公开(公告)号：US20230023164A1

公开(公告)日：2023-01-26

申请号：US17938042

申请日：2022-10-04

Applicant: PERCIPIENT.AI INC.

Inventor： Vasudev PARAMESWARAN ,  Atul KANAUJIA ,  Simon CHEN ,  Jerome BERCLAZ ,  Ivan KOVTUN ,  Alison HIGUERA ,  Vidyadayini TALAPADY ,  Derek YOUNG ,  Balan AYYAR ,  Rajendra SHAH ,  Timo PYLVANAINEN

IPC: G06N3/04 ,  G06V10/72 ,  G06V10/774 ,  G06V10/82

Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

公开(公告)号：US20240331375A1

公开(公告)日：2024-10-03

申请号：US17866389

申请日：2021-01-19

Applicant: PERCIPIENT.AI INC.

Inventor： Atul KANAUJIA ,  Ivan KOVTUN ,  Vasudev PARAMESWARAN ,  Timo PYLVAENAEINEN ,  Jerome BERCLAZ ,  Kunal KOTHARI ,  Alison HIGUERA ,  Winber XU ,  Rajendra SHAH ,  Balan AYYAR

IPC: G06V20/13 ,  G06T7/73 ,  G06V10/82

CPC classification number: G06V20/13 ,  G06T7/74 ,  G06V10/82 ,  G06V2201/08

Abstract: Systems, methods and techniques for detecting, identifying and classifying objects, including multiple classes of objects, from satellite or terrestrial imagery where the objects of interest may be of low resolution. Includes techniques, systems and methods for alerting a user to changes in the detected objects, together with a user interface that permits a user to rapidly understand the data presented while providing the ability to easily and quickly obtain more granular supporting data.