US 2020/0019799 A1 · AUTOMATED ANNOTATION TECHNIQUES

Abstract

An annotation system provides various tools for facilitating training data annotation. The annotation tools include a bidirectional annotation model that generates annotations for an image sequence based on both forward information and backward information in an image sequence. The annotation system also facilitates annotation processes by automatically suggesting annotations to the human operator based on a set of annotation predictions and locations of interactions of the human operator on the image. This way, the annotation system provides an accelerated way to generate high-quality annotations that take into account input from a human operator by using the predictions as a guide when it appears that an estimated annotation is consistent with the judgement of the human operator. The annotation system also updates annotations for an overlapping set of objects based on input from human operators.

Claims14

Dependent claims

A method of generating annotations for objects in a series of sensor images, comprising:

obtaining the sequence of sensor images from one or more sensors, the sequence of sensor images including sensor measurements that sense a surrounding environment of the one or more sensors;
generating a set of annotations that indicate locations of the objects in the sequence of sensor images, the set of annotations generated by applying a bidirectional machine-learned model to the sequence of sensor images, comprising:
generating a set of forward estimations for the sequence of sensor images by propagating a first sensor image of the sequence through the bidirectional machine-learned model in a forward direction,
generating a set of backward estimations for the sequence of sensor images by propagating a last sensor image of the sequence through the bidirectional machine-learned model in a backward direction, and
combining the set of forward estimations and the set of backward estimations to generate the set of annotations;
and
training a computer model using the annotated sequence of sensor images.

4 more elements

Dependencies are inferred from the claim text.

Automated annotation techniques

Life of this patent

Automated annotation techniques

Life of this patent

Abstract

Claims14