Here Global B.v.

Peter Christian

Anirudh Viswanathan

Anish Mittal

David Johnston Lawlor

Zhanwei Chen

An approach is provided for location correction using feature point correspondences between images or image sources. The approach, for example, involves processing a first image and a second image to identify a feature that is visible in both the first image and the second image. The first image has an image-to-ground correspondence between the feature in the first image and a geographic location. The approach also involves transferring the image-to-ground correspondence from the first image to the second image. The approach further involves using the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location.

Method, apparatus, and system for location correction based on feature point correspondence

A method is provided for establishing a location of a device based on a global navigation satellite system. Methods may include: receiving sensor data of an environment of the apparatus; estimating object location within the environment based on the sensor data; receiving a static elevation mask; generating a learned-elevation mask based, at least in part, on the static elevation mask and the estimated object location within the environment; receiving signals from a plurality of Global Navigation Satellite System (GNSS) satellites; filtering the signals from the plurality of GNSS satellites to eliminate from consideration a subset of satellites established as not having a line-of-sight with the apparatus; establishing a location of the apparatus from remaining satellites established as having a line-of-sight with the apparatus; and providing for at least one of route guidance or autonomous vehicle control based on the established location of the apparatus.

Method, apparatus, and computer program product for establishing location

An image and/or temporal sequence of images is received. The image and/or sequence of images was captured by an image capturing device of an apparatus and was down-sampled thereby. A scale of the image(s) is determined. An up-sampling network receives the image(s) and the scale. The up-sampling network determines appropriate network weights based on the scale. Based on the appropriate network weights, the up-sampling network generates a higher resolution image having a pre-defined scale.

Deep convolutional image up-sampling

An image and/or temporal sequence of images is received. The image and/or sequence of images was captured by an image capturing device of a vehicle apparatus onboard a vehicle and was down-sampled thereby. A scale of the image(s) is determined. An up-sampling network receives the image(s) and the scale. The up-sampling network determines appropriate network weights based on the scale. Based on the appropriate network weights, the up-sampling network generates a higher resolution image having a pre-defined scale.

Growing community of inventors

Berkeley, CA, United States of America

Peter Christian