| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_fff83fa20b60641d896f3c13da32ae16 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30252
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20064
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4007
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4046 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T3-40 |
| filingDate |
2022-05-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1dd1df3de07e4127e2d9c36b42cbb8b0
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0f6fe9d14d893a752cf720318bf29eca
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ab9e30a46793743172883bd0495395f8
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_964103dc25076d9159e57dd8025372b4 |
| publicationDate |
2022-08-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-114862681-A |
| titleOfInvention |
Image processing method and device for reversing image |
| abstract |
The invention relates to an image processing method and device for a reversing image, comprising: performing bicubic interpolation and pre-downsampling processing on a high-resolution image corresponding to an initial reversing image; decomposing the image through two-dimensional discrete wavelet transform; The sub-images are put into the deep residual network for convolutional iterative training of image feature information, and the corresponding predicted high-resolution sub-images are obtained; the final clear image is obtained by inverse wavelet transform. The above method uses the combination of two-dimensional discrete wavelet transform and deep residual network learning to process image data, which greatly reduces the number of network layers of the training model required by the neural network, and improves the training speed as well as the imaging speed. , and meet the needs of the vehicle system for image transmission and imaging delay, the image clarity obtained by the method of the present invention is improved, which provides a better basis for subsequent algorithm calculations, and also enables the driver to obtain clearer images. Reversing video image. |
| priorityDate |
2022-05-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |