and the exercise intensity, and controlling the wearable device according to the control parameters. The control parameters are adjusted according to at least the contact condition and the exercise intensity, so that the power consumption of the wearable equipment is always matched with a real use scene, the energy waste is avoided, and the use duration after single charging is remarkably prolonged.

This application discloses a method and apparatus for dynamically adjusting an AR user interface, relating to the field of augmented reality technology. The method includes: extracting features from real-time detected user head motion data to obtain a head motion state; the head motion state includes head motion rate and head motion direction; switching the interface mode of the AR user interface based on the head motion rate, with different interface modes corresponding to different sizes of the AR user interface; and determining the motion of the AR user interface based on the head motion direction and head motion rate. This solves the problem that existing AR user interfaces struggle to simultaneously accommodate external environment observation and AR information reading in highly dynamic task environments. It can adjust the interface mode and motion of the AR user interface according to the intensity and direction of the user's head motion, reducing interface occlusion. It provides a wider field of view during user head movement while simultaneously allowing the retrieval of key information from the AR user interface.

The invention relates to an activity amount detection method and device, electronic equipment and a medium. The activity amount detection method comprises the following steps: acquiring multiple pieces of motion information of a user, wherein parameters corresponding to the motion information are different; determining a plurality of exercise intensities according to the exercise information; and determining the current activity amount according to each exercise intensity. The current activity amount of the user is determined according to the motion information of the multiple dimensions, the problems that part of the motion information is inaccurate and the motion intensity of part of the dimensions cannot reflect the motion condition of the user are avoided, and therefore the accuracy of activity amount detection is improved.

The invention discloses a dynamic adjustment method and device for an AR user interface, and relates to the technical field of augmented reality, and the method comprises the steps: carrying out the feature extraction of the head motion data of a user detected in real time, and obtaining a head motion state; the head motion state comprises a head motion rate and a head motion direction; switching the interface modes of the AR user interface based on the head movement rate, wherein the sizes of the AR user interfaces corresponding to different interface modes are different; a motion of the AR user interface is determined based on the head motion direction and the head motion rate. The problem that an existing AR user interface is difficult to consider external environment observation and AR information reading in a high-dynamic task environment is solved. The interface mode and the interface motion of the AR user interface can be adjusted according to the motion intensity and the motion direction of the head of the user, and interface shielding is reduced. A larger environment view is provided in the head movement process of the user, and meanwhile key information can be read from the AR user interface.

A method, apparatus, program product, and electronic device for wildlife monitoring and processing are disclosed, relating to the field of image processing technology. The method includes: acquiring monitoring image frames; determining thermal change intensity based on the monitoring image frames; obtaining motion intensity based on pixel differences between the monitoring image frames; obtaining a fused motion intensity based on the thermal change intensity and the motion intensity; determining the target continuity of the target wildlife in the monitoring image frames based on the target wildlife detection results; triggering image acquisition based on the target continuity and the fused motion intensity to obtain a captured image of the target wildlife; and filtering the captured images of the target wildlife to obtain a target image. This method reduces false triggering caused by factors such as wind blowing vegetation, changes in light, or rain and snow, reduces the generation of redundant images at the source, and improves the efficiency of manual screening.

The application discloses a fire detection method based on a BES-BP classifier and space-time visual features. The method comprises the following steps: using a first frame and a second frame of fire images, determining a candidate fire area through red and yellow flame colors, and completing preprocessing to obtain a binary image by applying a maximum inter-class variance threshold algorithm Otsu; based on a flame motion detection technology of motion intensity perception, extracting motion intensity information and a motion area containing motion pixels; extracting four space-time features and two space features. The weights of a BP neural network are optimized by using a vulture algorithm to construct a BES-BP classifier for distinguishing between a real fire area and a non-real fire area. Compared with the prior art, the application realizes monitoring of a fire by automatically detecting flame video information shot by a camera, uses efficient space-time visual features to reliably identify fire flames in different situations, and ensures that the detection of the fire is accurately and quickly completed.

The application relates to the technical field of video processing of computer vision, and provides a smooth round positioning method in a sports video based on group motion information. The method comprises the following steps: obtaining a motion change index of a current video, taking the motion change index as group motion information, and measuring the motion intensity of athletes in the sports video; and positioning the smooth round in the video according to the motion change index, so as to achieve the purpose of segmenting the sports video. In the application, the tracking result of the athletes in the video is expressed in a matrix form, the smooth round and the non-smooth round are expressed as features which are easy to distinguish, and the positioning method of the smooth round is adopted, so that the ideal positioning effect of segmenting the sports video is achieved.

This invention relates to the field of video image denoising technology, and discloses a video image denoising method and apparatus based on temporal information and weighting factors. The method includes: determining the optimal reference image block for an image block to be processed based on weighting factors; determining the motion intensity of the image block to be processed based on temporal information of the image block to be processed and the optimal reference image block; determining the reference block filtering coefficients of the optimal reference image block based on the motion intensity; calculating the reference pixel filtering coefficients and the pixel filtering coefficients to be processed for reference pixels based on the reference block filtering coefficients; and performing denoising on the pixel to be processed based on the pixel filtering coefficients and the reference pixel filtering coefficients. Therefore, implementing this invention can determine the optimal reference image block based on a local weighting factor strategy, which can improve the efficiency and accuracy of image and video denoising and reduce the probability of inter-frame flicker and motion blur problems after denoising.

