78results about How to "Evaluation is objective and accurate" patented technology

The invention discloses a method for detecting lane change of a vehicle based on a vehicle-mounted camera. The method comprises the following steps: firstly, initializing a read-in image, and converting the read-in image to a gray space; secondly, segmenting an sky region and a ground region of the image, and acquiring the image of the ground region; thirdly, carrying out edge detection by utilizing the sobel operator; fourthly, carrying out binaryzation by utilizing an Otsu's method; fifthly, restricting a fitting range, wherein hough transformation is restricted by the minimum fitting points, and extracting a lane line equation; sixthly, determining the type of a lane line; seventhly, classifying lane line treatment results; and eighthly, determining the current lane change situation ofthe vehicle. According to the invention, the current lane change situation of the vehicle is detected by adopting the mode of images, the existing vehicle-mounted camera of a driving school is utilized, has low cost, high practicability, diversity detection data, and has accurate and objective evaluations of lane change level for students, the equipment is simple to install, and has wide applications.

The invention discloses a cooperative target pose precision measurement method based on a PNP perspective model. The cooperative target pose precision measurement method comprises the following steps: mounting N vision mark points on the outer surface of a cooperative target; photographing a mark image of a vision mark by using a camera; pre-setting an initial value of a position pose between the cooperative target and the camera, wherein horizontal and vertical components of a three-dimensional space coordinate and the effective focal length of the ith vision mark point, and horizontal and vertical components of a main point coordinate are in uncertain system errors and error limits are known, a two-dimensional coordinate of the center of the vision mark point in the mark image corresponding to the ith vision mark point is in a random error, and the corresponding error limit is known; quantifying and analyzing an influence weight coefficient of a pose error by each parameter; and calculating an uncertain system error component and a random error component of the position pose between the cooperative target and the camera, and weighing to obtain a target pose measurement error, so as to finish the pre-estimation of the target pose measurement precision.

The invention discloses a human motion posture recognition and evaluation method, and the method comprises the following steps: S01, collecting a video image test data set, and performing data processing on data in the video image test data set; S02, inputting the test data after data processing into the trained LSTM neural network model for human motion posture recognition, and outputting a recognition result; S03, comparing the output identification result with standard motion data, and evaluating the standard degree of the identified human motion posture according to the comparison result.The invention further discloses a human motion posture recognition and evaluation system, and the system comprises an image acquisition module, a data processing module, an LSTM neural network model,a model training module, a data center and a posture evaluation module. According to the method, the long-term time information can be captured, complex space-time clues of human body actions can be captured through a time domain attention mechanism and a space domain attention mechanism, and the accuracy of human body motion posture recognition is greatly improved.

The invention discloses a bituminous pavement surface structure 2D test evaluating system and method. The system comprises an image acquiring module, an image processing module, a surface structure line acquiring module, a surface structure line processing module, and an analyzing and computing module. The method comprises the following steps of: 1, making a bituminous mixture test piece; 2, acquiring a profile scanning image of the bituminous mixture test piece; 3, preprocessing the profile scanning image to obtain a profile scanning grey-scale map; 4, acquiring the surface structure line of the profile scanning grey-scale map; 5, performing bad point deletion, anti-confusion filtering, window function addition, and DFT on the surface structure line to obtain the constant-bandwidth narrow spectrum of the surface structure line; and 6, analyzing the power spectrum of the constant-bandwidth narrow spectrum of the surface structure line and computing an evaluation index octave index L<TX, I j> for the bituminous pavement surface structure. The system and the method are high in testing precision, simple in operation, low in cost, and easy to popularize.

