312 results about "Step detection" patented technology

A system (10) for pedestrian use includes an accelerometer (110) having multiple electronic sensors; an electronic circuit (100) operable to generate a signal stream representing magnitude of overall acceleration sensed by the accelerometer (110), and to electronically correlate a sliding window (520) of the signal stream with itself to produce peaks at least some of which represent walking steps, and further operable to electronically execute a periodicity check (540) to compare different step periods for similarity, and if sufficiently similar then to update (560) a portion of the circuit substantially representing a walking-step count; and an electronic display (190) responsive to the electronic circuit (100) to display information at least in part based on the step count. Other systems, electronic circuits and processes are disclosed.

In a pedometer device for detecting and counting steps of a user on foot, an accelerometer sensor detects a vertical acceleration generated during the step. A processing unit, connected to the accelerometer sensor, processes an acceleration signal relating to the acceleration in order to detect the occurrence of a step, and in particular compares the acceleration signal with a first reference threshold. The processing unit automatically adapts the first reference threshold as a function of the acceleration signal. In particular, the processing unit modifies the first reference threshold as a function of an envelope of the amplitude of the acceleration signal.

The invention relates to a walking movement classification method based on triaxial acceleration transducer signals, which comprises the following steps: fixing a triaxial acceleration transducer on the upper part of the ankle of a testee, connecting the triaxial acceleration transducer with a computer, setting an initial value, and acquiring the variation conditions of different accelerations during the movement; calling a one-step detection subprogram; judging whether the one-step detection is successful; calling a downstairs movement state detection subprogram; judging whether the testee is in the downstairs movement state; calling a voting algorithm subprogram; judging whether the testee is in the upstairs movement state; judging whether the testee is in the forward movement state; setting the movement state as the forward movement state; setting the movement state as the upstairs movement state; setting the movement state as the backward movement state; setting the movement stateas the downstairs movement state; judging whether the current acceleration value exceeds the preset value; setting the movement state as the stationary state; setting the movement state as the running state; and ending. The invention provides an effective solution for individual navigation systems, M-health systems to evaluate the position of walkers in some regions not covered by GPS signals.

The invention discloses an optical remote sensing image ship detection method based on a depth learning single-step detector and mainly solves problems of the limited ability of artificially-designedcharacteristic representation in traditional ship detection methods, insufficient interference resistance capability against the complex background and tedious and slow detection process. The method comprises steps that 1), a remote sensing image data set is established; 2), VGG-16 is utilized as a characteristic extraction portion, a multipath residual block is constructed and is taken as a prediction portion, and a new loss function is constructed; 3), the characteristic extraction portion, the prediction portion and the loss function form a single-step detector; 4), the established data setis utilized to train the single-step detector; and 5), ship detection is carried out thorugh utilizing the trained single-step detector. The method is advantaged in that the method is simple for realization, a ship target in the complex background can be rapidly and accurately detected, and the method is applicable to multiple types of real-time ship detection systems.

A system for maintaining fault-type selection during an out-of-step condition is provided comprising an element for calculating the element reach M; an element for fault type selection; an element for out-of-step detection and blocking; and an element for distinguishing between single-phase-to-ground faults and double-phase-to-ground faults. Single-phase-to-ground faults are distinguished from double-phase-to-ground faults through either a derivative or integration element.

An EEMD neural network based real-time data abnormal value detection method is provided, and the problem that the existing real-time data abnormal value detection method does not consider the historical data abnormal value is taken into account. The method comprises: obtaining historical time series data, and sorting the historical data according to a chronological order; using a median method to carry out preliminary detection on the historical data; finely detecting the historical data by using an EEMD method, and replacing the detected abnormal value with a zero value; then using the curve fitting method to fill the zero value, that is, correcting the abnormal value, and obtaining historical data closer to the objective reality after carrying out abnormal value detection and correction; and finally, by learning the historical data, using the neural network method so that the to-be-reported real-time data can be more accurately predicted, comparing the predicted value with the real-time reported monitored value so that whether there is abnormality can be determined, and correcting the abnormality. The method can be used to detect the real-time data abnormal value in one-dimensional time series, and is applicable to a wide range of fields such as water resources, traffic, weather, thermal power generation and other real-time monitoring data abnormal value detection.

The invention provides a device and method for testing a network device with power supplying function, which solves the problem that it is difficult to quantitatively test the performance index of the network device. The method for testing a network device comprises: receiving the signal transmitted by the network device with power supplying function, the power supply signal being separated from the received signal based on the power supplying signal access mode used by the network device, measuring the voltage and/or current of the separated power supplying signal; giving various answering signals direct towards the power receiving device detection signal and the power step detection signal sent by the network device. According to the technical proposal of the embodiment, the voltage and current of the power supply signal separated from the signal output from the PSE device are measured and various answering signals are given for the detection of the network device, thus the method and device can more accurately, completely test the POE of the PSE device compared with the prior testing method.

