Vehicle perception by adjusting deep neural network confidence valves based on k-means clustering
US12198440B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 25, 2022 |
| Grant date | Jan 14, 2025 |
| Priority date | — |
| Expiry date | Jul 25, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Vehicle perception techniques include obtaining a training dataset represented by N training histograms, in an image feature space, corresponding to N training images, K-means clustering the N training histograms to determine K clusters with respective K respective cluster centers, wherein K and N are integers greater than or equal to one and K is less than or equal to N, comparing the N training histograms to their respective K cluster centers to determine maximum in-class distances for each of K clusters, applying a deep neural network (DNN) to input images of the set of inputs to output detected/classified objects with respective confidence scores, obtaining adjusted confidence scores by adjusting the confidence scores output by the DNN based on distance ratios of (i) minimal distances of input histograms representing the input images to the K cluster centers and (ii) the respective maximum in-class.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.