The invention relates to the field of external mounting type recorders, and in particular relates to an external mounting type recorder with a dynamic early warning function, aiming at solving the problems that a traditional product is high in false alarm rate and insufficient in reliability in a mobile application scene and has defects in application in the fields of security and protection and state monitoring. According to the method, the dynamic degree of the physical motion intensity and the picture content of the equipment is quantified respectively, and the difference relation is calculated to obtain the dynamic bidirectional matching result, so that the consistency judgment of the motion source is realized, the technical limitation of singly depending on picture analysis is overcome, and the matching efficiency is improved based on the bidirectional matching mechanism. According to the method, when the equipment moves violently but the picture is relatively static, or the equipment is static but abnormal movement occurs in the picture, abnormal conditions with inconsistent states can be accurately identified, and a dynamic early warning signal is generated, so that false alarms caused by vibration and displacement of the equipment are effectively reduced, and missed alarms of potential safety hazards such as malicious shielding and lens faults are also avoided.

This application provides a method, system, device, and electronic device for motion intensity monitoring, relating to the field of image processing technology. The method involves: identifying a target object to be monitored and determining its baseline features; extracting target features from each image to be analyzed regarding the monitored area, and using these target features to determine image regions in the analyzed image whose image features match the baseline features; determining the various motion positions of the target object within the monitored area using the location of each determined image region in its respective image; generating a motion heatmap of the target object based on the first occurrence of the target object at each motion position, and determining the motion intensity of the target object within the acquisition time of the analyzed image based on the motion heatmap. Compared with related technologies, the solution provided in this application can monitor the motion intensity of a target object.

The application discloses a video coding method, system, electronic equipment and storage medium, and relates to the technical field of data processing, and comprises the following steps: dividing an original video sequence into multiple groups of images; determining a forward cumulative optical flow and a backward cumulative optical flow for any video frame in any group of images; determining a forward inter-frame motion intensity based on the forward cumulative optical flow and a backward inter-frame motion intensity based on the backward cumulative optical flow; determining a forward motion estimation result based on the forward inter-frame motion intensity and a backward motion estimation result based on the backward inter-frame motion intensity; and coding the video frame based on the forward motion estimation result and the backward motion estimation result to obtain video coding data corresponding to the video frame. The application can improve the accuracy of motion estimation during bidirectional video coding by introducing the forward and backward cumulative optical flows and the inter-frame motion intensity calculation based on the optical flows, thereby improving the coding efficiency and quality.

The invention provides a video frame rate adjusting method and system based on an LED display device, a medium, a program and a terminal, different frame compensation strategies are selected according to a second motion intensity value, and when low motion is needed and only one frame needs to be inserted, frame repetition, zero motion estimation and zero additional delay are adopted to ensure that the rhythm is natural and the real-time performance is met; and switching to motion compensation frame insertion when the system is in medium-high motion or needs multi-frame insertion, reconstructing an intermediate state according to displacement, continuously restoring a motion track, and inhibiting jitter and trailing. Moreover, when the motion compensation frame insertion strategy is executed, afterglow compensation is carried out on the insertion frame, so that the phenomena of smear, ghosting, local brightness overexposure and the like caused by the inherent afterglow effect of LED pixel points in the LED display device when a high-speed motion picture is played are avoided.

The invention relates to the field of intelligent data compression and transmission, in particular to an AI-based lossy compression control method and a video monitoring holder. An AI-based lossy compression control method comprises the following steps: S1, acquiring sensor data and video data, acquiring N original reading sequences according to the sensor data, and acquiring global motion intensity, local motion intensity and specific event confidence according to the video data; and according to the global motion intensity, the local motion intensity and the specific event confidence, respectively constructing a normalized global motion intensity sequence, a normalized local motion intensity sequence and a normalized specific event confidence sequence. According to the method, multi-modal monitoring data is fused, the dynamic association model is constructed, self-adaptive adjustment of the compression strategy is realized through weighted optimization and value evaluation, the data transmission efficiency and event integrity in a resource-limited scene are improved, and the method is suitable for intelligent monitoring of a complex environment.

The invention discloses a physical education evaluation system based on artificial intelligence, and relates to the technical field of teaching evaluation systems, the system comprises a motion data acquisition module, a data preprocessing module, a motion feature extraction module, a teaching target constraint generation module, a teaching evaluation model module and an evaluation result output module; the system collects motion video image data and / or motion sensing data of students in the physical education process, carries out denoising, time alignment and standardization processing on the motion data, and extracts motion track features, joint motion features and motion intensity features based on an artificial intelligence algorithm; and under the action of the teaching target constraint, carrying out weighted fusion and analysis on the multi-dimensional motion characteristics, generating a physical education teaching evaluation result at least comprising motion normalization, technology completion degree and exercise load, and outputting the matching degree between the student exercise performance and the corresponding teaching target.