The invention discloses a GNSS base station crustal movement velocity estimation method in consideration of nonlinear change. In consideration of the influence on the base station velocity estimationby the GNSS base station nonlinear change, a random model and like, the latest resolving strategy is adopted to acquire a GNSS base station coordinate time sequence under an ITRF2014 framework, a timesequence model for performing separation on the nonlinear change of the base station coordinate time sequence is established by combining a real physical correction model, abnormal location gross error and step detection and like methods; and a GNSS base station coordinate time sequence background noise model determination technology based on the singular spectrum analysis method is adopted, andan improved Bayes information minimum criterion noise model estimation method is proposed base on above conditions, a GNSS base station crustal movement velocity field estimation method is provided, thereby providing accurate and reliable velocity field data basis for the crustal movement velocity field estimation.

The invention discloses a sensor data-based deep learning step detection method. The method comprises the main contents of data input, modal transfer, transfer learning and image classification, and comprises the following steps of: firstly pre-processing a gait data set by adoption of a pre-trained convolutional neural network model, and re-adjusting the size to be 229*229 after noise separation; fitting a bounding box to slice pre-processed images; carrying out image extraction by utilizing a maximum frame method, an average method and a sequence analysis method; and carrying out transfer learning on the extracted images by a pre-trained Inception-v3 model, and obtaining a result after classification. According to the method, the pre-trained network model is adopted, so that plenty of calculation resources and time are saved; by utilizing the concept of transfer learning, the limitation that the other tasks cannot be learned when various flag-free data sets are executed is avoided; and the obtained classification precision is about 90% and is 12% higher than that of the conventional machine learning method.

A system and method for changing the weighting accelerometer filtering based upon motion sensor measurements. Using measurements from motion sensors, one or more features can be extracted. This information is used by an algorithm to assign a most appropriate test feature class to be the class of the state of motion at a particular moment in time. This information is used to provide more accurate positioning information, and can also be used to power down the motion sensor at various times, providing an improvement in battery efficiency.

The invention discloses a multi-sensor fusion and attitude algorithm based free attitude PDR positioning method. The method includes two sections, one is that a self-adaptive updating state judgementthreshold value MFSM step detection method is provided by analyzing the motion characteristics of pedestrians during walking, so that the precision of step detection can be guaranteed under free attitudes when mobile phones are stable relative to human body positions; and two is that a simple and accurate 180 DEG fuzzy judgement method is provided, and judgement can be performed on the motion axisdirection obtained by PCA analysis through acceleration so that the forward directions of the pedestrians can be obtained. A concept of fuzzy judgment confidence is provided at the same time so as tocombine with a gyroscope to perform correction on direction estimation results. Through actual measurement, the method reduces the attitude restriction when the pedestrians use potable electronic equipment to perform PDR positioning, and accurate stepping and direction estimation results can be obtained in the free attitude, such as flat holding, in pockets, in backpacks, etc., where the equipment is placed in a stable position relative to the human bodies.

The invention discloses an error detecting and concealing method of AVS video decoding. The method can accurately detects the macroblock having errors by grammar/semantic error detection and relativity detection and controls the current error frame to conceal errors by utilizing the ribbon structure of a previous correct decoding frame, thereby guaranteeing the image recovery with high quality; simultaneously, the errors are avoided to be transmitted to the next ribbon; in the method, the processing time of the macroblock having errors is equivalent to the required time for normally analyzing the code streams of macroblock frame so that a decoder is not interrupted when the method is applied and the real-time decoding speed of the decoder is not influenced; compared with the existing five-step detection method, the detection speed of the method of the invention is 2-3 times quicker than that of the five-step detection method; compared with the existing concealing method, under the same conditions, although the effect of image recovery is almost the same, the arithmetic complexity is obviously reduced, and the arithmetic speed is 1-1.5 times quicker than that of the prior art; compared with the ribbon concealing arithmetic with AVS video standard, the fault-tolerance effect is 3-4 times of that.

An apparatus and a method for step detection in a personal navigation system is disclosed. In the apparatus acceleration signals are obtained from an acceleration sensor in a movement direction and a gravity direction relative to a user. Sliding window summing data for the acceleration signals output from the acceleration sensor in the movement direction and the gravity direction are calculated so as to obtain a sum of the sliding window summing data. Then, a zero crossing point is detected based on differential sliding window summing data. A difference of a detection time between a present zero crossing point and a previous zero crossing point is compared with a threshold value, thereby detecting steps of the user based on the distinct signal pattern for walk. The step detection apparatus distinguishes zero crossing detection caused by chattering (e.g., vibration) of the human body from zero crossing detection caused by the step of the user, so the step detection apparatus more precisely detects the step of the user. Accordingly, it is possible to precisely detect the step of the user in a hand-held type personal navigation system, such as a portable phone or a PDA, including a micro sensor module.

