81 results about "Abnormal gaits" patented technology

The invention relates to the technical field of articles for daily use, in particular to a multifunctional intelligent insole and a gait similarity detection method. The multifunctional intelligent insole is convenient to use, light, convenient to carry, flexible to use and multifunctional, and has a series of functions of weighing, step counting, distance measuring, calorie consumption measuring, lostness prevention, warning while people fall off and wireless data transmission. According to the method, step postures and coordination of a detected object are judged mainly by analyzing triaxial accelerated speed, triaxial angular speed and pressure information of three positions of feet when the detected object moves, accordingly incorrect or abnormal gaits can be effectively found and corrected, and the insole has important application value for dancing lovers, babies learning to walk and patients walking for rehabilitation. Meanwhile, the gait detection method can be matched with an intelligent system for use, and test results can be presented to users visually through an intelligent terminal device.

A knee orthosis device provides medial, lateral, and rotational control of a knee joint. The novel knee orthosis device stabilizes an injured or surgically repaired, or a weakened knee joint having a neurological disability, which causes instability therein, by applying adjustable corrective and therapeutic forces, which operate to stabilize and protect the knee as well as to correct abnormal gait and to rehabilitate the knee joint and surrounding muscles above and below the knee by encouraging and recruiting said muscles to operate again more normally through the use of a dynamic swing assist mechanism. The knee orthosis also provides dynamically conformable thigh and shin cuff circumferential band systems in combination with a multitude of other elements that conform to the constant dimensional changes of the muscle groups that are surrounded by the knee orthosis device during ambulatory or athletic motion.

The invention relates to a Fourier descriptor and gait energy image fusion feature-based gait identification method. The method comprises the steps of performing graying preprocessing on a single frame of image, updating a background in real time by using a Gaussian mixture model, and obtaining a foreground through a background subtraction method; performing binarization and morphological processing on each frame, obtaining a minimum enclosing rectangle of a moving human body, performing normalization to a same height, and obtaining a gait cycle and key 5 frames according to cyclic variation of a height-width ratio of the minimum enclosing rectangle; extracting low-frequency parts of Fourier descriptors of the key 5 frames to serve as features I; centralizing all frames in the cycle to obtain a gait energy image, and performing dimension reduction through principal component analysis to serve as features II; and fusing the features I and II and performing identification by adopting a support vector machine. According to the method, the judgment whether a current human behavior is abnormal or not can be realized; the background is accurately modeled by using the Gaussian mixture model, and relatively good real-time property is achieved; and the used fused feature has strong representability and robustness, so that the abnormal gait identification rate can be effectively increased.

The invention discloses an abnormal gait identification method capable of facilitating screening Parkinsonism. The method is characterized in that the gait plantar pressure characteristics can be extracted, and the modeling and the identification of the neural network of the gait system of the normal healthy people and the patients suffering from the Parkinsonism can be dynamically carried out; the constant neutral network can be established; a dynamic estimator can be built by using the constant neutral network, and based on the difference between the gait modes of the normal healthy people and the patients suffering from the Parkinsonism in the gait system dynamics, the abnormal gait caused by the Parkinsonism and the normal gait of the normal healthy people can be distinguished according to the minimum error principle, and the screening detection of the Parkinsonism can be facilitated. By arranging a pressure sensing floor system or wearing the special shoes provided with the pressure sensor insole, the plantar pressure characteristics can be acquired, and the abnormal gait caused by the Parkinsonism and the normal gait of the normal healthy people can be distinguished conveniently, simply, and non-invasively, and therefore the daily gait monitoring of the family members can be realized, and the screening detection of the Parkinsonism can be facilitated.

The invention discloses an active detection and recognition system and method for a human gait behavior based on semantic folding. Embedded gait behavior detection and recognition system hardware with low power consumption is built by using a three-dimensional sound field positioning system, a sole force field positioning system, an HDMI high-definition camera, a high-definition video acquisition system, a microcomputer Raspberry and the like. Gait semantic energy diagrams with timing characteristics provided by the invention contain gait time information under different situations, and the learning and prediction ability of a gait behavior cognition system can be enhanced according to a lot of gait semantic energy diagrams with timing characteristics. Meanwhile, the active detection and recognition technology for a human gait behavior based on semantic folding has extensive application prospects in various fields which mainly comprises the fields such as long-distance identity recognition, abnormal gait behavior detection, pedestrian behavior prediction and mass video retrieval, and has excellent economical and social benefits.

