Qualcomm Incorporated

Ruowei Wang

Yin Huang

Xiaoyi Zhu

Liang Zhang

Jiangtao Ren

Kyu Woong Hwang

Haijun Zhao

Leslie Chiming Chan

Mingu Lee

Janghoon Cho

Wonil Chang

Yeonseok Kim

Certain aspects of the present disclosure are generally directed to apparatus and techniques for event state detection. One example method generally includes receiving a plurality of sensor signals at a computing device, determining, at the computing device, probabilities of sub-event states based on the plurality of sensor signals using an artificial neural network for each of a plurality of time intervals, and detecting, at the computing device, the event state based on the probabilities of the sub-event states via a state sequence model.

Vehicle entry detection

Embodiments include devices and methods for processing an image captured by an image sensor of a robotic vehicle. A processor of the robotic vehicle may calculate an image output orientation matrix for an image that is output by the image sensor. The processor may calculate image sensor orientation matrix the image sensor. The processor may calculate a body orientation matrix of the robotic vehicle. The processor may transform the image captured by the image sensor based on the image output orientation matrix, the image sensor orientation matrix, and the body orientation matrix.

Image output adjustment in a robotic vehicle

Embodiments include devices and methods for processing an image captured by an image sensor of an unmanned autonomous vehicle (UAV). A processor of the UAV may determine a body coordinate matrix of the UAV. The processor may determine an estimated rotation of the image sensor of the UAV. The processor may determine an estimated rotation of the UAV. The processor may transform an image captured by the image sensor based on the body coordinate matrix, the estimated rotation of the image sensor, and the estimated rotation of the UAV.

Image processing in an unmanned autonomous vehicle

Embodiments include devices and methods for adaptive image processing in an unmanned autonomous vehicle (UAV). In various embodiments, an image sensor may capture an image, while a processor of the UAV obtains attitude information from one or more attitude sensors. Such information may include the relative attitude of the UAV and changes in attitude. The processor of the UAV may determine a UAV motion mode based, at least in part, on the obtained attitude information. The UAV motion mode may result in the modification of yaw correction parameters. The processor of the UAV may further execute yaw filtering on the image based, at least in part, on the determined motion mode.

Adaptive motion filtering in an unmanned autonomous vehicle

Growing community of inventors

Beijing, China

Ruowei Wang