University of California

Mohan M Trivedi

Ravi Kumar Satzoda

Akshay Rangesh

Nachiket Deo

Sujitha Martin

Kohsia S Huang

Kevan Yuen

A surround multi-object tracking and surround vehicle motion prediction framework is provided. A full-surround camera array and LiDAR sensor based approach provides for multi-object tracking for autonomous vehicles. The multi-object tracking incorporates a fusion scheme to handle object proposals from the different sensors within the calibrated camera array. A motion prediction framework leverages the instantaneous motion of vehicles, an understanding of motion patterns of freeway traffic, and the effect of inter-vehicle interactions. The motion prediction framework incorporates probabilistic modeling of surround vehicle trajectories. Additionally, subcategorizing trajectories based on maneuver classes leads to better modeling of motion patterns. A model takes into account interactions between surround vehicles for simultaneously predicting each of their motion.

Surround vehicle tracking and motion prediction

A method for machine learning based driver assistance is provided. The method may include detecting, in one or more images of a driver operating an automobile, one or more facial landmarks. The detection of the one or more facial landmarks may include applying, to the one or more images, a first machine learning model. A gaze dynamics of the driver may be determined based at least on the one or more facial landmarks. The gaze dynamics of the driver may include a change in a gaze zone of the driver from a first gaze zone to a second gaze zone. A state of the driver may be determined based at least on the gaze dynamics of the driver. An operation of the automobile may be controlled based at least on the state of the driver. Related systems and articles of manufacture, including computer program products, are also provided.

Machine learning based driver assistance

Detecting the presence of target vehicles in front of a host vehicle by obtaining, using one or more visual sensors, an image of a field of view in front of a host vehicle and detecting, individually, a plurality of parts of one or more target vehicles in the obtained image. The detected plurality of parts, of the one or more target vehicles, are extracted from the obtained image and paired to form a complete target vehicle from the plurality of parts. The pairing is only performed on selective individual parts that overlap and have similar sizes indicating that they belong to the same target vehicle. A complete target vehicle is detected in response to forming a substantially complete target vehicle.

Multiple-parts based vehicle detection integrated with lane detection for improved computational efficiency and robustness

A driver assistance system including at least a first camera. The first camera can be configured to obtain image data of a region external to the host vehicle. Lane detection analysis can be performed on the image data to identify a region of interest in the image data. The region of interest can be divided into portions. Each portion can be analyzed to determine whether it includes the characteristics of an under-vehicle region. When an under-vehicle region is detected a portion of the image adjacent an under-vehicle region can be analyzed to determine whether it includes an image of another vehicle. A distance between the another vehicle and the host vehicle can be determined using the image data. A threat analysis can be performed to provide a level of threat posed by the another vehicle to the host vehicle.

Embedded surround vision-based driver assistance for safe zone estimation

Digital video imaging systems and techniques for efficiently transforming warped video images into rectilinear video images, real-time tracking of persons and objects, face recognition of persons, monitoring and tracking head pose of a person and associated perspective view of the person.

Growing community of inventors

San Diego, CA, United States of America

Mohan M Trivedi