The invention discloses a multifunctional material electromagnetic parameter test system. The multifunctional material electromagnetic parameter test system comprises a base, an arched frame, an operating platform and an auxiliary sliding rail, wherein the arched frame, the operating platform and the auxiliary sliding rail are respectively fixed on the base; the auxiliary sliding rail is of a circular arc shape, the auxiliary sliding rail and the arched frame are positioned in the same plane, and the center of the auxiliary sliding rail and the center of an arc part of the arched frame are coincided; the operating platform is provided with a transmission hole, and the center point of the transmission hole and the center of the auxiliary sliding rail are coincided; the operating platform is horizontally arranged and is fixedly connected with the vase through vertical plates arranged on the two sides of the operating platform; each of the arched frame and the auxiliary sliding rail is provided with a signal antenna which is connected in a sliding manner, and the signal antennae are used for emitting or receiving the signals. In a multifunctional material electromagnetic parameter test method based on the test system, the relative positions of the arched frame and the auxiliary sliding rail is regulated according to different test parameters; due to the arrangement of the operating platform and the installation of a standard metal plate or a test material on the vertical plates, emitted signals and received signals of the signal antennae are utilized to obtain the test parameters; in addition, electromagnetic parameters for testing a testing material include a transmissivity/or reflectivity and/ or space electromagnetic parameter.

The invention discloses an evaluation method for the perpendicularity of an image sensor light-sensitive surface and an optical axis and an optical test card, used for quantitatively calibrating the perpendicularity of the image sensor light-sensitive surface and the optical axis. The evaluation method comprises the steps of collecting N frames of images of the test card during a process that a focusing ring of a camera lens rotates a circle; according to a preset coordinate system, respectively extracting target areas from at least three same positions of the N frames of images; respectively computing a boundary information value of each target area in each frame of image; and computing the perpendicularity of the image sensor light-sensitive surface and the optical axis according to the boundary information values.

The invention discloses a detection evaluation method of roller surface layer grain size, and the method is as follows: using a cleaning agent for cleaning a roller to-be-detected region which is treated by surface grinding; preparing a surface wave sensitivity test block with rectangular seamed edges, choosing a surface wave probe with a frequency of 2MHz and an ultrasonic flaw detector, using the sensitivity test block for regulation of ultrasonic flaw detector sensitivity by a surface wave test block end part seamed edge method; setting the sonic path distance of the ultrasonic flaw detector to be 250mm, putting the probe in the roller surface to-be-detected region for well coupling, moving the probe at a uniform speed under the set detection sensitivity, observing waveform display changes of an oscilloscope screen, and acquiring a grass-like echo waveform; and in 20-100% sonic path distance range of the oscilloscope screen, according to the grass-like echo amplitude value, determining the roller surface grain size grade range. The method overcomes the defects of traditional metal grain size detection, improves the detection speed and simplifies the detection process, without restriction of detecting positions and destroying of a specimen, so that the roller quality can be accurately and objectively evaluated.

The embodiment of the invention discloses a face image fuzziness computing method and device which prevent a high local gradient value due to strong light by normalizing the local gradient value of each pixel, which prevent an increase in the local gradient value due to plenty of background texture by assigning different weighted values to pixels of a face or background; and which prevent influence of the noise of image acquisition equipment on fuzziness evaluation by introducing gradient density. The method may overcome influence of light change and the noise of background and acquisition equipment, objectively and accurately evaluate image quality, and is good in robustness.

The invention relates to a method and an apparatus for optimizing a human face picture quality evaluation model. The method comprises the steps of establishing a human face picture test set; identifying the similarity between a to-be-tested human face picture and a sample human face picture in a preset human face database, and according to the similarity and picture identity information, obtainingan identification result of each to-be-tested human face picture; according to the identification result, determining a quality score of each to-be-tested human face picture; and performing neural network training by taking the to-be-tested human face pictures and the corresponding quality scores as training data to obtain optimized human face picture quality evaluation model and parameters. Through the human face picture quality evaluation model and the parameters, human face picture quality evaluation is not influenced by human subjective factors.

