Abstract: An apparatus is provided. The apparatus receives a video feed and processes the video feed in real-time as the video feed is received. The apparatus performs object detection and recognition on the video feed to detect and classify objects therein, performs activity recognition to detect and classify activities of at least some of the objects, and outputs classified objects and classified activities in the video feed. The apparatus generates natural language text that describes the video feed, produces a semantic network, and stores the video feed, classified objects and classified activities, natural language text, and semantic network in a knowledge base. The apparatus generates a graphical user interface (GUI) configured to enable queries of the knowledge base, and presentation of selections of the video feed, classified objects and classified activities, natural language text, and semantic network.

Abstract: Behavior of an industrial system is communicated to an operator through graphical representations of gauges having a scale and pointer that represent parameters of the system. The pointer is positioned relative to the scale to indicate a measured parameter value. In various embodiments, when the parameter value is within operating limits, a first range is displayed that corresponds to the operating limits. When the parameter value has gone outside of the operating limits, the displayed range is changed, in various embodiments, to a second range that goes beyond the operating limits. A local visual indicator is also displayed, in particular embodiments, when the parameter value has gone outside of the operating limits. In a number of embodiments, such a tool can help to make the operator better aware of abnormal parameters of the system for early detection and correction of problematic operating conditions.

Abstract: An apparatus for automatic target recognition with reinforcement learning is provided. The apparatus receives an image of a scene and performs an automatic target recognition on the image to detect objects in the image as candidate targets. The apparatus divides the candidate targets into subsets of candidate targets and performs a verification of the automatic target recognition to identify true targets in the image. In the verification, the apparatus solicits user input to manually identify some true targets in the image. The verification is performed according to a reinforcement learning process to minimize a total verification time.

Abstract: An apparatus is provided. The apparatus receives a video feed and processes the video feed in real-time as the video feed is received. The apparatus performs object detection and recognition on the video feed to detect and classify objects therein, performs activity recognition to detect and classify activities of at least some of the objects, and outputs classified objects and classified activities in the video feed. The apparatus generates natural language text that describes the video feed, produces a semantic network, and stores the video feed, classified objects and classified activities, natural language text, and semantic network in a knowledge base. The apparatus generates a graphical user interface (GUI) configured to enable queries of the knowledge base, and presentation of selections of the video feed, classified objects and classified activities, natural language text, and semantic network.

Abstract: An apparatus for automatic target recognition with reinforcement learning is provided. The apparatus receives an image of a scene and performs an automatic target recognition on the image to detect objects in the image as candidate targets. The apparatus divides the candidate targets into subsets of candidate targets and performs a verification of the automatic target recognition to identify true targets in the image. In the verification, the apparatus solicits user input to manually identify some true targets in the image. The verification is performed according to a reinforcement learning process to minimize a total verification time.

Abstract: Behavior of an industrial system is communicated to an operator through graphical representations of gauges having a scale and pointer that represent parameters of the system. The pointer is positioned relative to the scale to indicate a measured parameter value. In various embodiments, when the parameter value is within operating limits, a first range is displayed that corresponds to the operating limits. When the parameter value has gone outside of the operating limits, the displayed range is changed, in various embodiments, to a second range that goes beyond the operating limits. A local visual indicator is also displayed, in particular embodiments, when the parameter value has gone outside of the operating limits. In a number of embodiments, such a tool can help to make the operator better aware of abnormal parameters of the system for early detection and correction of problematic operating conditions.

Abstract: Behavior of an industrial system is communicated to an operator through graphical representations of gauges having a scale and pointer that represent parameters of the system. The pointer is positioned relative to the scale to indicate the parameter value. In various embodiments, when the parameter value is within operating limits, a first range is displayed that corresponds to the operating limits. When the parameter value has gone outside of the operating limits, the displayed range is changed, in some embodiments, to a second range that goes beyond the operating limits. A local visual indicator is also displayed, in particular embodiments, when the parameter value has gone outside of the operating limits. In a number of embodiments, such a tool can help to make the operator better aware of abnormal parameters of the system for early detection and correction of problematic operating conditions.

Abstract: Behavior of an industrial system is communicated to an operator through graphical representations of gauges having a scale and pointer that represent parameters of the system. The pointer is positioned relative to the scale to indicate the parameter value. In various embodiments, when the parameter value is within operating limits, a first range is displayed that corresponds to the operating limits. When the parameter value has gone outside of the operating limits, the displayed range is changed, in some embodiments, to a second range that goes beyond the operating limits. A local visual indicator is also displayed, in particular embodiments, when the parameter value has gone outside of the operating limits. In a number of embodiments, such a tool can help to make the operator better aware of abnormal parameters of the system for early detection and correction of problematic operating conditions.

Abstract: Devices, systems and methods for removing foreign bodies within a body lumen are disclosed. An unfolding balloon catheter may include an elongated shaft having an intussuscepting balloon that can be actuated within a body lumen to capture and retrieve an intravascular device. The balloon may be configured to radially and/or axially expand when inflated, enveloping the intravascular device. In certain embodiments, the balloon may be formed by folding the ends of a distensible member inwardly, and then bonding the ends of the distensible member to the elongated shaft to form an expandable sleeve. An adhesive layer located along a portion of the elongated shaft may be used to temporarily secure the balloon to the elongated shaft.

Abstract: An exercise apparatus and method. Typically, the exercise apparatus includes a frame, and left and right pedals interconnected to the frame. The left and right pedals are adapted to be moved in any one of the following ways: in a substantially vertical direction, in a substantially horizontal direction, and simultaneously in a substantially vertical direction and a substantially horizontal direction. The apparatus may include a pedal support assembly interconnecting the pedals to the frame. The pedal support assembly typically includes a horizontal guide assembly configured to enable the pedals to move horizontally, and a vertical guide assembly configured to enable the pedals to move vertically. Additionally, the apparatus may include a resistance subsystem configured to selectively apply a resistance force against the motion of the pedals. The resistance subsystem may be used to limit motion of the pedals to a predefined pedal path within the range of motion.