Abstract:
A three-dimensional information reconstraction device includes a corresponding point detector that detects a plurality of corresponding point pairs to which a first feature point included in a first image captured by a first image capturing device and a second feature point included in a second image captured by a second image capturing device correspond, and a three-dimensional coordinate deriver that, based on the plurality of corresponding point pairs, reconstructs three-dimensional coordinates to which the first feature point is inverse-projected.
Abstract:
A shipping assistance device which enables a delivery service operator to quickly confirm that the size of an item has been properly measured and there is no need to re-measure the size, and proceed to operations for transportation, comprises a table to place items, upper and side shooting devices for shooting images of an item on the table, a storage chamber for storing items, front-facing and upward-facing displays a printer for printing a shipping label, and a processing controller configured to measure the size of the item on the table based on shot images, determine if the item is acceptable to be put in the storage chamber based on the measured size, display a determination result on the displays, and when the item is determined acceptable, instruct the printer to print a shipping label with an acceptance signature for the item.
Abstract:
An observer simply performs operations as necessary such as confirmation as to whether or not erroneous detection is made and confirmation as to whether or not intrusion detection is normal, and the observer can efficiently execute the observation operation. An observation area is captured by at least two cameras separately disposed, a plurality of camera images are acquired, a three-dimensional measurement unit performs a three-dimensional measurement for measuring a three-dimensional position of an object in the observation area based on the camera images to generate three-dimensional information of the observation area, an intrusion detector detects an object intruding into the observation area based on a change in the three-dimensional information, and a screen generator generates a map image obtained by visualizing the three-dimensional information and a mark image indicating the object intruding into the observation area, and outputs an observation screen displaying an image selected by an input operation of a user in the camera image and the map image, and the mark image.
Abstract:
The information presentation device has an image acquisition unit, a parameter deriving unit, an abnormality detection unit, and the presentation unit. The image acquisition unit acquires a first image which is captured by a first imaging device and a second image which is captured by a second imaging device. The parameter deriving unit derives parameters for deriving three-dimensional coordinates from the first image and the second image. The abnormality detection unit determines presence or absence of an abnormality in a relative positional relationship or a relative relationship of pose between the first imaging device and the second imaging device according to the derived parameters. In a case where an abnormality is determined, the presentation unit presents warning information including an instruction that there is an abnormality.
Abstract:
An image display method includes displaying an input image having distortion on a display, receiving a plurality of points which are specified on the displayed input image in response to a user input, calculating a first processing area having a first shape according to the points specified on the displayed input image so that the first shape becomes a predetermined shape when distortion of the first processing area having the first shape is corrected, and displaying the first processing area having the first shape together with the input image on the display.
Abstract:
A method for processing an image includes receiving an input image having distortion, receiving position information input by a user on the received input image, generating a first image by correcting the input image having distortion, and translating a position on the input image having distortion indicated by the received position information into a position on the generated first image. The method further includes setting, on the generated first image, a first mask area having a predetermined shape and including the position on the generated first image translated from the position on the input image having distortion, and performing mask processing on the set first mask area on the generated first image.