The invention provides a performance test system for a battery liquid cooling plate. The system comprises a test module for simulating heating in charging and discharging a battery, a water inlet pipeand a water outlet pipe. The test module comprises an insulating shell with an opened bottom surface and also comprises an upper metal plate, an electric heater, a lower metal plate and a silica gelthermal conductive pad which are stacked from the top to bottom in the shell. An inner wall of the shell is provided with a heat insulation layer, the electric heater is provided with a power controller, the silica gel thermal conductive pad is provided with multiple thermocouples, a bottom of the shell is used for connecting a liquid cooling plate to be tested, the silica gel thermal conductive pad is attached to the surface of the liquid cooling plate, the water inlet pipe is provided with an inlet temperature sensor and an inlet pressure sensor and is connected to a liquid cooling plate water inlet, the water outlet pipe is provided with an outlet temperature sensor and an outlet pressure sensor, and the water outlet pipe is connected to a water outlet of the liquid cooling plate. The system has the advantages that the heat balance rates of the liquid cooling plate of a power battery under various operating conditions can be quickly simulated and tested, the accurate and objective evaluation of the heat dissipation performance of the liquid cooling plate is facilitated, and the rapid selection design is achieved.

The embodiment of the invention discloses a network quality analysis method and device, computer equipment and a storage medium. The method comprises the steps that communication data between preset data links in the interaction process are acquired, and the communication data are parameter data which are generated between the preset data links and represent the network quality when data transmission is conducted based on a preset communication protocol; classifying the communication data according to a preset analysis type; and performing statistical calculation on the classified communication data to obtain quality parameter values of different preset analysis types in the network. According to the technical scheme of the invention, the quality measurement of each data transmission is described under the combined condition of the network state and the transmission protocol. An internal network quality detection tool or application does not need to be additionally arranged, so that the network quality analysis is quicker and more gradual, the data volume is large, the network quality is evaluated by adopting a statistical analysis mode, and the evaluation is more objective, more accurate and more direct.

The invention relates to a second-hand vehicle detection system, which comprises a vehicle body surface paint data analysis module, a vehicle chassis data analysis module, a vehicle computer data analysis module, an engine cylinder pressure data analysis module, an engine cylinder body analysis module, an engine performance analysis module and a comprehensive evaluation module, wherein the vehicle body surface paint data analysis module is used for setting the number of vehicle body surface paint data acquisition surfaces according to a different vehicle type, and each vehicle body surface paint data acquisition surface is provided with five acquisition points; vehicle body surface paint defects are judged according to the vehicle body surface paint data; and the comprehensive evaluation module is used for evaluating the comprehensive state of the vehicle according to the vehicle body surface paint defects, the vehicle chassis deformation state, the working state of each part of the vehicle, the engine cylinder body state and the engine power performance state. As each vehicle body surface paint data acquisition surface is provided with five acquisition points, the overall vehicle body surface paint detection efficiency is greatly improved, and compared with the phenomenon that four acquisition points are arranged for the original vehicle body surface paint detection, the efficiency is improved by about 30%.

The invention discloses a washing machine motor rotor production process, comprising the following steps: S1: stamping; S2: casting aluminum, setting the temperature of a resistance melting aluminum furnace, and preheating, then adding pure aluminum into the resistance melting aluminum furnace, Put the stamped rotor into the cast aluminum mold, start the cast aluminum hydraulic press, and carry out the cast aluminum operation of the rotor. After the end, inspect the cast aluminum rotor to determine whether it meets the requirements; S3: Finale, press the shaft into the cast aluminum rotor ;S4: Turning, place the rotor on a lathe, and perform turning operation. After the turning operation is completed, perform surface runout detection, and clean up the burrs and aluminum cutting flashes of the rotor; S4: Perform surface processing, and complete the entire Rotor production process. The motor rotor proposed by the invention has a perfect production process, a clear process, high detection accuracy of key procedures, accurate evaluation of the quality of the motor rotor, and ensures that the produced rotor has good quality, stable performance and long service life.

