Tusimple, Inc.

Beijing Tusen Weilai Technology Co., Ltd.

Yijie Wang

Lingting Ge

Xiaodi Hou

Yiqian Gan

Zehua Huang

Siyuan Liu

Panqu Wang

Pengfei Chen

Chenzhe Qian

Jianan Hao

Ligeng Zhu

Techniques are described to estimate orientation of one or more cameras located on a vehicle. The orientation estimation technique can include obtaining an image from a camera located on a vehicle while the vehicle is being driven on a road, determining, from a terrain map, a location of a landmark located at a distance from a location of the vehicle on the road, determining, in the image, pixel locations of the landmark, selecting one pixel location from the determined pixel locations; and calculating values that describe an orientation of the camera using at least an intrinsic matrix and a previously known extrinsic matrix of the camera, where the intrinsic matrix is characterized based on at least the one pixel location and the location of the landmark.

Camera orientation estimation

A method includes receiving a series of road images from a side-view camera sensor of the autonomous driving vehicle. For each object from objects captured in the series of road images, a series of bounding boxes in the series of road images is generated, and a direction of travel or stationarity of the object is determined. The methods and apparatus also include determining a speed of each object for which the direction of travel has been determined and determining, based on the directions of travel, speeds, or stationarity of the objects, whether the autonomous driving vehicle can safely move in a predetermined direction. Furthermore, one or more control signals is sent to the autonomous driving vehicle to cause the autonomous driving vehicle to move or to remain stationary based on determining whether the autonomous driving vehicle can safely move in the predetermined direction.

Autonomous driving crash prevention

Devices, systems and methods for fusing scenes from real-time image feeds from on-vehicle cameras in autonomous vehicles to reduce redundancy of the information processed to enable real-time autonomous operation are described. One example of a method for improving perception in an autonomous vehicle includes receiving a plurality of cropped images, wherein each of the plurality of cropped images comprises one or more bounding boxes that correspond to one or more objects in a corresponding cropped image; identifying, based on the metadata in the plurality of cropped images, a first bounding box in a first cropped image and a second bounding box in a second cropped image, wherein the first and second bounding boxes correspond to a common object; and fusing the metadata corresponding to the common object from the first cropped image and the second cropped image to generate an output result for the common object.

Image fusion for autonomous vehicle operation

Disclosed are methods and devices related to autonomous driving. In one aspect, a method is disclosed. The method includes determining three-dimensional bounding indicators for one or more first objects in road target information captured by a light detection and ranging (LIDAR) sensor; determining camera bounding indicators for one or more second objects in road image information captured by a camera sensor; processing the road image information to generate a camera matrix; determining projected bounding indicators from the camera matrix and the three-dimensional bounding indicators; determining, from the projected bounding indicators and the camera bounding indicators, associations between the one or more first objects and the one or more second objects to generate combined target information; and applying, by the autonomous driving system, the combined target information to produce a vehicle control signal.

Data integration from multiple sensors

Image processing techniques are described to receive bounding box information that describes a bounding box located around a detected object in an image, determine one or more positions of one or more reference points on the bounding box, determine, for each reference point, 3D world coordinates of a point of intersection of the reference point and the road surface, and assign the 3D world coordinates of the one or more reference points to a location of the detected object.

Depth estimation in images obtained from an autonomous vehicle camera

Image processing techniques are described to select and crop a region of interest from an image obtained from a camera located on or in a vehicle, such as an autonomous semi-trailer truck. The region of interest can be identified by selecting one or more reference points and determining one or more positions of the one or more reference points on the image obtained from the camera. As an example, a location of two reference points may be 500 meters and 1000 meters in front of a location of autonomous vehicle, where the front of the autonomous vehicle is an area towards which the autonomous vehicle is being driven.

Partitioning images obtained from an autonomous vehicle camera

A system and method for aerial video traffic analysis are disclosed. A particular embodiment is configured to: receive a captured video image sequence from an unmanned aerial vehicle (UAV); clip the video image sequence by removing unnecessary images; stabilize the video image sequence by choosing a reference image and adjusting other images to the reference image; extract a background image of the video image sequence for vehicle segmentation; perform vehicle segmentation to identify vehicles in the video image sequence on a pixel by pixel basis; determine a centroid, heading, and rectangular shape of each identified vehicle; perform vehicle tracking to detect a same identified vehicle in multiple image frames of the video image sequence; and produce output and visualization of the video image sequence including a combination of the background image and the images of each identified vehicle.

System and method for aerial video traffic analysis

A system method for detecting taillight signals of a vehicle using a convolutional neural network is disclosed. A particular embodiment includes: receiving a plurality of images from one or more image-generating devices; generating a frame for each of the plurality of images; generating a ground truth, wherein the ground truth includes a labeled image with one of the following taillight status conditions for a right or left taillight signal of the vehicle: (1) an invisible right or left taillight signal, (2) a visible but not illuminated right or left taillight signal, and (3) a visible and illuminated right or left taillight signal; creating a first dataset including the labeled images corresponding to the plurality of images, the labeled images including one or more of the taillight status conditions of the right or left taillight signal; and creating a second dataset including at least one pair of portions of the plurality of images, wherein the at least one pair of portions of the plurality of the images are in temporal succession.

Growing community of inventors

San Diego, CA, United States of America

Yijie Wang