A computer-implemented method for gait analysis of a subject includes obtaining visual data from an image capture device positioned in front of or behind the subject, the visual data comprising at least two image frames of the subject over a period of time walking toward or away from the image capture device, the at least two image frames capturing at least a portion of the gait of the subject, detecting within the at least two images body parts as two-dimensional landmarks using a pose estimation algorithm on each of the at least two frames, generating a joint model depicting the location of the at least one joint in each of the at least two frames, using the joint model to segment a gait cycle for the at least one joint, and comparing the gait cycle to a threshold value to detect abnormal gait.

The invention discloses an abnormal gait detection method based on a determined learning theory. The abnormal gait detection method based on the determined learning theory includes the steps that features are extracted, neural network modeling and identification are dynamically carried out on a gait system of healthy and normal people and patients with motor neurodegenerative diseases of different types on the basis of the extracted gait features, a constant neural network is built, a dynamic estimator is built by the utilization of the constant neural network, and abnormal gaits caused by the motor neurodegenerative diseases are distinguished from normal gaits of the general healthy people according to the minimum error principle on the basis of differences between the gait mode of the healthy and normal people and the gait mode of the patients with the motor neurodegenerative diseases of different types on the gait system dynamics, so that the abnormal gaits are detected accurately and a detection result is evaluated. The abnormal gait detection method based on the determined learning theory has the advantages that the method is convenient and easy to implement and is in a non-invasion mode, and under the intelligent home environment, daily gait monitoring on family members can be achieved by mounting a pressure sensing floor system or wearing special shoes with sensor insoles.

The invention relates to a method for determining abnormal gait comprising the following steps: (a) measuring ground reaction force generated during walking by a plurality of sensors arranged on the left-foot and the right-foot respectively; (b) applying measurements from each of the plurality of sensors to a predetermined fuzzy membership function to transform the measurements into the first fuzzy values; (c) applying the first fuzzy values to a predetermined fuzzy logic to generate the second fuzzy values for a plurality of gait phases; and (d) comparing the second fuzzy values with pre-stored data of normal gait to determine whether it is abnormal gait or not. Therefore, it is possible to determine abnormal gait more accurately even with fewer sensors.

The invention discloses a wearable intelligent insole with the health consultation function. The wearable intelligent insole with the health consultation function comprises an insole base layer, flexible pressure sensors, a control circuit, a signal transmission circuit and a power supply device, wherein the flexible pressure sensors, the control circuit, the signal transmission circuit and the power supply device are arranged in the insole base layer. The flexible pressure sensors are put on corresponding positions of a tiptoe, a first metatarsophalangeal joint, a fourth metatarsophalangeal joint and a heel respectively, the signal output ends of the flexible pressure sensors are connected with the input end of the control circuit, the output end of the control circuit is connected with the input end of the signal transmission circuit, and the power supply device is connected with the control circuit for supplying power to the flexible pressure sensors. A main chip of the control circuit is integrated with the multi-ary-and-multi-scale-symbolic-entropy data analysis method, and the movement condition, the gait characteristics and the healthy condition of the human body are analyzed according to multiple pressure signals of the foot sole. According to the wearable intelligent insole with the health consultation function, signals of the abnormal gait and the healthy normal gait can be analyzed, processed and identified, and limitation of small data points is met; meanwhile, the coupling relationship between pressure signals of different parts of the foot sole is achieved, the accuracy and the efficiency of gait identification are improved, and the human health is conveniently and remotely monitored.

