Abstract: Systems and methods are described where odometry information that is obtained from a video camera mounted on an underwater vehicle is used to estimate the velocity of the underwater vehicle. The techniques described herein estimate the velocity of the underwater vehicle passively without emitting sound or other energy from the underwater vehicle.

Abstract: Systems and methods are described where odometry information that is obtained from a video camera mounted on an underwater vehicle is used to estimate the velocity of the underwater vehicle. The techniques described herein estimate the velocity of the underwater vehicle passively without emitting sound or other energy from the underwater vehicle.

Abstract: A 3D reconstruction technique using integral imaging, which does not require computing point correspondences. The technique has been demonstrated that it can effectively estimate the surface of an object, and reconstruct the surfaces of partially occluded objects. Reconstruction can be performed from either an array of imaging sensors, or a single moving imaging sensor with known positions. The technique relies on the concept that each view is allowed to vote on the contents of the scene via ray tracing. Various sharpness metrics are utilized for estimating the locations of visible surfaces in the views, and reconstruction is posed as an optimization problem.

Abstract: Embodiments of the present disclosure include systems, device, and methods of providing optical sensing. Various embodiment include an optical transmitting and receiving apparatus that can include an optical fiber bundle having an end located proximate to a lens and an aperture through which optical energy is received by the optical fiber bundle, and a sensor array, where the optical fiber bundle receives optical energy and passes the optical energy through the bundle to the sensor array, and where the sensor array is located remotely from the lens.

Abstract: One device embodiment includes a device for filtering radiation from a target region in multiple spectral bands. The device includes a number of optical quantum dot filters, each having a particular pass-through wavelength range, positioned on a rotatable disk.

Abstract: A smart weed recognition and identification system comprises a chlorophyll sensor for detecting green vegetation and memory map means for storing images which contain different forms of green vegetation. The memory maps stored in memory are processed to eliminate the background information and leave a memory map containing only green vegetation. The enhanced memory map is further processed by an operation of segmentation into identifiable regions and the identifiable green vegetation regions are processed to identify unique attributes for each of the regions.

Abstract: A polarization diverse image sensor identifies different objects of green vegetation and produces a vegetation index of such vegetation. The sensor defines the degree, angle and intensity of polarization. This information is stored in a memory for producing an image memory map of the polarized pixel data. Differential pixel data is computed and then employed to generate a new polarization difference image which is further processed by histogramming slices of the new image to obtain a segmented image of the green vegetation. The attributes of the segmented image are then compared with segmented data which was previously stored in a model base library to obtain a match or no match of the identification of the green vegetation. If match is obtained, a controller issues control signals which controls the spray heads and chemicals carried on a moving spray platform. However, if no match is obtained, the original raw data is labeled, formatted and stored in the model base library as reference data.

Abstract: An apparatus and method for on-the-go measuring of the amount and quality of grain being harvested including a first light source for projecting a first light image onto a pile of grain on a conveyor in a harvesting machine to cream a three-dimensional light image on the pile of grain on the conveyor and then converting the light image into coordinates for comparison to reference coordinates to determine the volume of the pile of grain on the conveyor belt; and an apparatus for determination of the amount of moisture in the pile of grain by projecting a second light image of a first wavelength onto the pile of grain, with the wavelength of the light of a frequency responsive to the amount of moisture in the pile of grain, and measuring the amount of reflectance of the light image of the first wavelength; and projecting a third light image of a second wavelength on the pile of grain, with the second wavelength of light in a region where reflectance is not responsive to the amount of moisture in the pile of gra

Abstract: A performance measure of an ATR is made from ancillary target data and the ATR output. A parameter of the ATR is varied to determine the change an ATR performance due to the parameter variation. Separate performance in the form of a quadratic equation models provide performance as a function of parameter and metrics. The performance model is partially differentiated with respect to the parameter. The partial differentiation allows solution for the estimated metric.

Abstract: A knowledge and model based adaptive signal processor for ensuring optimum performance in automated object recognition (AOR) systems. The invention does not require ground-truth information but uses predictive performance models for parameter adaption and updates for the AOR. The performance models are representations of continuous surfaces that interpolate and extrapolate for data and scenarios not previously tested. The present invention increases probability of detection and decreases false detection alarm rates of AOR systems.

Abstract: A system for classifying a two-dimensional object, the object having a boundary. The system includes a sensor for sensing the boundary of the object, a processor which assigns a chain code to the boundary of the object and memory for storing a plurality of chain code histograms corresponding to known two-dimensional objects. A histogram is generated from the object's assigned chain code and correlated in the processor with a chain code histogram from memory. A final ambiguity between the normalized chain code of the object and the chain code of the correlating known object is resolved through application of a Viterbi algorithm.