An optical navigation system comprising a camera oriented to face towards a plurality of markers located at spaced apart locations from the camera, calculating means adapted to calculate an angle subtended between pairs of markers, the subtended angles being calculated by monitoring the pixel locations of the markers in a series of images captured by the camera, the optical navigation system additionally comprising means for creating a three-dimensional model whereby the location of the camera relative to the markers is determined by triangulating the subtended angles in the three-dimensional model.

A depth map generation unit (15) generates a depth map through a matching process using a first image generated by a first imaging unit which has a pixel configuration including pixels having different polarization directions and a second image generated by a second imaging unit which has a different pixel configuration from the pixel configuration of the first imaging unit. A normal-line map generation unit (17) generates a normal-line map based on a polarization state of a polarized image of at least one of the first and second images. A map unifying unit (19) performs a process of unifying the generated depth map and the generated normal-line map and acquires an image in which the number of pixels is not reduced while generating the depth map with precision equal to or greater than the generated depth map. The image in which the number of pixels is not reduced can be acquired while generating the highly precise depth map.

A display control unit causes a display unit to display an image and designation point information. The designation point information indicates whether or not a position of at least one designation point included in a plurality of designation points is suitable for measurement of a subject. After position information of the at least one designation point is input to an input device, the display control unit causes the display unit to display the designation point information in only a period except a non-display period. The non-display period includes at least a portion of a period from a first timing to a second timing. The first timing is a timing at which the position information of a first designation point is input to the input device. The second timing is a timing at which the position information of a second designation point is input to the input device.

A display control unit causes a display unit to display an image and designation point information. The designation point information indicates whether or not a position of at least one designation point included in a plurality of designation points is suitable for measurement of a subject. After position information of the at least one designation point is input to an input device, the display control unit causes the display unit to display the designation point information in only a period except a non-display period. The non-display period includes at least a portion of a period from a first timing to a second timing. The first timing is a timing at which the position information of a first designation point is input to the input device. The second timing is a timing at which the position information of a second designation point is input to the input device.

A high-definition map system receives sensor data from vehicles travelling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date.

A high-definition map system receives sensor data from vehicles travelling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date.

Using one or more patterned markers inside the projector module of a three-dimensional (3D) camera to facilitate automatic calibration of the camera's depth sensing operation. The 3D camera utilizes epipolar geometry-based imaging in conjunction with laser beam point-scans in a triangulation-based approach to depth measurements. A light-sensing element and one or more reflective markers inside the projector module facilitate periodic self-calibration of camera's depth sensing operation. To calibrate the camera, the markers are point-scanned using the laser beam and the reflected light is sensed using the light-sensing element. Based on the output of the light-sensing element, the laser's turn-on delay is adjusted to perfectly align a laser light spot with the corresponding reflective marker. Using reflective markers, the exact direction and speed of the scanning beam over time can be determined as well. The marker-based automatic calibration can periodically run in the background without interfering with the normal camera operation.

Using one or more patterned markers inside the projector module of a three-dimensional (3D) camera to facilitate automatic calibration of the camera's depth sensing operation. The 3D camera utilizes epipolar geometry-based imaging in conjunction with laser beam point-scans in a triangulation-based approach to depth measurements. A light-sensing element and one or more reflective markers inside the projector module facilitate periodic self-calibration of camera's depth sensing operation. To calibrate the camera, the markers are point-scanned using the laser beam and the reflected light is sensed using the light-sensing element. Based on the output of the light-sensing element, the laser's turn-on delay is adjusted to perfectly align a laser light spot with the corresponding reflective marker. Using reflective markers, the exact direction and speed of the scanning beam over time can be determined as well. The marker-based automatic calibration can periodically run in the background without interfering with the normal camera operation.

The present technique relates to an apparatus and a method for measurement, and a program each of which enables distance estimation to be more simply carried out with higher accuracy. A three-dimensional measurement apparatus has a rotation control portion controlling rotation of a photographing portion by a rotation mechanism in such a way that the photographing portion is rotated with a center of rotation as an axis in a state in which a distance from the center of rotation of the rotation mechanism portion to a focal point position of the photographing portion is a constant distance; and a distance calculating portion calculating a distance to an object on a space on the basis of a plurality of photographed images obtained through photographing in positions different from one another by the photographing portion in a state in which the photographing portion is rotated.

The present technique relates to an apparatus and a method for measurement, and a program each of which enables distance estimation to be more simply carried out with higher accuracy. A three-dimensional measurement apparatus has a rotation control portion controlling rotation of a photographing portion by a rotation mechanism in such a way that the photographing portion is rotated with a center of rotation as an axis in a state in which a distance from the center of rotation of the rotation mechanism portion to a focal point position of the photographing portion is a constant distance; and a distance calculating portion calculating a distance to an object on a space on the basis of a plurality of photographed images obtained through photographing in positions different from one another by the photographing portion in a state in which the photographing portion is rotated.