Google Inc.

Mohamed Aly

Jean-Yves Bouguet

Sergey Ioffe

Charles Joseph Rosenberg

Adel Amin Youssef

Methods and systems for automatically generating pose estimates from uncalibrated unordered panoramas are provided. An exemplary method of automatically generating pose estimates includes receiving a plurality of uncalibrated and unordered panoramic images that include at least one interior building image, and extracting, for each panoramic image, feature points. The method includes generating a match matrix for all the panoramic images based on the one or more feature points, constructing a minimal spanning tree based on the match matrix, identifying a first and second panoramic image, based on the minimal spanning tree, wherein the second panoramic image is associated with the first panoramic image providing a navigation from the first panoramic image to the second panoramic image.

Automatic pose estimation from uncalibrated unordered spherical panoramas

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining image search results. One of the methods includes generating a plurality of feature vectors for each image in a collection of images, wherein each feature vector is associated with an image tile of an image, wherein each feature vector corresponds to one of a plurality of predetermined visual words. All images in the collection of images that share at least a threshold number of matching visual words associated with matching image tiles are classified as near-duplicate images.

Near duplicate images

A sensor in a network to which to route a packet is selected, where the sensor is selected independently of energy status of the sensors included in the network, and the sensor is selected by a source sensor. The packet is routed from the source sensor toward the destination sensor.

Traffic-oblivious load balancing protocol for sensor networks

A first query that is substantially similar to a second query is detected. A network of sensors includes a first sensor, a second sensor, and a data-source sensor, the first and second queries are addressed to the data-source sensor, and the first query is forwarded by the first sensor to the data-source sensor and the second query is forwarded by the second sensor to the data-source sensor. The data-source sensor provides, to the first sensor, results answering the first query. The first sensor provides the results to the second sensor.

Growing community of inventors

Pittsburgh, PA, United States of America

Mohamed Aly