A stereoscopic endoscope apparatus includes: an image pickup device configured to pick up optical images for a right eye and a left eye; a similarity degree determination portion configured to receive input of an image signal for the right eye and an image signal for the left eye outputted from the image pickup device, and calculate a similarity degree between the image for the right eye and the image for the left eye; and an image signal output portion configured to switch and output a three-dimensional image signal formed of the image signal for the right eye and the image signal for the left eye and a two-dimensional image signal formed of either one of the image signal for the right eye and the image signal for the left eye, based on the similarity degree calculated by the similarity degree determination portion.

The disclosure relates to systems, methods, and devices for determining a depth map of an environment based on a monocular image. A method for determining a depth map includes receiving a plurality of images from a monocular camera forming an image sequence. The method includes determining pose vector data for two successive images of the image sequence and providing the image sequence and the pose vector data to a generative adversarial network (GAN), wherein the GAN is trained using temporal constraints to generate a depth map for each image of the image sequence. The method includes generating a reconstructed image based on a depth map received from the GAN.

The disclosure relates to systems, methods, and devices for determining a depth map of an environment based on a monocular image. A method for determining a depth map includes receiving a plurality of images from a monocular camera forming an image sequence. The method includes determining pose vector data for two successive images of the image sequence and providing the image sequence and the pose vector data to a generative adversarial network (GAN), wherein the GAN is trained using temporal constraints to generate a depth map for each image of the image sequence. The method includes generating a reconstructed image based on a depth map received from the GAN.

A method for selecting an operation mode of a mobile platform includes detecting a height grade of the mobile platform and selecting an operation mode of the mobile platform according to a result of the detecting.

There is provided an image processing apparatus which is connected to a camera head capable of imaging a left eye image and a right eye image having parallax on one screen based on light at a target site incident on an optical instrument, the apparatus including: an image processor that performs the signal processing of the left eye image and the right eye image which are imaged by the camera head; and an output controller that outputs the left eye image and the right eye image on which the signal processing is performed to a monitor, in which the image processor adjusts an extraction position of at least one of the left eye image and the right eye image in accordance with a user operation based on the left eye image and the right eye image which are displayed on the monitor.

There is provided an image processing apparatus which is connected to a camera head capable of imaging a left eye image and a right eye image having parallax on one screen based on light at a target site incident on an optical instrument, the apparatus including: an image processor that performs the signal processing of the left eye image and the right eye image which are imaged by the camera head; and an output controller that outputs the left eye image and the right eye image on which the signal processing is performed to a monitor, in which the image processor adjusts an extraction position of at least one of the left eye image and the right eye image in accordance with a user operation based on the left eye image and the right eye image which are displayed on the monitor.

A method for decoding a data stream representative of an image sequence. At least one current block of a current image in the image sequence is encoded using a predictor block of a reference image, the predictor block being identified in the reference image via location information. An information item enabling the reference image to be identified from a set of reference images is obtained. When the reference image satisfies a predetermined criterion, the location information of the predictor block is decoded using a first decoding mode, otherwise the location information of the predictor block is decoded using a second decoding mode, the first and second decoding modes including at least a different decoding parameter. The current block is then reconstructed from the predictor block.

A reconfigurable imaging apparatus, a computer-implemented method, and an imaging system are described. Generally, the apparatus includes platforms. Each platform houses one or more optical sensors. A pivotal connector is connected with at least two platforms and supports a relative movement of such platforms with respect to one another. Hence, the platforms can be arranged and switched between different arrangements based on the pivotal connector, thereby allowing a reconfiguration of the apparatus. In an example, arrangement, the optical sensors are pointed in different directions to cover different fields of views, thereby supporting monoscopic imagery. In another example arrangement, the optical sensors are pointed in substantially a same direction to cover substantially a same field of view, thereby supporting stereoscopic imagery.

A reconfigurable imaging apparatus, a computer-implemented method, and an imaging system are described. Generally, the apparatus includes platforms. Each platform houses one or more optical sensors. A pivotal connector is connected with at least two platforms and supports a relative movement of such platforms with respect to one another. Hence, the platforms can be arranged and switched between different arrangements based on the pivotal connector, thereby allowing a reconfiguration of the apparatus. In an example, arrangement, the optical sensors are pointed in different directions to cover different fields of views, thereby supporting monoscopic imagery. In another example arrangement, the optical sensors are pointed in substantially a same direction to cover substantially a same field of view, thereby supporting stereoscopic imagery.

An agricultural working machine, in particular a tractor, has at least one agricultural working unit for working a crop field including a multitude of useful plants, and a camera system which includes a 3D camera. The camera system is configured for generating with the 3D camera 3D information regarding the crop field by recording stereoscopic image pairs along two different viewing axes. The viewing axes proceed from optical centers of the 3D camera, which are connected to each other by a baseline that is inclined relative to the horizontal.