Abstract: In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.

Abstract: In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.

Abstract: A system improves privacy without compromising effectiveness of data collection by allowing an autonomous or remotely operated camera system, such as that on an Unmanned Aerial Vehicle (UAV), satellite, or other robot to self-censor by removing incidentally-collected non-critical data at the source, before that data can become accessible offboard the remotely operated camera system. In an example in which a region of interest is defined as a building, the system may automatically remove data not corresponding to the building before transmitting or archiving such data. In another example in which a person is incidentally observed, the system may automatically remove data corresponding to the person before transmitting or archiving such data.

Abstract: In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.

Abstract: A detection process, contact recognition process, classification process, and identification process are applied to raw sensor data to produce an identified contact record set containing one or more identified contact records. A prioritization process is applied to the identified contact record set to assign a contact priority to each contact record in the identified contact record set. Data are removed from the contact records in the identified contact record set based on the contact priorities assigned to those contact records. A first contact stream is produced from the resulting contact records. The first contact stream is streamed in a contact transport stream. The contact transport stream may include and stream additional contact streams. The contact transport stream may be varied dynamically over time based on parameters such as available bandwidth, contact priority, presence/absence of contacts, system state, and configuration parameters.

Abstract: In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.

Abstract: In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.

Abstract: A virtual serial-stream processor or system consists of one or more data input ports, zero or more data output ports, zero or more virtual control ports, one or more virtual serial and stream processing cores, one or more virtual serial control processors, and memory. Virtual components are spread across multiple physical devices, multiple virtual processing cores implemented in one physical device, or some combination, as dictated by an application-specific design.