A method for gait analysis of a subject performed periodically over time to detect changes in one or more gait characteristics. The method includes detecting and identifying a subject and analyzing the gait of the subject on a plurality of occasions. Analyzing the gait of the subject includes, a detecting body parts, generating a joint model depicting the location of the at least one joint in each of the at least two frames, using the joint model to segment a gait cycle for the at least one joint, and comparing the gait cycle to a threshold value to detect abnormal gait.

A device for detecting Parkinson abnormal gaits is disclosed. The device for detecting the Parkinson abnormal giants comprises a gait detection sensor, a time domain analysis module, a frequency domain analysis module, a frequency domain calculation module, a time domain calculation module and a correction module; the gait detection sensor is used for detecting the gaits of a patient and outputting detection signals; the time domain analysis module is used for conducting time domain analysis on the detection signals so as to obtain time domain indexes; the frequency domain analysis module is used for conducting frequency domain analysis on the detection signals so as to obtain frequency domain indexes; the frequency domain calculation module is used for judging the gaits of the patient according to the frequency domain indexes and outputting a frequency domain judgment result when the gaits of the paint are abnormal gaits; the time domain calculation module is used for judging the gaits of the patient according to a preset parameter and the time domain indexes and outputting a detection result of the abnormal gaits in real time; the correction module is used for generating a correction factor according to the frequency domain judgment result and the detection result of the abnormal gaits; and the time domain calculation module is further used for conducting correction on the preset parameter according to the correction factor. The device for detecting the Parkinson abnormal gaits has the advantages of being high in detection accuracy degree and good in real-time performance. The invention further provides a device for relieving the Parkinson abnormal gaits.

The invention discloses a gait analysis method for auxiliary screening of injury of anterior cruciate ligament. The method comprises the following steps: based on the gait characteristics of the extracted knee joint angle and displacement, carrying out neural network modeling and identification on gait system dynamics of healthy normal persons and patients with injury of anterior cruciate ligament; establishing a constant neural network; constructing a dynamic estimator by utilizing the constant neural network; and based on the difference between gait modes of the healthy normal persons and the patients with injury of anterior cruciate ligament in gait system dynamics, distinguishing the abnormal gait caused by the injury of anterior cruciate ligament from the normal gait of the healthy persons according to the minimum error principle, thereby realizing auxiliary screening detection of the injury of anterior cruciate ligament. According to the invention, the gait characteristic data of the knee joint angle and displacement is acquired through an optical sensor, so that the abnormal gait caused by the injury of anterior cruciate ligament and the normal gait of the healthy persons can be conveniently, simply and non-intrusively distinguished; and compared with the screening means, such as magnetic resonance imaging and arthroscopic surgery, the method disclosed by the invention can realize non-invasive screening and can save time and cost.

The invention discloses a gait analysis method capable of carrying out auxiliary screening on knee osteoarthritis. The gait analysis method comprises the following steps: on the basis of the gait characteristic data of an extracted knee joint angle and displacement, dynamically carrying out neural network modeling and identification on the gait system of healthy normal people and the gait system of knee osteoarthritis patients; establishing a constant value neural network; and utilizing the constant value neural network to construct a dynamic estimator, distinguishing abnormal gaits caused by the knee osteoarthritis and the normal gaits of general healthy crowd according to a minimum error principle on the basis of differences between the gait modes of the healthy normal people and the knee osteoarthritis patients on an aspect of gait system dynamics to realize the auxiliary screening detection of the knee osteoarthritis. An optical sensor obtains the gait characteristic data, and the abnormal gaits caused by the knee osteoarthritis and the normal gaits of the general healthy crowd can be conveniently and simply distinguished in a non-intrusive way. Compared with screening means including magnetic resonance imaging, arthroscopic surgeries and the like, the gait analysis method can realize the noninvasive screening of the knee osteoarthritis and saves time and cost.