The invention provides a method for civil aircraft flight deck human-computer interface comprehensive evaluation. The method comprises the steps that an evaluation index of a human-computer interface is selected through a comprehensive method or an analysis method or a composite algorithm method or an index attribute grouping method; a civil aircraft flight deck human-computer interface comprehensive evaluation index system is determined; grading is conducted on each index of civil aircraft flight deck human-computer interface evaluation and an initial grading value of the index is determined; data collection is conducted on a given human-computer interface sample, prepared inspection data are substituted, and a relative error of an output actual value and a predicted value is calculated; the accuracy of the relative error is inspected, data of each index of the civil aircraft flight deck human-computer interface to be evaluated are input and are calculated through an established BP nerve network module, and a final evaluation result is obtained. The method can conduct objective and accurate evaluation on the civil aircraft flight deck human-computer interface.

The invention discloses a method and apparatus for evaluating audio and video content. The method comprises the following steps: collecting an image and/or sound of a current environment in a processof playing of the audio and video content; performing feature information recognition on the collected image and/or sound, and judging whether the collected image and/or sound meets an evaluation criterion according to a recognition result of the feature information; and generating an evaluation result of the audio and video contents according to the recognized feature information. By adoption ofthe technical scheme, the evaluation of a user can be obtained by knowing the emotion and other reactions of the user after obtaining the audio and video content without affecting the user from watching or listening to the audio and video, and the authenticity of the evaluation is ensured by filtering out the false data, so that the obtained evaluation result is more objective and accurate.

The invention discloses a power supplier evaluation method based on an MATLAB algorithm. The method comprises the steps of collecting material types and historical electricity consumption informationcorresponding to a supplier contract; selecting a certain amount of data as samples; The power consumption data is separated into trend and fluctuation through wavelet transformation, a supplier powerconsumption analysis model is established, the reasonable monthly power consumption interval of the supplier is analyzed according to the model, and whether the productivity of the supplier meets therequirement or not can be more objectively and accurately evaluated in combination with the monthly actual power consumption of the supplier.

The invention provides a rank learning-based quality evaluation method for the deep scarification operation of a farm machine. The method solves the problem in the prior art that the existing evaluation for the deep scarification operation quality of farm machines does not adopt any objective evaluation system. The method comprises the steps of collecting the operation data of multiple farm machines during one deep scarification operation, wherein the operation data are composed of a plurality of equispaced time points, and the longitude, the latitude, the triaxial acceleration, the triaxial angular velocity and the ploughing depth data of the deep digging plough of each farm machine at each time point; pre-processing the operation data of the farm machines; extracting operation feature values out of the pre-processed operation data of the farm machines, and adopting the feature values and corresponding tag values as a training sample set, wherein the feature values comprise the plot track regularity, the bad operation behavior number of the farm machines within a unit mileage, and the ploughing depth stable value; adopting the rank learning method to train the training sample set, and obtaining an optimal farm machine deep scarification operation quality evaluation model; by adopting the obtained model, evaluating the deep scarification operation quality of farm machines.

The invention relates to an integration device for collecting lateral seepage of a rice field and overland runoff. The integration device is characterized by comprising a top sealing collection box with a right trapezoid-shaped longitudinal section, wherein the box body is vertically inserted into the soil on the ridge of the rice field by taking the slope as a base plate, and a lateral seepage storage trough is formed at the inclined bottom; a U-shaped trough plate with a U-shaped longitudinal section is embedded into the collection box, and the bottom of the U-shaped trough plate is downwards inclined from the liquid feeding side wall to the liquid discharging side wall; the U-shaped trough plate is hermitically connected with the box body to form an overland runoff storage trough; a lateral seepage filtering net is arranged at a lateral seepage inlet in the bottom of the liquid feeding side wall below the outwards folded edge at the top of the liquid feeding side, and an overland runoff inlet with a sliding baffle capable of adjusting the liquid feeding height is formed in the liquid feeding side wall above the outwards folded edge at the top of the liquid feeding side; an overland runoff filtering net is arranged at the outwards folded edge at the top of the liquid feeding side of the U-shaped trough; a lateral seepage flow guide pipe and an overland runoff flow guide pipe are arranged and are led to a suction sampling device from the corresponding liquid discharging side wall. The integration device has the advantages of reducing the investment, increasing the utilization rate of equipment and facilitating the use.

