6 results about "Variable bitrate" patented technology

This invention discloses a satellite image compression method under extremely low bandwidth conditions. The steps are as follows: collect a static image dataset; establish a variable bitrate image encoding / decoding network; train the encoding / decoding network; embed a generative adversarial network (GAN) at the decoder and retrain it; embed a super-resolution network after the encoder / decoder and retrain it; the user selects a region of interest (ROI), and the selected region is compressed; the decoder restores the bitstream to an image and displays it; the unselected regions are compressed; when bandwidth is sufficient, the unselected regions are transmitted, and the decoder stitches the images together; super-resolution processing is performed. This image transmission method, under extremely low bandwidth constraints, provides a superior subjective reconstruction effect compared to traditional image coding methods such as JPEG and deep learning-based image coding methods in a large number of test images.

This invention relates to a neural video compression method and system based on visual saliency, belonging to the field of computer vision technology. Addressing the problems of existing end-to-end neural video compression methods, such as uniform bitrate allocation across regions within a frame and neglect of differences in human visual perception, this invention deeply integrates a lightweight visual saliency detection network with an end-to-end video compression framework. The method includes: using a saliency detection network with MobileNetV2 as its backbone to extract multi-scale features from video frames, generating a saliency probability map, which is then concatenated with the original video frames and input into a variable bitrate conditional video encoding / decoding framework; adaptively allocating the encoding precision of each region based on the saliency probability map, allowing salient regions to receive more bitrate; and employing an adaptive mask prior entropy model for checkerboard-style step-by-step entropy encoding, combined with spatial and channel-dimensional adaptive quantization to improve encoding efficiency. The system includes a saliency detection module, a variable bitrate conditional video encoding / decoding framework module, and an adaptive mask prior entropy model module, which work together to form an end-to-end optimized video compression system. Experimental results show that, at the same bitrate, the present invention can improve human visual image quality (EW-PSNR) by about 2 dB and save about 50% bitrate at the same quality.

The application provides a distortion and perceptual code rate adaptive variable code rate depth image compression method, encoder model construction is carried out, including dividing the image to be encoded into image blocks of different granularities, extracting hierarchical features, and obtaining non-repeated hierarchical features by filtering using an image mask; hierarchical vector quantization codebooks are used to quantize the hierarchical features, discrete index representations are generated, and code stream files are encoded; decoder model construction, including decoding the code stream files into discrete index representations, recovering the hierarchical features through the hierarchical vector quantization codebooks, fusing and decoding using a hybrid conditional decoder, and generating a reconstructed image; the encoder model, the decoder model and the hierarchical vector quantization codebook are jointly trained; the input image is encoded into a code stream file through the trained encoder model, and the code stream file is decoded into a reconstructed image through the trained decoder model. The application can realize fine bit rate control and adaptive switching between perceptual and distortion optimization.

The application provides an AVS-based variable code rate control method and device, and relates to the technical field of video coding.The method comprises the following steps: determining a target bit number of an i-th image group in a video sequence; determining a scene switching factor of a previous coded frame adjacent to a to-be-coded frame in the i-th image group; adjusting a target bit number remaining before the to-be-coded frame is coded in the i-th image group based on the scene switching factor of the previous coded frame adjacent to the to-be-coded frame in the i-th image group, the target bit number of the i-th image group, a coded bit number of the previous coded frame adjacent to the to-be-coded frame, a coded bit number in the i-th image group, an actual code rate of a coded stream in the i-th image group, and a frame rate; and determining a target bit number of the to-be-coded frame in the i-th image group.The application has higher scene fitting degree, is good in adaptability to a video sequence with violent motion, frequent scene switching and complex texture, and is low in coding complexity.

The application discloses an image compression method, system and storage medium based on continuous variable code rate allocation, and the method comprises the following steps: acquiring an image to be compressed, inputting the image into a trained image continuous variable code rate image compression network, and outputting an image compression result; the image to be compressed is encoded and decoded, and the encoding end comprises the following steps: extracting an image feature value y, using a joint quantization module to perform joint quantization on the channel dimension and the spatial dimension of the image feature value y, and obtaining a quantized feature value; using an arithmetic encoder to encode the quantized feature value into bit stream data; the decoding end comprises the following steps: after the received bit stream data is decoded by an arithmetic decoder, joint dequantization is performed on the channel dimension and the spatial dimension, and a decoded image feature value y is obtained ’ ; the decoded image feature value y ’ is subjected to feature reconstruction, and a reconstructed image is obtained. The application can dynamically control the bit rate during image compression, reduce the bit error rate, and improve the quality of the compressed image.

The invention provides a storage device and a method for writing data to the storage device. A method for writing data to a storage device includes determining, by the storage device, a write amplification factor (WAF) value and a fill factor value associated with the storage device in response to a write request; obtaining, by the storage device, a current parity mode value of the storage device; determining, by the storage device, a WAF threshold and a fill factor threshold associated with the current parity mode value; determining, by the storage device, whether to change the current parity mode value to a higher parity mode value of the plurality of parity mode values based on the WAF threshold, the WAF value, the fill factor threshold, and the fill factor value; and writing, by the storage device, data to a storage area of the storage device based on a result of the determination.