The invention discloses a flexible ankle rehabilitation robot system. An execution module is connected with a foot module through a Bowden cable and a shank module, and a tension module for measuringtransmission force of the Bowden cable is arranged between the shank module and the foot module; a shank gyroscope is arranged on the shank module, a foot gyroscope and a pressure insole are arrangedon the foot module, a heel pressure sensor and a foot sole pressure sensor are arranged on the pressure insole, and the shank gyroscope and the foot gyroscope are arranged on the front face and the foot face of the shank of a user correspondingly; the pressure insole is located inside the foot module, sends a control instruction towards the execution module through an upper computer and receives sensing feedback information; the execution module transmits torque through the Bowden cable and the shank module to the foot module, so that ankle movement is assisted; and the shank gyroscope and thefoot gyroscope are mutually matched for detecting ankle motion information. The flexible ankle rehabilitation robot system is low in weight and achieves the gait training function for users with abnormal gaits of foot drop and strephenopodia.

The invention discloses a pig gait anomaly detection method based on ellipse fitting and a predictive neural network. The method comprises steps: a video sample needed for an experiment is collected; the video sample is intercepted to acquire continuous target frames, the target frames are pre-processed, and a pig contour sequence with normal walking and abnormal gaits is obtained; ellipse fitting is used for modeling each part of the pig body, and a pig walking gait feature parameter sequence is built; through principal component analysis, the extracted features are subjected to optimized processing, and a feature sequence is extracted; and the predictive neural network is used for building a training model about normal walking and abnormal gait feature sequences, and through the training model, whether the inputted gait sequence belongs to abnormal walking is detected. Abnormal walking, such as laming, diseases of the forelimbs and instable forelimb walking caused by injuries of the pig, can be effectively recognized, and a good basis is provided for realizing a large-scale and intelligent pig industry.

The invention discloses a hemiplegia balancing training instrument which comprises a base, a main stand rod vertically arranged in the center of the front end of the base, a left electronic scale and a right electronic scale. The left electronic scale and the right electronic scale are symmetrically arranged on the base and used for supporting the corresponding lower limbs of a patient. A transverse holding rod with the height adjustable is horizontally arranged on the main stand rod, the main stand rod is arranged on a wall, the left electronic scale and the right electronic scale respectively comprise a display screen used for displaying stress data to remind the patient to keep lower limb stress balance, and the display screens are arranged on the left side and the right side of the main stand rod respectively corresponding to the electronic scales. According to the instrument, the limb joints and muscles of the hemiplegic patient can be exercised and trained, the function can be restored more easily, the patient can consciously control the body gravity center to carry out excursion, the stress of the lower limbs is coordinated to achieve balance, the abnormal gait of the patient can be prevented and treated, the instrument is suitable for training cerebral apoplexy patients, cerebral apoplexy patients and other hemiplegic patients before walking, and the solid foundation can be laid for the normal walking training of the hemiplegic patients.

The invention belongs to the technical field of biological feature recognition, and particularly relates to a multi-sensor signal fusion method based on deep learning for gait classification. Abnormalgaits are classified by constructing a deep neural network, and multi-source heterogeneous information source data from an IMU inertial sensing unit and SEMG surface electromyography are fused by utilizing a convolutional neural network; The fusion content comprises a data layer (CNN input layer), a feature layer (CNN pooling layer 1 to convolutional layer 2) and a decision layer (CNN output layer) fusion, so that multi-source heterogeneous sensor information is completely extracted, the classification precision of the classifier is improved, the data preprocessing workload is reduced, and the classification accuracy and the judgment efficiency are improved. It is verified that the classification effect of the method in multiple abnormal gait classification tasks is remarkably improved compared with that of a single-mode sensor, and in an abnormal gait six-classification task mentioned in the embodiment, the classification accuracy reaches 99.15%, and is improved by about three percentage points compared with that of a single IMU information source CNN network.

The invention relates to an abnormal gait recognition apparatus and an abnormal gait recognition method, and belongs to the technical field of gait analysis. The abnormal gait recognition apparatus comprises a smart left foot shoe, a smart right foot shoe, a left shank data collection device, a right shank data collection device, a left thigh data collection device, a right thigh data collection device, a trunk data collection device, a data receiver and a cloud server. Abnormal gait models are established by collecting relevant data; and then, computation is carried out by utilizing the collected data, and comparison is performed with abnormal gait model standards so as to determine occurrence of abnormal gaits.

