9results about How to "Automatically determine" patented technology

The invention provides a super-division method based on a graph driving program, a super-division device based on the graph driving program, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a target super-resolution parameter under the condition of determining to start image super-resolution processing based on a submission time interval of a final frame in computer equipment; based on the hardware operation information of the computer equipment, determining a target execution device used for executing image super-division processing in the computer equipment and a corresponding target super-division algorithm; the hardware operation information represents the rendering time consumption of the computer equipment, the occupation condition of a video memory and the use condition of a hardware acceleration unit; and performing image super-division processing on the submitted final frame based on the target super-division parameter, the target execution device and the target super-division algorithm to obtain a super-division frame.

The present application provides an image processing method, device and storage medium, comprising: acquiring a to-be-tested image of each to-be-tested object in a plurality of same to-be-tested objects, acquiring a definition difference value between a first target region of a first to-be-tested image and a second target region of a second to-be-tested image, acquiring a target parameter according to the definition difference value, and if the target parameter is greater than a target threshold, determining that the first target region and / or the second target region is an image blur region. The present application compares the definition difference value between the target regions at the same position in different to-be-tested images to determine the image blur region, automatically determines the image blur region, improves the identification efficiency of the image blur region, avoids image blur judgment errors caused by background color difference, improves the accuracy of image blur region determination, and the identified image blur region can be subsequently adjusted smoothly to achieve clear detection.

The invention relates to the technical field of image processing, and provides an OCT image adaptive contrast enhancement method, and the method comprises the steps: obtaining an OCT image, normalizing the OCT image to a preset gray interval, and obtaining a normalized image; according to gray level distribution statistical information of the normalized image, a target gray level upper limit value used for eliminating an overexposure area in the OCT image and a target gray level lower limit value used for eliminating a background noise area in the OCT image are determined, an enhancement function based on a Sigmoid function is constructed, and a definition domain of the enhancement function is limited by the target gray level upper limit value and the target gray level lower limit value; the output value is used for representing the enhanced pixel gray scale; and acting the enhancement function on the normalized image pixel by pixel to generate an enhanced image. According to the method, while the middle gray contrast is stretched, a smooth Sigmoid curve is adopted, a definition domain is limited in an effective signal interval, dark part noise and bright part details are protected, and therefore the enhancement effect and practicability are both considered.

The invention discloses a video generation method and device, a storage medium and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the steps: obtaining a target document which comprises information used for describing a to-be-generated target video; processing the target document through a sub-mirror generation model to obtain sub-mirror information of a plurality of video sub-mirrors; for each video sub-mirror, generating a sub-mirror image and a sub-mirror audio according to the sub-mirror information of the video sub-mirror; and generating a target video corresponding to the target document according to the sub-mirror images and the sub-mirror audios of the plurality of video sub-mirrors. Through the method and the device, the problem of low video generation efficiency due to dependence on manual generation of the video according to the document in related technologies is solved.

The application discloses a path planning method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining a to-be-transported task and road network information of a vehicle, and determining a transportation area of the to-be-transported task according to the to-be-transported task and the road network information; inputting the transportation area and the to-be-transported task into a path prediction model to obtain a plurality of predicted paths corresponding to the to-be-transported task and a plurality of confidence degrees of the predicted paths; determining a target predicted path according to the confidence degrees of the predicted paths, and associating the target predicted path with the to-be-transported task and returning to a user end. In the embodiment of the application, the to-be-transported task is analyzed through the road network information, the area of the selected path is reduced, the analysis of the data in the road network information is reduced, and the prediction accuracy is improved; the path corresponding to the to-be-transported task is predicted through the path prediction model, the target predicted path is screened out, the approval time is shortened, the transportation path is automatically determined, and the transportation efficiency is improved.

The application discloses a prompt sound statistical method, device, equipment and readable storage medium. The prompt sound statistical method comprises the following steps: obtaining square wave data corresponding to an envelope line of collected audio data; determining a time period corresponding to an a-th wave band in the square wave data; obtaining audio corresponding to the time period from the audio data to obtain a target audio segment; calculating the similarity between the target audio segment and each collected segment in the audio data; determining a first target peak point and a target threshold in a cross-correlation function; determining at least one second target peak point in the plurality of similarities; and determining the playing information of the prompt sound in the audio data according to the total number of the first target peak point and the second target peak point and the time interval between the first target peak point and the second target peak point. According to the embodiment of the application, the accuracy of determining the playing number or frequency of the prompt sound can be effectively improved, and the reliability of the test result of the device outputting the prompt sound is improved.

The application discloses a kind of continuous pelvic tilt posture under acetabular form evaluation method and system, belong to clinical evaluation technical field.Method includes: constructing pelvic three-dimensional model and femur three-dimensional model;Establish pelvic front plane anatomical reference coordinate system;Obtain the double hip axis of refined estimation;Get left and right two optimal acetabular opening planes, take the normal vector of left and right two optimal acetabular opening planes as the initial axis of corresponding side pelvic acetabulum;Construct the rigid body motion model of pelvic acetabular initial axis around the continuous rotation of double hip axis, calculate the change of acetabular axis direction under different pelvic tilt postures and corresponding acetabular anteversion angle, abduction angle;Establish acetabular abduction angle / anteversion angle curve under pelvic tilt, complete acetabular form evaluation.The application realizes the automatic calculation of acetabular space direction and accurate acetabular form evaluation, and lays a foundation for finding the most suitable patient acetabular prosthesis installation angle.

The present disclosure relates to a delay parameter determination method, a delay parameter determination device, a computer readable storage medium and an electronic device, and relates to the technical field of integrated circuits. The delay parameter determination method comprises: determining a setup time of a clock signal relative to a DQ data signal in a memory; dividing the clock signal into a plurality of clock sub-signals, and determining a target sampling delay of the plurality of clock sub-signals relative to the DQ data signal; and determining a delay parameter of the DQ data signal relative to the clock signal according to the target sampling delay and the setup time. The present disclosure provides a method for effectively sampling DQ data by clock sub-signals.

The invention provides a method for determining a line loss line of a distribution network low-voltage transformer area and related equipment, and relates to the technical field of power monitoring. The determination method comprises the following steps: acquiring a target sampling position corresponding to a target line in the low-voltage transformer area by adopting a binary search principle according to a low-voltage topological graph of the low-voltage transformer area; on the basis of the Kirchhoff's current law, according to the target current value at the target sampling position and the sum of the current values of the user electricity meters corresponding to the rear-section line at the target sampling position, whether line loss exists in the rear-section line or not is determined; if yes, taking the rear-section line as a target line, and if not, taking the front-section line at the target sampling position as the target line; and according to the re-determined target line, skipping to the step of obtaining a target sampling position corresponding to the target line in the low-voltage transformer area by adopting a binary search principle according to the low-voltage topological graph of the low-voltage transformer area until a target line loss line is obtained. According to the invention, the troubleshooting efficiency of the line loss line of the distribution network low-voltage transformer area can be greatly improved.