45 results about "Video assessment" patented technology

A frame rate is determined in accordance with the smoothness in movement of a video. An amount of change detection section extracts an amount of change based on a plurality of frame pictures included in an input video signal input as a moving picture signal from the outside and outputs an amount of change to an evaluation value calculation section. The evaluation value calculation section computes an amount of change in time between each of the frame pictures based on the amount of change and the time interval between frame pictures based on frame rate information and evaluates an evaluation value for evaluating the smoothness in movement of an input video based on the amount of change in time. The evaluation value is output to the outside as a factor for determining a frame rate.

The invention discloses a direct broadcast video assessment method and device. The method comprises the steps: obtaining the scoring information of each viewer terminal, which watches a direct broadcast video, for a target direct broadcast video; and carrying out the assessment of the rating degree of the target direct broadcast video according to the scoring information. According to the technical scheme of the invention, when the scoring information of each viewer terminal, which watches the direct broadcast video, for the target direct broadcast video is obtained, the method can carry out the assessment of the rating degree of the target direct broadcast video according to the scoring information, thereby quantifying the rating degree of the target direct broadcast video, and enabling the rating degree of the target direct broadcast video to be more accurate so as to carry out more targeted related operation based on the rating degree of the target direct broadcast video.

The invention provides a hot video evaluation method and system. The hot video evaluation method comprises the steps of recording effective watching number of times of a preheating video in a set period, wherein the preheating video is a video, the video on demand number of times of which is greater than a first set threshold in the set period, and effective watching refers to a watching behaviorcharacterized in that a duration of continuously watching the preheating video is greater than a second preset threshold; calculating a watching heat value of the preheating video according to the effective watching number of times of the preheating video; and evaluating whether the preheating video is a hot video according to the effective watching number of times and the watching heat value of the preheating video. The hot video evaluation method considers the video on demand number of times, effective watching number of times and a watching heat value of a video, so that the hot video evaluation method can reflect the actual heat level of the video more objectively, and the evaluation result of the hot video is more objective and accurate. The hot video is allocated to an edge node, notwasting storage resource of the edge node but relieving pressure of a center node of a content delivery network.

The embodiment of the invention provides a determination method and device of a video assessment set, and electronic equipment. The method comprises the following steps: acquiring a video clip interception record for a to-be-assessed video by a video platform user, wherein the video clip interception record comprises starting time and ending time of each intercepted video clip; computing the interception frequency that each unit clip at different time quantum in the to-be-assessed video is intercepted according to the starting time and the ending time of each intercepted video clip of the video clip interception record; selecting the unit clip with the interception frequency not less than a preset threshold to obtain each to-be-aggregated unit clip; aggregating various to-be-aggregated unit clips in time order according to a preset clustering algorithm, thereby obtaining various target video sequences; and determining a set formed by various target video sequences as an assessment setof the to-be-assessed video. Through the determination method provided by the embodiment of the invention, the assessment set of the video is efficiently obtained.

The invention discloses a video quality evaluation method, device and apparatus and a storage medium. The method comprises the following steps: firstly, decoding a video to obtain an image sequence and audio information, then extracting an action feature vector and a face feature vector in the image sequence, extracting an audio feature vector in the audio information, and constructing a video feature vector according to at least one of the action feature vector, the face feature vector and the audio feature vector; and finally, determining a quality score of a to-be-evaluated video accordingto the video feature vector. According to the embodiment, the quality score of the to-be-evaluated video can be determined according to at least one or more vectors of the action feature vector, the face feature vector and the audio feature vector extracted from the to-be-evaluated video, the real-time performance of video quality evaluation can be realized through the video, and the accuracy of high-quality video evaluation is improved.

The invention provides a video evaluation and recommendation system, which comprises a mode selection module, a video evaluation module, a video recommendation module, a self-made content evaluation and recommendation database and a self-made content history database. Wherein, a mode selection module is used for acquiring an evaluation mode instruction or a recommendation mode instruction issued by a user terminal; the video evaluation module is used for calling the data of the self-made content evaluation recommendation database and the standard data of the self-made content history databaseaccording to the evaluation mode instruction to evaluate the evaluation object and sending the evaluation result to the user terminal; the video recommendation module is used for calling the data of the self-made content evaluation recommendation database and the standard data of the self-made content history database according to the recommendation mode instruction, calculating and obtaining theself-made content which meets the filtering condition, and sending the filtering recommendation result to the user terminal.

Described herein is a method and system for video sequence evaluation in the presence of cross-chroma interference. When the luma and chroma components in an analog video sequence are separated, the luma component may add interference to the chroma component. This is called cross-chroma interference. In the evaluation of the video sequence, the cross-chroma interference may be interpreted as motion, noise, or other artifacts. By reducing the cross-chroma interference during the evaluation, motion and noise can be identified with greater probability. The proper identification can aid motion estimators used in video coding and motion compensated temporal filtering, and it can aid video filters that do not utilize motion compensation.