The invention provides an abnormal gait detection method and an abnormal gait detection system. The abnormal gait detection method includes acquiring a video containing gait information to be detected, and extracting the information indicating a characteristic part of the gait of the human being in the gait information to be detected; and according to the extracted information of the characteristic part, determining whether the gait in the gait information to be detected is an abnormal gait by means of a first neural network. The detection method can determine whether the gait information to be detected is an abnormal gait by means of the neural network based on the video, thereby improving the detection efficiency of the abnormal gait and saving the medical resources.

Embodiments of the present invention disclose a gait identification method and an electronic device. The method comprises: acquiring a gait parameter of a target object; extracting gait feature information of the gait parameter according to the gait parameter; matching the gait feature information with an abnormal gait model stored in the gait database to obtain a matching ratio; and if the matching ratio reaches a preset threshold, identifying that the current gait of the target object is the abnormal gait. According to the embodiments of the present invention, gait identification accuracy can be improved in a facilitated manner, and the probability of misjudgment can be reduced.

The invention discloses a new abnormal gait analysis method and system. The method comprises steps that S1, a moving human target is tracked, footprints of three consecutive steps in an image are corrected to acquire the image pixel position (ui<M>, vi<M>) of the corrected footprints in a straight line; S2, according to the image pixel position (ui<M>, vi<M>) of the corrected footprints, the observation distance of two adjacent corrected footprints in the image and observation step size ratios A and B between two adjacent steps after correction are calculated; S3, step sizes of an unilateral leg are supposed to be basically identical, namely L3<Real>=L1<Real>, and the ratio of the actual step size L2<Real> of a second step to the actual step size L1<Real> of a first step is calculated; andS4, clustering statistics of adjacent step size ratios of a monitored object is carried out, and the real-time adjacent step size ratio of the monitored object is compared with a clustering center ofthe clustering result. The method is advantaged in that the application scope is wider, the method is suitable for general straight line conditions, compared with a no-correction gait method and an MGM system, estimation accuracy of the adjacent step size ratio is higher, and the error is reduced.

The invention is a gait analysis technology of a wearable device, and relates to a diabetic foot risk early warning device based on time-space domain characteristics of plantar pressure information. The device includes a wearable shoe system, a data processing unit, a kinematics feature extraction unit and a prediction model; the wearable shoe system includes a data acquisition unit for collectingdynamic plantar pressure data of a subject; the data processing unit acquires plantar pressure data within a continuous period of time and divides the data into plantar pressure signals in each gaitcycle; the kinematics feature extraction unit performs kinematic feature extraction from the divided plantar pressure signals to obtain a data label pair set; the data label pair set is divided into atraining set and a test set to construct and train a prediction model; and the characteristic parameters of the plantar pressure distribution of the subject is input into the trained prediction modelto obtain the result of whether the subject has an abnormal gait. The device makes full use of the pressure information in multiple characteristic areas of planta pedis, and warns the subject whetherthe gait is abnormal in time.

The invention discloses a person-based abnormal gait detection method for a lateral gait video. The lateral gait video is collected through a common camera or mobile phone; a stride change feature anda body forward lean feature of a person are extracted from the lateral gait video; a one-class support vector machine model is trained by using feature information of normal gaits; and correspondinggaits can be quickly and effectively detected to be normal or abnormal. A special detection device is not required, and the gait detection does not need to be performed in a specific place, so that the flexibility is high. The body forward lean characteristic is considered when the gait features are extracted through the gait video, and the detection capability of the abnormal gait detection modelcan be effectively prevented from being influenced by abnormal training data, so that the detection accuracy is improved. The one-class support vector machine model is trained by only adopting features of normal gait information, few training samples are required, and the gaits can be quickly and accurately detected to be normal or abnormal, so that a doctor is assisted to perform abnormal gait diagnosis, and the working efficiency of the doctor is improved.