The invention discloses a method for auditing the safety of an internet video by using a computer system. Digital genes are formed by extracting the characteristics of a sample image or video. Each gene represents all samples with similar characteristics so that the validity and the availability of the samples are improved through abstraction. In the process of detection comparison, a four-step detection method, i.e. slicing and screening, preliminary detection comparison of a maximum sample, a secondary detection comparison of a minimum sample, result feedback and alarming, is adopted, therefore, screening is carried out first, then a large-scope comparison is fast carried out so that the number of the video images to be detected is reduced, and then the detection with pertinence is carried out so as to greatly improve the audition efficiency and increases the accuracy, validity and completeness of the audition.

The invention provides a radar moving target detection method based on a sea clutter background of Doppler oversampling, and relates to the field of target detection on the sea clutter background. The method includes the first step of receiving echo data, the second step of carrying out oversampling and Fourier transformation on selected data, the third step of calculating detection statistics, the fourth step of giving false alarm probability and determining a detection threshold in a Monte Carlo algorithm, the fifth step of comparing the detection statistics with the threshold and judging whether a target exists or not, the sixth step of carrying out the steps from the second step to the fifth step on all distance units in the echo data to obtain the distance unit where the target exists, the seventh step of obtaining new detection data and the eighth step of obtaining the new distance unit where the target exists. The method mainly solves the problem that in the prior art, the number of pulses is small, consistence of Doppler center frequency and Doppler channels of signals is not good, and large targets have a shielding effect on surrounding small targets, so that a detection effect is unsatisfactory.

Disclosed is a traversal path planning method of a pipeline robot. The pipeline robot comprises a car frame. Two driving wheels, two driving wheel motor, a supporting wheel, a forward-looking obstacle detection sensor, a side-looking obstacle detection sensor, , a step detection sensor, and a processor are arranged on the car frame, wherein the two driving wheel motor and the supporting wheel are connected with the driving wheels, the forward-looking obstacle detection sensor is arranged in the front of the car frame, the side-looking obstacle detection sensor is arranged at side of the car frame, the step detection sensor is arranged at the bottom of the car frame, and the processor is used for intensively control. Free motion of the processor is achieved through respectively set of speed and direction of the two driving wheels and the processor can detect distance of obstacles in front and at side. A characteristic signal identification device is arranged in the pipeline robot. The characteristic signal identification device is connected with the processor to identifies characteristic signals of starting point. With the traversal path planning method of the pipeline robot, different strategies are designed according to different positions of pipelines to guide the pipeline robot to walk along a pipeline wall, and thus traversal process in the pipeline can be achieved.

The invention relates to a one-step detection method of genetic mutation, which integrates enzyme cutting, polymerase chain reaction (PCR) enrichment, amplification refractory mutation system (ARMS) fluorescence quantitative PCR; and the method realizes the detection of mutation allele by completing enzyme cutting, PCR enrichment and ARMS fluorescence quantitative PCR in one step through effective temperature and time control.

There is provided a retarder control device which is simple in constitution and can reliably apply braking. An engine rotational speed detector detects an engine rotational speed, gear step detection means detects a gear step of a transmission, an accelerator operation detector detects the operated state of an accelerator, and a retarder controller previously stores automatic braking amount determination data representing the relation between the engine rotational speed and the automatic braking amount of a retarder corresponding to each gear step of the transmission and controls the retarder according to the automatic braking amount of the retarder calculated from the automatic braking amount determination data based on the detected engine rotational speed and gear step of the transmission when the accelerator is judged to be off from the detected operated state of the accelerator.

The invention provides an omni-directional mobile platform and a control method thereof, and a treadmill. The omni-directional mobile platform includes a universal running table, a human body step detection module and a data processing module; the universal running table includes a plurality of movable units and a driving device, and the plurality of movable units include a plurality of first movable units and a plurality of second movable units; the human body step detection module is used for detecting human body steps; the data processing module is used for decomposing human body steps detected by the human body step detection module into the speed in the first direction and the speed in the second direction, and driving the first movable units to move in the first direction according to the speed in the first direction through the driving device and driving the second movable units to move in the second direction according to the speed in the second direction through the driving device. The omni-directional mobile platform can meet the virtual actual demand that the human body can walk at different speeds in any direction.

The invention discloses an EEMD-based time series data abnormal value detection and correction method, and mainly aims at solving the problem that the existing method cannot well detect local abnormal values according to time series change characteristics. The method comprises the following steps of: obtaining original time series data, sorting the original time series data according to a time sequence, and filling the missing data by using the value 0; carrying out preliminary abnormal value detection on the original data by using a median method, and replacing the detected abnormal values by using the value 0; carrying out refined abnormal value detection on the preliminarily detected data by using an EEMD method, and replacing the detected abnormal values by using a value 0; and after carrying out abnormal value detection for twice, all the abnormal values are replaced by the value 0, filling the value 0 by using a local curve fitting method, namely, correcting the abnormal values. Through abnormal value detection and correction, data closer to objective reality is obtained. The method can be used for the abnormal value detection and correction of one-dimensional time series data, and is wide in application fields such as water resource monitoring data, traffic flow data, meteorological monitoring data and financial data.