The invention discloses an objective video quality assessment method based on chromaticity co-occurrence matrix weighting. The method includes the steps that firstly, a quaternion matrix with the dimension being 8*8 is used for describing characteristics, based on the time domain and the space domain, of 8*8 image blocks in a reference image and characteristics, based on the time domain and the space domain, of 8*8 image blocks in a distortion image; then the cosine of an included angle between singular value vectors of the characteristics, based on the time domain and the space domain, of two image blocks, which correspond to each other in position, in the reference image and the distortion image is obtained, and the cosine serves as the difference degree between the two image blocks, which correspond to each other in position, in the reference image and the distortion image; objective assessment values of the image blocks in the distortion image are obtained through the difference degree and weighted values of chromaticity co-occurrence matrixes of the image blocks in the distortion image, and therefore the objective assessment value of the distortion image and the objective assessment value of distortion video are obtained. According to the method, computation complexity in the video assessment process is low, and the relevance between an objective assessment result and subjective perception can be effectively improved.

Many embodiments of the invention include systems and methods for evaluating motion from a video, the method includes identifying a target individual in a set of one or more frames in a video, analyzing the set of frames to determine a set of pose parameters, generating a 3D body mesh based on the pose parameters, identifying joint positions for the target individual in the set of frames based on the generated 3D body mesh, predicting a motion evaluation score based on the identified join positions, providing an output based on the motion evaluation score.

A system and method for virtual camera configuration and selection. For example, one embodiment of a system comprises: a decode subsystem comprising circuitry to concurrently decode a plurality of video streams captured by cameras at an event to generate decoded video streams from a perspective of corresponding virtual cameras (VCAMs); video evaluation logic to apply at least one video quality metric to determine a quality value for the decoded video streams or a subset thereof, and to rank the decoded video streams based, at least in part, on the quality values associated with the decoded video streams; preview logic to provide the decoded video streams or modified versions thereof to one or more computing devices accessible to one or more video production team members and to further provide the quality values and/or the rank generated by the video quality evaluation logic; stream selection hardware logic to select a subset of the plurality of decoded video streams based on input from the one or more video production team members; and transcoder hardware logic to transcode the subset of the plurality of decoded video streams for live transmission over a public or private network.

The invention discloses a VR video quality evaluation method, which comprises the steps of obtaining a code rate, a frame rate, a resolution and a TI of a VR video, and determining an average subjective opinion score MOS of the VR video according to the code rate, the frame rate, the resolution and the TI of the VR video, the MOS of the VR video being used for representing the quality of the VR video. The invention further discloses an evaluation device. By adopting the embodiment of the invention, the accuracy of the VR video evaluation result can be improved.

The invention discloses a mobile video QoE (Quality of Experience) evaluation method based on a self-adaption degree, which comprises the following specific steps: user priority: in order to construct the self-adaption-based QoE evaluation method, a base station can carry out resource allocation adjustment according to the QoE; the adaptation degree of wireless resource allocation and code rate selection: calculating the adaptation degree Matchn (t) of wireless resource allocation and code rate selection by using Bn, j (t) and time, j (t); in the prior art, the QoE is estimated by depending on traditional network QoS parameters, and the method combines a quantitative index of a user side with wireless resource allocation of a base station side, and carries out QoE evaluation from a self-adaptive perspective. According to the method, the priority of the radio resource demand urgency degree of the user is adopted to indicate a direction for radio resource allocation, and then the radio resource share of the user is determined through the user code rate selection and the radio resource allocation suitability degree. Through real-time measurement, positive feedback is given in time when the downloading rate of the user is matched with code rate selection, negative feedback is given in time when the downloading rate is not matched with the code rate selection, and the obtained QoE score is more accurate in video service evaluation.

The invention provides a video quality evaluation method and system, computer equipment and a storage medium, and the method comprises the steps: obtaining a video data set, and randomly dividing the video data set into a training set and a test set according to a preset proportion; inputting the training set into a preset video quality evaluation network for training to obtain a video quality evaluation model, the video quality evaluation network sequentially comprising a preprocessing module, an attention coding module and a vector regression module, smf the attention coding module comprising a plurality of space-time attention coding modules; and predicting the test set by using the video quality evaluation model to obtain a corresponding predicted video quality score. According to the method, the quality evaluation problem of the naturally distorted video is effectively solved, the long-range space-time dependence characteristic in the video sequence is efficiently captured, the training convergence speed and the video evaluation performance are improved, and the application field of the Transform architecture is expanded.