A knee orthosis device provides medial, lateral, and rotational control of a knee joint. The novel knee orthosis device stabilizes an injured or surgically repaired, or a weakened knee joint having a neurological disability, which causes instability therein, by applying adjustable corrective and therapeutic forces, which operate to stabilize and protect the knee as well as to correct abnormal gait and to rehabilitate the knee joint and surrounding muscles above and below the knee by encouraging and recruiting said muscles to operate again more normally through the use of a dynamic swing assist mechanism. The knee orthosis also provides dynamically conformable thigh and shin cuff circumferential band systems in combination with a multitude of other elements that conform to the constant dimensional changes of the muscle groups that are surrounded by the knee orthosis device during ambulatory or athletic motion.

The invention belongs to the technical field of biometric feature recognition, and particularly relates to a gait anomaly recognition method based on a back-propagation neural network. The method comprises the steps that an IMU worn by the human body is used for collecting signals when the human body walks normally and when typical abnormal gait walking is simulated to obtain triaxial accelerationinformation under different gaits; original data is subjected to windowing cutting pretreatment according to a target typical walking stride frequency, and each data queue is labeled correspondinglyaccording to gait classes; a BNPP back-propagation neural network is constructed; obtained data tag pairs are classified into a training set and a test set, the training set is sent to a BPNN for training, and after training is completed, the test set is used for evaluating a model classification effect. The gait anomaly recognition method based on the back-propagation neural network has the advantages that the original IMU triaxial acceleration data is directly classified by increasing the number of input layer nodes, thereby eliminating the complicated gait cycle division and feature extraction engineering, increasing the classification accuracy rate of various abnormal gaits, reducing the workload of data pre-processing and improving the classification accuracy.

The invention discloses an abnormal gait behavior recognition method based on virtual posture sample synthesis. The virtual posture sample synthesis model is trained by using a three-dimensional parameterized abnormal gait real training sample; and then a virtual sample is generated by using the trained model, a SoftMax abnormal gait behavior classifier is trained by using the real training sampleand the virtual sample, and the collected abnormal gait behavior can be accurately recognized through the classifier after the training is completed. According to the invention, a virtual attitude sample synthesis method and a characteristic modulation mechanism are adopted; the problem of few human body abnormal gait real training samples can be effectively solved; the abnormal gait behavior detection and recognition model has wide application prospects, including dangerous area abnormal gait behavior recognition, elder abnormal gait behavior detection, pedestrian gait behavior analysis in intelligent driving and security and protection and the like, and has good economic and social benefits.

The invention relates to a parkinson patient abnormal motion prompting method and device. The method comprises the following steps: if the patient is in a walking state, obtaining gait information, wherein the gait information comprises gait patterns and / or gait time intervals; determining whether the gait is an abnormal gait according to the gait pattern and / or the gait time interval; reminding if the gait is abnormal. By acquiring gait information of a Parkinson patient, the Parkinson patient abnormal motion prompting method and device according to the disclosed embodiment can remind the Parkinson's disease patient when it is determined that the gait corresponding to the gait information is an abnormal gait, thereby enabling the Parkinson's disease patient to correct the gait in time andpromoting the recovery of the patient. In addition, by determining abnormal gait according to gait pattern and / or gait time interval, it is easy to realize, the determination of abnormal gait is faster. And the reminder of abnormal gait for Parkinson patients is more timely.

The present invention discloses a conjugate gradient attitude solving method for abnormal gait recognition. The method comprises the following steps: processing data of an accelerometer and a magnetometer by using a conjugate gradient method to obtain a solution attitude angle, and then fusing the solution attitude angle with an attitude angle of a gyroscope obtained by numerical integration to obtain a final attitude angle. According to the method provided by the present invention, by using the complementary characteristics of the gyroscope, and the magnetometer and accelerometer in the frequency domain, through a complementary filter, the solution attitude angle of the magnetometer and accelerometer is fused with the attitude angle of a gyroscope obtained by numerical integration to obtain a final attitude angle, so that the precision of the attitude measurement can be improved, the error of the gyroscope attitude is reduced, and the dynamic performance of the accelerometer is improved.

A walking assistance method may include receiving at least one abnormal gait type selected from a plurality of abnormal gait types, and differently controlling a walking assistance apparatus based on the at least one abnormal gait type.