An obstacle detection apparatus incudes an operation control portion configured to control operation of a movable portion, a first obtaining portion configured to obtain captured image data from an imager provided at the movable portion, the captured image data including first captured image data when the movable portion is in a first state and second captured image data when the movable portion is in a second state, a second obtaining portion configured to obtain moving amount information of the movable portion, an imager position calculation portion configured to calculate imager position information including a position of the imager when the movable portion is in the first state and a position of the imager when the movable portion is in the second state, and an obstacle position calculation portion configured to calculate a three-dimensional position of an obstacle included in the first captured image data and the second captured image data.

There is provided a mobile robot that performs the obstacle avoidance and visual simultaneous localization and mapping (VSLAM) according to image frames captured by the same optical sensor. The mobile robot includes a pixel array and a processor. An upper part of the pixel array is not coated with any filter and a lower part of the pixel array is coated with an IR filter. The processor performs range estimation using pixel data corresponding to the lower part of the pixel array, and perform the VSLAM using pixel data corresponding to the upper part of the pixel array.

A vehicle, system and method of detecting an object. The system includes an image network, a radar network and a head. The image network receives image data and proposes a boundary box from the image data and an object proposal. The radar network receives radar data and the boundary box and generates a fused set of data including the radar data and the image data. The head determines a parameter of the object from the object proposal and the fused set of data.

There is provided a moving robot including a light projector, an image sensor and a processing unit. The light projector projects a vertical light segment and a horizontal light segment toward a moving direction. The image sensor captures, toward the moving direction, an image frame containing a first light segment image associated with the vertical light segment and a second light segment image associated with the horizontal light segment. The processing unit recognizes a plush carpet in the moving direction when a vibration intensity of the second light segment image is higher than a predetermined threshold, and an obstacle height calculated according to the first light segment image is larger than a height threshold.

A method, apparatus, and system for filtering obstacle candidates determined based on outputs of a LIDAR device in an autonomous vehicle is disclosed. A point cloud comprising a plurality of points is generated based on outputs of the LIDAR device. One or more obstacle candidates are determined based on the point cloud. The one or more obstacle candidates are filtered to remove a first set of obstacle candidates in the one or more obstacle candidates that correspond to noise based at least in part on characteristics associated with points that correspond to each of the one or more obstacle candidates. One or more recognized obstacles comprising the obstacle candidates that have not been removed are determined. Operations of an autonomous vehicle are controlled based on the recognized obstacles.

Systems and methods are described, including a system (100) for automatically ascertaining a height characteristic of a contaminant (104) on a travel surface (102). The system (100) comprises an illumination and imaging device (106). At a first time, when the travel surface (102) is generally free of contaminant, the illumination and imaging device (106) illuminates the travel surface (102) with at least one light beam (119), and images at least one impingement of the at least one light beam (119). At a second time, when the travel surface (102) is covered by a layer of contaminant (104), the illumination and imaging device (106) illuminates the travel surface with a light beam (132), and images an impingement of the light beam on an impingement surface (107). In response to the imaging, a computer (130) calculates the height characteristic of the contaminant. Other embodiments are also described.

A method for training a machine learning system, in which image data are fed into a machine learning system with processing of at least a part of the image data by the machine learning system. The method includes synthetic generation of at least a part of at least one depth map that includes a plurality of depth information values. The at least one depth map is fed into the machine learning system with processing of at least a part of the depth information values of the at least one depth map. The machine learning system is then trained based on the processed image data and based on the processed depth information values of the at least one depth map, with adaptation of a parameter value of at least one parameter of the machine learning system, the adapted parameter value influencing an interpretation of input data by the machine learning system.

A method displays information graphically on an image captured by a vehicular optical system. The method includes capturing the image and identifying an object in the image. The method the assigns a priority level to the object based on a predetermined criterion. The object is altered based on its priority level to create an altered object. An altered object may have a changed color, a colored halo surrounding it, or a colored object inside it. Other possible ways to alter the way the object looks are possible. The altered object is displayed in the image in place of the object on a mobile device to alert a person of its presence and the priority level associated therewith.

A driving assistance device includes: a line-of-sight direction detection unit that detects a direction of a line of sight of a driver of a moving body; an obstacle detection unit that detects a position of an obstacle in environs of the moving body; an assessment criteria determination unit that determines assessment criteria of a look at the obstacle by the driver based on at least one of time, location, weather, a state of the moving body, and a state of the driver; and a warning processing unit that obtains an assessment result by applying, to the assessment criteria, a score computed based on the direction of the line of sight of the driver and the position of the obstacle, the warning processing unit determining at least one of whether or not a warning needs to be issued to the driver and a level of the warning, based on the assessment result.

The present invention improves the accuracy of predicting rarely occurring behavior of moving bodies, without reducing the accuracy of predicting commonly occurring behavior of moving bodies. A vehicle 101 is provided with a moving body behavior prediction device 10. The moving body behavior prediction device 10 is provided with a first behavior prediction unit 203 and a second behavior prediction unit 207. The first behavior prediction unit 203 learns first predicted behavior 204 so as to minimize the error between behavior prediction results for moving bodies and behavior recognition results for the moving bodies after a prediction time has elapsed. The second behavior prediction unit 207 learns future second predicted behavior 208 of the moving bodies around the vehicle 101 so that the vehicle 101 does not drive in an unsafe manner.