A method for video evaluation of the heart rate and/or respiratory rate of a baby, in particular under dim or nocturnal conditions, in a device comprising a video camera and a source of infrared light, the method comprising the steps of:

A1—illuminating the baby with the infrared source,

A2—capturing video images of the baby,

B1—determining the position of the baby's head by finding an ellipse forming an outline of the head,

B2—identifying an area of interest centered on a selected ellipse,

C—evaluating, by plethysmographic analysis of the area of interest, the heart rate and/or respiratory rate of the baby,

and associated system.

The invention discloses a method for realizing transcoding test evaluation by using video features. The method specifically comprises the following steps: (1) analyzing a source file, obtaining feature information through a source file feature analysis module, and realizing video length segmentation through the feature information; (2) combining just analyzed source video feature information to obtain transcoding parameters meeting requirements through a transcoding parameter collection and analysis module; (3) matching the video clips obtained in the step (1) with the transcoding parameters obtained in the step (2), and realizing quality analysis through a result obtained by transcoding of a feature clip transcoding module; and (4) after video evaluation is carried out through a transcoding output quality analysis module, if the video quality evaluation is poor, returning to the step (2), and if the video quality evaluation is good, transcoding and outputting a comparison source video, and outputting a file to realize analysis and evaluation. The beneficial effects of the invention are that the method achieves the cumulative combination of data, and achieves the final high-quality and low-code-rate effect of a video.

The invention discloses a city-level monitoring video quality evaluation method and system. The method comprises the following steps: obtaining a quality evaluation task; performing task scheduling according to the quality evaluation task and the evaluation processing time to obtain a task scheduling result; performing task allocation according to the task scheduling result and the task important factors to obtain a task allocation result; based on the task allocation result, evaluating the performance of each monitoring camera to obtain a quality evaluation detection result of the single monitoring camera; and based on the quality evaluation detection result of the single monitoring camera and the scores of the monitoring videos in other areas, performing overall evaluation on the monitoring videos in the quality evaluation task to obtain a city-level monitoring video quality evaluation result. According to the method, the to-be-processed monitoring cameras are optimally allocated, so that the monitoring video quality evaluation behavior can be quickly carried out, and the city-level monitoring video evaluation speed can be accelerated.

A method for evaluating video to ensure appropriateness for viewing by children. A video submission computer is utilized to upload unevaluated video to a video evaluation and display website installed on a server computer. The unevaluated video is then downloaded from the website to a video evaluation computer where a human being views the video for the purpose of evaluating the video for appropriateness for children. The human being will then evaluate the video to either approve the video or reject the video. If the human being cannot decide whether to approve or reject the video, in a preferred embodiment the human being may refer the decision to a supervisor or a secondary review team. If the human being approves the video, the video is transferred to an approved video database where it may be downloaded by a child for viewing. If the human being rejects the video, the video is transferred to a rejected video database.

The invention discloses a soil mass structure evolution real-time online evaluation device and method based on a driverless car. The device comprises the driverless car, a telescopic unit, a micro video image collection unit, a first signal receiver, a second signal receiver, and a remote control computer. The method comprises the steps of firstly establishing a micro video gray level image database, then establishing a corresponding relationship between substances and gray value intervals in the database, then making statistics on the number of pixels in the gray value interval representing each of the substances in a micro video gray level image, establishing the relationship between the number and a corresponding substance content and form thereof, and at last, determining actual characteristic parameters of a to-be-tested soil mass according to above relationship, thereby determining a development state of the soil mass. According to the soil mass structure evolution real-time online evaluation device and method based on the driverless car disclosed by the invention, site soil mass micro video evaluation is carried out directly, so the test precision is high; the micro video image is adopted, so that the identification on soil mass composition and evolution thereof is more accurate; and the device and the method can carry out wide-range long-term continuous real-time online monitoring on the soil mass in any region, thereby obtaining an evolution rule of the soil mass in the region.

The invention discloses a microscopic video image monitoring and assessing method of the agglomeration and discretion degree of soil particles. The method comprises the following steps: establishing a microscopic video grey scale image database, establishing a corresponding relation between every substance and the grey level interval in the database, carrying out statistics on the relation between the quantity of pixels in the grey level interval, representing all substances and the content or form of the substances in the microscopic video grey scale image, and determining the practical characteristic parameters of soil to be detected according to the relation in order to determine the agglomeration and discretion degree of soil particles. The method allows onsite microscopic video assessment of a soil sample to be directly carried out without a process from onsite soil disturbance sampling to laboratory test; the agglomeration and discretion process details of the soil particles can be tracked in real time by adopting the microscopic video image; and soil in a region can be continuously monitored in real time for a long term through the microscopic video image monitoring and assessing method of soil evolution in order to obtain the evolution rule of the soil in the region.