Shanghai Sensetime Intelligent Technology Co., Ltd

Chendi Yu

Ke Zhao Li

Cheng Yi Huang

Ke Li

Renbo Qin

De Meng

Wenzhi Liu

Haibo Zhu

Chengming Yi

Tianyuan Du

Guanhua Liang

Yadi Yang

Han Huang

Yang Wei

Guangliang Cheng

The present disclosure relates to methods and apparatuses for dynamic action detection and dynamic action control. A dynamic action detection method includes: adding an image frame in a video stream into a first queue, to obtain the first queue with a partially updated image frame; detecting a dynamic action in the partially updated image frame; and in response to the dynamic action not matching with the action detection result, updating an action detection result according to the dynamic action, the action detection result including an action reference result or a previously detected action detection result. A dynamic action detection in the present disclosure is executed according to the partially updated image frame in the first queue, so that the dynamic action can be detected more timely; and the dynamic action can also be rapidly determined, so that the action detection result is more accurate and the detection efficiency is higher.

Dynamic motion detection method and apparatus, and storage medium

A passenger state analysis method and apparatus, a vehicle, an electronic device and a storage medium. The method includes: obtaining a video stream of a rear seat area in a vehicle; performing face and/or body detection on at least one image frame in the video stream; determining state information of a passenger in the rear seat area according to a face and/or body detection result; and in response to the fact that the state information of the passenger satisfies a predetermined condition, outputting prompt information to a driver area or a specified device in the vehicle.

Passenger state analysis method and apparatus, vehicle, electronic device and storage medium

Vehicle door unlocking control methods, apparatuses, and systems for vehicles. The vehicle door unlocking control method can be carried out by the apparatuses and systems and includes: obtaining an acquisition trigger signal; controlling, based on the acquisition trigger signal, a first camera assembly disposed on a vehicle to acquire a first face image of a user; performing feature matching between the first face image and a pre-stored second face image; performing living body detection on the first face image; and sending a vehicle door unlocking instruction to at least one vehicle door lock of the vehicle in response to successful feature matching and successful living body detection. This door unlocking solution may be used to provide face-based vehicle door opening in a safe, convenient and reliable manner.

Vehicles, vehicle door unlocking control methods and apparatuses, and vehicle door unlocking systems

Embodiments of the present disclosure disclose a lane line-based intelligent driving control method and apparatus, and an electronic device. The method includes: obtaining a lane line detection result of a vehicle traveling environment; determining, according to a traveling state of the vehicle and the lane line detection result, an estimated distance of traveling out of the lane line by the vehicle and/or estimated time of traveling out of the lane line by the vehicle; and performing intelligent driving control on the vehicle according to the estimated distance and/or the estimated time. The embodiments of the present disclosure implement lane line-based intelligent control on the vehicle traveling state, thereby helping to improve the driving safety.

Lane line-based intelligent driving control method and apparatus, and electronic device

A vehicle control method and system includes: acquiring a face image of a user currently requesting to use a vehicle; acquiring a feature matching result between the face image and at least one pre-stored face image in a data set of the vehicle, where the data set stores pre-stored face images of at least one pre-recorded user allowed to use the vehicle; and if the feature matching result indicates that the feature matching is successful, controlling actions of the vehicle to allow the user to use the vehicle. The rights of pre-recorded personnel can be guaranteed based on feature matching, and feature matching can be achieved without a network, thereby overcoming the dependency on the network and further improving the safety guarantee of the vehicle.

Vehicle control method and system, vehicle-mounted intelligent system, electronic device, and medium

Embodiments of the present disclosure disclose driving management methods and systems, vehicle-mounted intelligent systems, electronic devices, and medium. The method includes: controlling a camera assembly provided on a vehicle to collect a video stream of a vehicle driver; obtaining a feature matching result of a face part of at least one image in the video stream and at least one pre-stored face image in a data set, where the data set stores a pre-stored face image of at least one registered driver; and if the feature matching result represents that the feature matching is successful, controlling the vehicle to execute an operation instruction received by the vehicle. The embodiments of the present disclosure reduce the dependence of the driver identification on a network, can realize feature matching without the network, and further improve the safety guarantee of the vehicle.

Growing community of inventors

Shanghai, China

Chendi Yu