We propose two H.264 bit rate prediction and selection applications based on features extracted for our blind video quality assessment (VQA) algorithm, Video BLIINDS. We describe the blind VQA algorithm briefly, and we show that is correlates highly with human judgments of quality. We then demonstrate two applications: an H.264 bit rate predictor and an H.264 bit rate selector.

https://hal.archives-ouvertes.fr/hal-01207875/document

Blind Prediction of Natural Video Quality and H.264 Applications

As the rapid development of big data and the artificial intelligence technology, users prefer uploading more and more local files to the cloud server to reduce the pressure of local storage, but when users upload more and more duplicate files , not only wasting the network bandwidth, but also bringing much more inconvenience to the server management, especially images and videos. To solve the problems above, we design a multi-parameter video quality assessment model based on 3D convolutional neural network in the video deduplication system, we use a method similar to analytic hierarchy process to comprehensively evaluate the impact of packet loss rate, codec, frame rate, bit rate, resolution on video quality, and build a two-stream 3D convolutional neural network from the spatial flow and timing flow to capture the details of video distortion, set the coding layer to remove redundant distortion information. Finally, the LIVE and CSIQ data sets are used for experimental verification, we compare the performance of the proposed scheme with the V-BLIINDS scheme and VIDEO scheme under different packet loss rates. We also use the part of data set to simulate the interaction process between the client and the server, then test the time cost of the scheme. On the whole, the scheme proposed in this paper has a high quality assessment efficiency.

A Multi-parameter Video Quality Assessment Model Based on 3D Convolutional Neural Network on the Cloud

The invention provides a video processing method and device, a video operation method and device, a storage medium and equipment, belongs to the technical field of computers, and relates to artificialintelligence and computer vision technologies. The method comprises the following steps: for each image frame in a target image sequence obtained from a video, obtaining position information of a target detection box used for indicating a target object in each target image frame, determining the stability of the target object in the target image sequence according to the position information of the target detection box in the target image frame, and obtaining a stable video clip according to the target image sequence of which the stability of the target object meets a set condition. Through the method, the stable video clip only containing the stable picture and the stable target can be screened out from the video, and compared with manual screening, the stability and efficiency of videoscreening can be improved.

Video processing method and device, video operation method and device, storage medium and equipment

An image processing method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining an image frame sequence, the image frame sequence comprising an image frame to be processed and one or more image frames adjacent to the image frame to be processed, and performing image alignment on the image frame to be processed and the image frames in the image frame sequence to obtain multiple pieces of alignment feature data (101); determining, on the basis of the multiple pieces of alignment feature data, multiple similarity features between the multiple pieces of alignment feature data and alignment feature data corresponding to the image frame to be processed, and determining weight information of each piece of alignment feature data in the multiple pieces of alignment feature data on the basis of the multiple similarity features (102); and fusing the multiple pieces of alignment feature data according to the weight information of each piece of alignment feature data to obtain fusion information of the image frame sequence, the fusion information being used for obtaining a processed image frame corresponding to the image frame to be processed (103). The method can improve the quality of alignment and fusion of multiple frames in image processing, and enhance the display effect of image processing.

Image processing method and apparatus, electronic device, and storage medium

The present application relates to the technical field of computer visions, and relates to a scene switching detection method and apparatus, an electronic device, and a storage medium, for use in solving the problems of the complex computing process and the low efficiency in the current scene switching detection method for a video. The method comprises: determining a target image corresponding to an original image in a video to be tested; determining, according to gray scale values of pixel points in target images respectively corresponding to two adjacent frames of original images, a reference value indicating the degree of difference between gray scale values of pixel points in two target images; and if the reference value is greater than a preset threshold, determining that the scene switching occurs to said video between the two adjacent frames of original images. In this way, the scene switching detection is carried out by calculating a reference value indicating the degree of difference between gray scale values of pixel points in two target images, and comparing the reference value with a preset threshold, which reduces the complexity of data to be acquired during scene switching detection, and thus, the detection speed and the detection efficiency of the scene switching can be improved.

Scene switching detection method and apparatus, electronic device, and storage medium

The invention relates to an image processing method and device, electronic equipment and a storage medium, and relates to the technical field of information processing According to the invention, thetarget area in the target image is detected, the attention center point of the target image is determined according to the target area, the cutting center of the cutting frame is determined accordingto the attention center point, the cutting range of the cutting frame is determined, and the target image is cut according to the cutting center and the cutting range Determining a cutting center ofthe cutting frame through the attention center point of the target image; according to the method, the interest point of the user is determined, and the target image is automatically cut in combination with the cutting range of the cutting box, so that the cut target image comprises the area needing to be reserved by the user, the user does not need to manually cut the target image any more, andthe cutting effect better meets the requirements of the user

Image processing method and device, electronic equipment and storage medium

Each part of a nonuniform distorted video (NUDV) has a unique distortion degree. When NUDV blocks are used as inputs, traditional machine-learning-based video quality assessment (VQA) methods frequently do not work effectively. Because these methods directly assign the label of the entire video to blocks, causing the unreliability of labels. We creatively propose video bag, a collection of video blocks, to deal with this unreliability. We develop a novel multiple instance learning (MIL) based model, VQA-MIL, which dynamically adjusts the weights by a block-wise attention module and enriches the features of video bags by a MI Pooling layer. Furthermore, we apply the mixup data-augmentation strategy to address the lack of human labels in common video datasets. We test our method on LIVE and CSIQ, and on a relatively large-scale dataset, named NUDV-KT, that we have collected. Results show that our method outperforms popular state-of-the-art no-reference VQA methods on NUDVs.

No-Reference Nonuniform Distorted Video Quality Assessment Based on Deep Multiple Instance Learning

The invention provides a method and device for synthesizing a video based on a video template, a terminal and a storage medium, and aims to improve the video synthesizing efficiency and optimize the user experience. The method for synthesizing the video based on the video template comprises the following steps: clustering a plurality of video materials according to a theme of the video template toobtain a set of candidate video materials matched with the theme; determining a preset number of target video materials from the set of candidate video materials; and filling the preset number of target video materials into the video template to synthesize a video.

Method and device for synthesizing video based on video template, terminal and storage medium

The invention relates to a video editing method and device, an electronic device and a computer readable storage medium. The method comprises the steps of extracting a plurality of candidate images from a target video; for each candidate image, performing evaluation analysis on the candidate image to obtain an evaluation score of the candidate image; and based on the evaluation scores of the plurality of candidate images, performing interception operation on the target video to obtain a video clip. Therefore, the video editing effect is optimized, and the user experience is improved.

Video editing method and device, electronic equipment and computer readable storage medium

The invention relates to an icon position determining method and device, electronic equipment and a computer readable storage medium. The icon position determining method comprises the following steps of: detecting a target object in the target image, determining a reference position of the target object in the target image; detecting a significant position in the target image, and obtaining a relatively critical object or a reference position where the object is located in the target image and more concerned salient positions in the target image; and finally, selecting an icon position from the candidate positions according to the reference position or the distance between the significant position and a preset candidate position, so that the icon can be prevented from shielding the reference position and the significant position, manual participation is completely not needed, and the efficiency is relatively high.

Zheng Yunfei

Papers

Image processing method and device, electronic equipment and storage medium

No-Reference Nonuniform Distorted Video Quality Assessment Based on Deep Multiple Instance Learning

Method and device for synthesizing video based on video template, terminal and storage medium

Video editing method and device, electronic equipment and computer readable storage medium

Icon position determining method and device