Koito Manufacturing Company, Ltd.

Brightway Vision Ltd.

Toru Nagashima

Shuki Yamamoto

Misako Kamiya

Shunsuke Okamura

Jun Kano

Koji Itaba

Kensuke Arai

An object identification system includes a camera and a processing device. The processing device includes a classifier subjected to machine learning based on the output image of the camera so as to allow it to identify an object. A gating camera divides a field of view in the depth direction into multiple ranges, and captures an image while changing the time difference between light projection and exposure for each range. The classifier is subjected to machine learning using multiple images IMGthrough IMGgenerated by the gating camera as the learning data.

Object identification system

A first light emitting element emits first detecting light toward the outside of a vehicle. A second light emitting element emits second detecting light toward the outside of the vehicle. A first light receiving element outputs a first signal corresponding to an amount of incident light. A second light receiving element outputs a second signal corresponding to an amount of incident light. A processor acquires first data corresponding to the first signal and second data corresponding to the second signal, and exchanges the first data and the second data in a case where the first data is based on the second detecting light and the second data is based on the first detecting light.

Sensor system

A sensing system provided in a vehicle capable of running in an autonomous driving mode, includes: a LiDAR unit configured to acquire point group data indicating surrounding environment of the vehicle; and a LiDAR control module configured to identify information associated with a target object existing around the vehicle, based on the point group data acquired from the LiDAR unit. The LiDAR control module is configured to control the LiDAR unit so as to increase a scanning resolution of the LiDAR unit in a first angular area in a detection area of the LiDAR unit, wherein the first angular area is an area where the target object exists.

Sensing system and vehicle

A three-dimensional sensor generates multiple items of line data with respect to multiple horizontal lines arranged at different heights. Multiple first neural networks each generate first intermediate data relating to a corresponding item from among the multiple items of line data. Each first intermediate data indicates the probability of matching between the corresponding line data and each of multiple portions of multiple kinds. A combining processing unit receives the multiple items of first intermediate data, and combines the first intermediate data thus received so as to generate at least one item of second intermediate data. A second neural network receives the at least one item of second intermediate data, and generates final data that indicates the probability of matching between the object and each of the multiple kinds.

A recognition sensor includes a three-dimensional sensor and a controller. The three-dimensional sensor scans a scan beam in the horizontal direction, and measures the distance up to each of multiple measurement points defined on a scan line. The controller corrects the elevation angle of the three-dimensional sensor such that the height of a correction point, which is selected from among the multiple measurement points, approaches a predetermined value.

Growing community of inventors

Shizuoka, Japan

Toru Nagashima