Beijing Didi Infinity Technology and Development Co., Ltd.

Panasonic Intellectual Property Corporation of America

Haifeng Shen

Long Ma

Yuan Zhao

Bingqi Zhang

Xiubao Zhang

Yukun Ge

Embodiments of the disclosure provide a method for detecting an inter-person conflict. The method includes receiving at least one image from an image data resource, where the at least one image is captured by at least one camera. The method further includes detecting human objects from the at least one image. The method additionally includes determining a distance between two of the detected human objects. The method additionally includes determining whether there is a conflict between the two of the detected human objects based on the determined distance.

System and method for detecting in-vehicle conflicts

The present disclosure relates to a system and a method for distinguishing a driver and passengers in an image captured inside a vehicle. The system may perform the method to: obtain a face set from the image, the face set including at least one human face inside the vehicle and coordinates of the at least one human face; obtain a candidate driver face set from the face set based on the coordinates of the at least one human face, the candidate driver face set including at least one candidate driver face and coordinates of the at least one candidate driver face; and identify a target driver face from the at least one candidate driver face based on the coordinates of the at least one candidate driver face.

Systems and methods for distinguishing a driver and passengers in an image captured inside a vehicle

Embodiments of the disclosure provide a system for detecting a conflict in a vehicle. The system includes at least one camera, which is configured to capture a plurality of images in the vehicle. The system further includes a controller in communication with the at least one camera. The controller is configured to detect human objects from the plurality of images, estimate depth information of the respective human objects, and detect the conflict based on the depth information.

A modeling device comprises a front end which receives enrollment speech data from each target speaker, a reference anchor set generation unit which generates a reference anchor set using the enrollment speech data based on an anchor space, and a voice print generation unit which generates voice prints based on the reference anchor set and the enrollment speech data. By taking the enrollment speech and speaker adaptation technique into account, anchor models with a smaller size can be generated, so reliable and robust speaker recognition with a smaller size reference anchor set is possible.

Modeling device and method for speaker recognition, and speaker recognition system

A device and method for pass-phrase modeling for speaker verification and a speaker verification system are provided. The device comprises a front end which receives enrollment speech from a target speaker, and a template generation unit which generates a pass-phrase template with a general speaker model based on the enrollment speech. With the device, method and system of the present disclosure, by taking the rich variations contained in a general speaker model into account, the robust pass-phrase modeling is ensured even the enrollment data is insufficient, even just one pass-phrase is available from a target speaker.

Growing community of inventors

Beijing, China

Haifeng Shen