Back to results
US 12,755,339 B2Granted
Resolution converter, resolution conversion method, and resolution conversion computer program
AssigneeToyota Jidosha Kabushiki Kaisha
InventorEiji Nakatsugawa
Life of this patent
Estimating the term…
Abstract
A resolution converter includes a processor configured to select a super-resolution model corresponding to a capturing condition under which an image was generated, among a plurality of super-resolution models for improving resolution, the plurality of super-resolution models corresponding to different capturing conditions, and generate a high-resolution image having a higher resolution than the image by inputting the image into the selected super-resolution model.
Claims4
A resolution converter comprising:
- a memory configured to store a plurality of distributions of feature vectors corresponding to different capturing conditions, and
- a processor configured to:
- select a super-resolution model corresponding to a capturing condition under which an image was generated, among a plurality of super-resolution models for improving resolution, the plurality of super-resolution models corresponding to different capturing conditions,
- generate a high-resolution image having a higher resolution than the image by inputting the image into the selected super-resolution model, wherein the capturing condition comprises one or more of a date and time of generation of the image, a position of a vehicle at the time of generation of the image, and weather information indicating weather around the vehicle at the time of generation of the image,
- calculate a feature vector of the image,
- calculate, for each of the plurality of distributions of feature vectors, Mahalonobis distance between the feature vector and the distribution of feature vectors, and
- select a super-resolution model corresponding to a capturing condition corresponding to a distribution of feature vectors having the shortest Mahalonobis distance, among the plurality of super-resolution models, as the super-resolution model corresponding to the capturing condition under which the image was generated.
4 more elements
A resolution conversion method, comprising:
- selecting a super-resolution model corresponding to a capturing condition under which an image was generated, among a plurality of super-resolution models for improving resolution of the image, the plurality of super-resolution models corresponding to different capturing conditions;
- generating a high-resolution image having a higher resolution than the image by inputting the image into the selected super-resolution model, wherein the capturing condition comprises one or more of a date and time of generation of the image, a position of a vehicle at the time of generation of the image, and weather information indicating weather around the vehicle at the time of generation of the image;
- calculating a feature vector of the image;
- calculating, for each of the plurality of distributions of feature vectors, Mahalonobis distance between the feature vector and the distribution of feature vectors;
- and
- selecting a super-resolution model corresponding to a capturing condition corresponding to a distribution of feature vectors having the shortest Mahalonobis distance, among the plurality of super-resolution models, as the super-resolution model corresponding to the capturing condition under which the image was generated.
3 more elements
A non-transitory recording medium that stores a resolution conversion computer program, the computer program causing a computer to execute a process comprising:
- selecting a super-resolution model corresponding to a capturing condition under which an image was generated, among a plurality of super-resolution models for improving resolution of the image, the plurality of super-resolution models corresponding to different capturing conditions;
- generating a high-resolution image having a higher resolution than the image by inputting the image into the selected super-resolution model, wherein the capturing condition comprises one or more of a date and time of generation of the image, a position of a vehicle at the time of generation of the image, and weather information indicating weather around the vehicle at the time of generation of the image;
- calculating a feature vector of the image;
- calculating, for each of the plurality of distributions of feature vectors, Mahalonobis distance between the feature vector and the distribution of feature vectors;
- and
- selecting a super-resolution model corresponding to a capturing condition corresponding to a distribution of feature vectors having the shortest Mahalonobis distance, among the plurality of super-resolution models, as the super-resolution model corresponding to the capturing condition under which the image was generated.
3 more elements
Dependencies are inferred from the claim text.