37results about How to "Visual comparison" patented technology

The invention discloses an automobile driving characteristic evaluation and early warning method based on driving inclination, which belongs to the technical field of automobile intelligent interaction. The invention aims at collecting real-time operation data of an automobile as original data for evaluating automobile driving characteristics, extracting the original data according to scenes and exerting the characteristic advantage that the driving inclination evaluates specific scenes in real time. The data complexity can be reduced by using a time sequence dimension reduction algorithm, andmeanwhile, time sequence characteristics implicit in the data are reserved; operation fragments are counted to obtain a high-frequency operation fragment database, and detailed driving characteristicbehavior description can be carried out; an HMM model is used for inclination identification, and an identification result has high credibility; by further calculating the camber value, the operationcharacteristics of all parties of a driving game can be compared; early warning information is obtained through quantitative and qualitative evaluation results, and the content is convenient to compare; the data are continuously updated along with the operation of the automobile, the real-time performance of the evaluation result and the early warning information is ensured, and the practicability is very high.

The invention relates to a double-base-layer anti-fake structure and a manufacturing method and an anti-fake method thereof. The double-base-layer anti-fake structure comprises a first base layer, an adhesive layer, a bottom layer and a second base layer, wherein one of the two surfaces of the first base layer is coated with a release agent, and a metal plating layer is formed on the surface, coated with the release agent, of the first base layer; the bottom layer is coated with a release agent, and the surface with the release agent is attached to the metal plating layer through the adhesive layer; the second base layer is stuck to the surface, without the release agent, of the first base layer. The sticking efficiency can be improved by improving the physical structure of the anti-fake structure.

The invention discloses a visual detection device for motor vibration tests and a stability adjusting method. According to the visual detection device, a damper is mounted on a motor. A lower computer, a host computer and at least one acceleration sensing module are comprised, the acceleration sensing module is fixedly mounted on the surface of the damper and is used for transmitting the acquired data to the lower computer, the lower computer is for calculation of the data, a kalman filtering algorithm is utilized to carry out data processing, each corresponding acceleration value is acquired, the host computer and the lower computer are in communication connection, a processing application program capable of processing the acceleration values is comprised, a wave-shaped curve map is drafted and is displayed on a screen, and stability of the motor is adjusted through employing the adjusting method on the basis of the detection device. Through the device and the method, readability and comparability of the data can be greatly improved, difference among the acceleration values can be visually observed and compared, quality of each position of the damper can be accurately increased or reduced, so vibration of positions of the motor tends to be consistent, influence of vibration on the work condition can be reduced, and service life of the motor is prolonged.

The invention relates to a photographing device which comprises a bottom plate with scale labels on the periphery, two supplementary lamps, a camera support with adjustable height and a camera. The color and the size of the bottom plate can be determined according to the type of tested crops. The supplementary lamps have a light supplement effect. After camera height is fixed according to the tested crops, proper focal length is obtained by adjusting, the camera support and the focal length are not adjusted any longer, at the time, crop pictures taken at one stage are in order, and visual grasping and comparing on parents or hybridized combination during scientific research and breeding processes are achieved. The problem that pictures are not in order during a photographing process of crop testing is avoided.

The invention provides a dynamic recognition-based shadowboxing training method and system, and relates to the technical field of video processing. The shadowboxing training method based on dynamic recognition comprises the following steps: acquiring real-time human body motion image data through image acquisition equipment, and creating a forwarding data packet for the acquired human body motion image data; based on a skeleton node recognition algorithm, recognizing a skeleton node image corresponding to the target user contained in the human body motion image data, and analyzing and calculating skeleton key point data of a motion state; and acquiring standard skeleton key point data as a key skeleton node image model, outputting key skeleton node images in sequence, and comparing the key skeleton node images with real-time human body motion image data acquired by the image acquisition equipment to judge whether the target user completes a standard action sequence or not. When the user performs action learning, the difficulty is reduced, the interestingness is increased, the enthusiasm is enhanced, and the practice effect is improved.

The present invention is a method capable of judging the measurement error stability of a single-phase smart electric energy meter at the installation site. In the EEPROM of the electric energy meter, the factory error data curve of the meter is formed, and then the whole second judgment is inserted in the main loop of the single-phase smart electric energy meter software, the display button is pressed for > 5 seconds, the display error symbol = 1, and the error display symbol is 1 Judgment, read the current real-time power of the metering chip, according to the current real-time power, average the error data of two adjacent test points before and after to display the ideal error data, the error display timing is greater than 240 seconds to judge, display error sign = 0, return to normal main loop. It can not only meet the requirements of measurement accuracy, but also save operating costs, save labor and time, and has the advantages of being simple and applicable, fast and accurate.

The invention relates to the technical field of cable equipment detection, in particular to a partial discharge on-line monitoring and diagnosis method, which comprises the following steps: step 1, data acquisition, step 2, monitoring system establishment, step 3, detection and diagnosis, step 4, risk classification, step 5, risk tracking and step 6, risk control. According to the invention, through an electromagnetic field sensing module, a noise sensing module, a temperature sensing module, a humidity sensing module and a dust sensing module, the surrounding environment can be conveniently detected, the equipment can be conveniently protected in advance according to the measured data, and the influence of the environment on a discharge signal can be conveniently analyzed; and the accuracy of discharge signal detection is improved by recording the surrounding environment and conveniently comparing the recorded surrounding electromagnetic data, the discharge diagnosis result is more intuitively compared through the discharge accumulation comparison diagram and the similar characteristic pulse comparison diagram, the high-voltage cable edge defect condition is judged, and the detection and diagnosis effect is improved.

The invention discloses a method and system for evaluating classroom attention, comprising: S1. Performing head posture detection on a frame-by-frame basis of a collected classroom video of a class, and obtaining the position frame and head posture of students in each frame of images; Obtain the number of students in each frame of images, and record the mode of the number of students in each frame of images as the total number of students; S2. Based on the head posture of the students in each frame of images and the total number of students, calculate the positive head-up rate and activity of the class. Index; among them, the positive head-up rate is the average of the ratio of the number of students whose head posture is a positive head-up to the total number of students; the activity index is the average of the frequency of the students' head posture from non-positive head-up to head-up posture; S3. Calculate The product of the positive head-up rate for the class and the activity index yields the attention estimate for the class. The invention designs an activity index used to describe the active state of the classroom, and the activity index and the head-up rate complement each other to assess the attention in the classroom, so that the assessment result is more accurate.

The invention provides a handwriting color graph characterization method based on an electronic signature, which comprises the following steps: receiving electronic handwriting data corresponding to a target electronic signature, the electronic handwriting data comprising position coordinate data; importing the position coordinate data into a preset two-dimensional coordinate axis to obtain an electronic signature pen mark image corresponding to the target electronic signature; extracting pen wielding direction features corresponding to handwriting in the electronic signature pen mark image according to preset eight-direction SOBEL operator templates, and assigning preset colors corresponding to the SOBEL operator templates in all directions to the corresponding pen wielding direction features to obtain a pen wielding direction color graph corresponding to the target electronic signature. According to the handwriting color graph characterization method based on the electronic signature, the pen wielding direction, the pen wielding speed, the pen force change and the color are combined to obtain the pen wielding direction color graph and the speed change color graph corresponding to the target electronic signature feature, so that the electronic signature can be compared more visually; and the identification accuracy of the electronic signature is improved.

The present invention provides a building quality prediction method, device and storage medium based on deep learning, including: acquiring quality data of multiple dimensions, and the quality data of each dimension respectively includes corresponding quality evaluation scores, dimension information and building type information; The dimension weight values ​​of different dimension information are determined based on the building type information, and the quality data of multiple dimensions of the same building have the same building type information; the variable values ​​in the first deep learning model are filtered according to the multiple dimension information to obtain the second a deep learning model, where variables in the second deep learning model correspond to quality data of multiple dimensions; and a third deep learning model is obtained by adjusting variable weights of variable values ​​in the second deep learning model based on the quality data of multiple dimensions; A plurality of quality evaluation scores and dimension weight values ​​are input into the third deep learning model to obtain building quality prediction results, accuracy prediction results and comprehensive results.

Methods and systems for collecting high definition images of spent firearm cartridges under different illumination conditions described herein. Features indicative of firing pin impact with each spent firearm cartridge are extracted and compared to features extracted from different spent firearm cartridges. The likelihood that the cartridges were fired from the same firearm is determined based on the differences between the extracted features. A cartridge fixture locates a spent firearm cartridge inside an imaging chamber illuminated by different combinations of illumination devices located in different locations with respect to the spent firearm cartridge. Collected images are filtered by a trained image feature filter to extract features indicative of a firing pin strike. Features extracted from different spent firearm cartridges are compared to determine the likelihood that the spent firearm cartridges were fired from the same firearm based on one or more error metrics characterizing feature differences.

The invention relates to a method for managing device setting information, wherein said method comprises that: presetting setting mark of setting information type, when user uses client to manage thedevice setting information, the client obtains setting mark and operation mark, and one or more marks of manage targets to be sent to server; the server operates setting information relative to the manage target and setting mark. The invention can manage and maintain the setting information of one or more devices, to improve working efficiency.

The invention discloses a method of converting EDA (Electronic Document Authorization) files to ATE (Automatic Test Equipment) machine station format files. The method comprises the following steps of: processing (E) VCD (Video Compact Disc) format files in the EDA files by using a series of processing steps to produce WGL (Wingate License File) format files; and secondly converting the WGL format files and STIL (Standard Test Interface Language) format files in the EDA files to the ATE machine station format files by using a series of processing steps. According to the method disclosed by the invention, a special file processing technology is adopted, so that the conversion time is greatly reduced, wherein the WGL conversion time is about one third of a foreign product, so that a blank space of the field of national semiconductor testing is filled, and a new selection is supplied for enterprises needing the technical scheme of the invention, such as design companies and ATE manufacturers.

Methods and systems for collecting high definition images of spent firearm cartridges under different illumination conditions described herein. Features indicative of firing pin impact with each spent firearm cartridge are extracted and compared to features extracted from different spent firearm cartridges. The likelihood that the cartridges were fired from the same firearm is determined based on the differences between the extracted features. A cartridge fixture locates a spent firearm cartridge inside an imaging chamber illuminated by different combinations of illumination devices located in different locations with respect to the spent firearm cartridge. Collected images are filtered by a trained image feature filter to extract features indicative of a firing pin strike. Features extracted from different spent firearm cartridges are compared to determine the likelihood that the spent firearm cartridges were fired from the same firearm based on one or more error metrics characterizing feature differences.