A method for modularizing high dimensional neural networks into neural networks of lower input dimensions. The method is suited to generating full-DOF robot grasping actions based on images of parts to be picked. In one example, a first network encodes grasp positional dimensions and a second network encodes rotational dimensions. The first network is trained to predict a position at which a grasp quality is maximized for any value of the grasp rotations. The second network is trained to identify the maximum grasp quality while searching only at the position from the first network. Thus, the two networks collectively identify an optimal grasp, while each network's searching space is reduced. Many grasp positions and rotations can be evaluated in a search quantity of the sum of the evaluated positions and rotations, rather than the product. Dimensions may be separated in any suitable fashion, including three neural networks in some applications.

Images may be captured at an image capture device mounted on an image capture device gimbal capable of rotating the image capture device around a nodal point in one or more dimensions. Each of the plurality of images may be captured from a respective rotational position. The images may be captured by a designated camera that is not located at the nodal point in one or more of the respective rotational positions. A designated three-dimensional point cloud may be determined based on the plurality of images. The designated three-dimensional point cloud may include a plurality of points each having a respective position in a virtual three-dimensional space.

In some examples, a computing apparatus may include one or more non-transitory computer-readable storage media and program instructions stored on the one or more computer-readable storage media that, when executed by one or more processors, direct the computing apparatus to perform various steps. For example, the program instructions may continually present a graphical user interface (GUI) at the computing apparatus including a display of a current view of the physical environment from a perspective of an aerial vehicle. The program instructions may detect user interactions with the GUI while the aerial vehicle is in flight. The user interactions may include instructions directing the aerial vehicle to maneuver within the physical environment and configure parameters for scanning a three-dimensional (3D) scan volume. The program instruction may then transmit, to the aerial vehicle, data encoding the instructions for performing a 3D scan of the 3D scan volume.

A system and method for generating a depth map from image data in a surgical robotic system that employs a robotic subsystem having a camera assembly with first and second cameras for generating image data. The system and method generates based on the image data a plurality of depth maps, and then converts the plurality of depth maps into a single combined depth map having distance data associated therewith. The system and method can then control the camera assembly based on the distance data in the single combined depth map.

A system to capture a plurality of two dimensional digital source images of scene by user, a smart device having a memory device for storing an instruction, a processor in communication with the memory and configured to execute the instruction, a plurality of digital image capture devices in communication with the processor and each image capture device configured to capture a digital image of the scene, the plurality of digital image capture devices positioned linearly in series within approximately an interpupillary distance, wherein a first digital image capture devices is centered proximate a first end of the interpupillary distance, a second digital image capture devices is centered on a second end of the interpupillary distance, and any remaining the plurality of digital image capture devices are evenly spaced therebetween, a display in communication with the processor, display configured to display multidimensional digital image and add audio file thereto.

The methods and systems disclosed herein improve upon previous 3D imaging techniques by making use of a longer illumination pulse to obtain the same or nearly the same range resolution as can be achieved by using a much shorter, conventional laser pulse. For example, a longer illumination pulse can be produced by one or more Q-switched lasers that produce, for example, 5, 10, 20 ns or longer pulses. In some instances, the laser pulse can be longer than the modulation waveform of a MIS-type imaging system and still produce a repeatable response function. The light pulse generation technologies required to achieve longer pulse lengths can be significantly less expensive and less complex than known technologies presently used to generate shorter illumination pulse lengths. Lower-cost, lower-complexity light pulse sources may facilitate lower-cost, commercial 3D camera products.

The methods and systems disclosed herein improve upon previous 3D imaging techniques by making use of a longer illumination pulse to obtain the same or nearly the same range resolution as can be achieved by using a much shorter, conventional laser pulse. For example, a longer illumination pulse can be produced by one or more Q-switched lasers that produce, for example, 5, 10, 20 ns or longer pulses. In some instances, the laser pulse can be longer than the modulation waveform of a MIS-type imaging system and still produce a repeatable response function. The light pulse generation technologies required to achieve longer pulse lengths can be significantly less expensive and less complex than known technologies presently used to generate shorter illumination pulse lengths. Lower-cost, lower-complexity light pulse sources may facilitate lower-cost, commercial 3D camera products.

A safe optoelectronic sensor is provided for securing a monitored zone comprising at least one machine, wherein the sensor has at least one light receiver for generating a received signal from received light from the monitored zone and a control and evaluation unit that is configured to determine distances from objects in the monitored zone from the received signal, and to treat gaps, i.e. safety relevant part regions of the monitored zone in which no reliable distance can be determined, as an object at a predefined distance. The predefined distance here corresponds to a height for securing against reach over.

A safe optoelectronic sensor is provided for securing a monitored zone comprising at least one machine, wherein the sensor has at least one light receiver for generating a received signal from received light from the monitored zone and a control and evaluation unit that is configured to determine distances from objects in the monitored zone from the received signal, and to treat gaps, i.e. safety relevant part regions of the monitored zone in which no reliable distance can be determined, as an object at a predefined distance. The predefined distance here corresponds to a height for securing against reach over.

An electronic device (100) and a method for controlling the electronic device (100) are provided. The electronic device (100) includes a time-of-flight (TOF) module 20, a color camera 30, a monochrome camera (40), and a processor (10). The TOF module (20) is configured to capture a depth image of a subject. The color camera (30) is configured to capture a color image of the subject. The monochrome camera (40) is configured to capture a monochrome image of the subject. The processor (10) is configured to obtain a current brightness of ambient light in real time, and to construct a three-dimensional image of the subject according to the depth image, the color image, and the monochrome image when the current brightness is less than a first threshold.