The invention discloses an atlas similarity calculation method based on baijiu features. The method comprises the following steps: eliminating a weight difference caused by the large atlas data scaledifference of a baijiu sample through the normalization preprocessing, screening out atlas data with the large contribution rate of the baijiu features through the principal component analysis, and determining a weight value of the atlas data participating in the similarity calculation according to the size of the contribution rate of the atlas data. While the similarity of two baijiu atlases in the same type is calculated, only the screened atlas data is selected, and the corresponding weight value is substituted in a similarity formula to obtain a similarity value. The similarity value obtained by using the method is capable of eliminating the adverse effect to the similarity value caused by the low contribution rate or irrelevant atlas data, adequately considering the differences of thecontribution rates to the baijiu features caused by the different feature components, and more accurately reflecting the similarity level of the baijiu features, so the objective evaluation to baijiuis more accurate.

The invention discloses a visual attention mechanism-based fabric pilling grade evaluation method. The method comprises the following steps of: 1, acquiring a fabric pilling image; 2, carrying out wavelet multilayer decomposition on the fabric pilling image; 3, determining a central layer subgraph and a peripheral layer subgraph of the fabric pilling image; 4, constructing a fabric pilling saliency map; 5, obtaining a fabric pilling target; 6, extracting fabric pilling features; and 7, evaluating a fabric pilling grade. According to the visual attention mechanism-based fabric pilling grade evaluation method, the central layer subgraph and the peripheral layer subgraph are correctly selected and central-peripheral operation is carried out between the two subgraphs, so that the significance of the pilling target can be improved and the calculated amount can be decreased; threshold value segmentation and filtration are carried out on the fabric pilling saliency map, so that the fabric pilling target can be effectively obtained; and on such basis, the pilling features are extracted, so that objective evaluation can be rapidly and correctly carried out on the fabric pilling grade.

The invention provides a multi-target game method and device for tactical decision of multiple unmanned aerial vehicles in a confrontation environment, which relates to the technical field of tactical decision. According to the method, the relative situation advantages are subjected to multi-target representation (i.e., the situation advantages are decomposed into a plurality of sub-situation advantages), and compared with a traditional evaluation method in which the plurality of sub-situation advantages are aggregated into one comprehensive situation advantage processing, the four sub-situation advantages are respectively considered as four sub-optimization targets, and a payment function is designed on the basis, and a high-dimensional matrix is constructed, and information of each sub-situation advantage in the situation advantages is comprehensively reflected. Objective evaluation is more accurate, and the situation of information loss is avoided.

The embodiment of the invention discloses a sleeping monitoring chip system and a sleep monitoring chip. The system comprises a chip body, a mobile phone APP monitoring software and a signal cloud processing platform; the system is based on the key signal parameter data such as brain waves and respiratory rhythm collected by the chip body, the signal cloud processing platform is used for data collection, storage, EEG algorithm analysis model construction and application, the sleep of target population is monitored in real time; and the system makes a comparative analysis with the general population, the difference parameters and rhythm are found out, and data support are provided for more accurate and objective evaluation of sleep quality and designation of accurate sleep treatment programs.

The invention discloses a perfume fragrance holding time accelerating tester. The tester comprises a constant temperature and humidity device, an exhaust fan, a wind speed controller connected to theexhaust fan, a hollow cylinder having one end connected to the housing of the exhaust fan, a sponge ball and a clip for fixing the sponge ball. The invention also discloses a method for operating theperfume fragrance holding time accelerating tester. The operation method of the invention is used to test the perfume fragrance holding time to avoid the difference between the body temperature and the sensory sense of the human body and establish a uniform detection method for the fragrance holding time of various perfumes so as to facilitate more accurately and objectively estimate the perfume quality for production guide and formula design. The perfume fragrance holding time accelerating tester is convenient to use, rapid, efficient, small and easy for industrial production.