摘要:
An automatic system (fig. 2, 100) that uses one to three grids (20cm) of overhead cameras (20c) to first video an event area (2), and overall bandwidth is greatly reduced by intelligent hubs (26) thast extract foreground blocks 10m based upon initial and continuously updates background images (2r), and the hub also analyze current image (10c) to constantly locate, classify and track in (3D) the limited number of expected foreground objects (10) and as object (10) of interest are tracked, the system automatically direct ptz perspective view cameras (40c) to follow the activities.
摘要:
An automated end labeler system (1) includes a scanning unit with a robotic label applicator (24) attached for horizontal movement on a horizontal arm (27). The horizontal arm (27) is capable of controlled vertical movement on a stand (26). The unit (24) emits a focused incident scanning energy beam (38) and receives the reflection of this beam off the end of a lumber unit (10). Electrical power and control signals are provided to the unit (24) via a cable (25). The system (1) is in direct communication with an office computer system (100) via a communications link (101). In a first alternative embodiment, optically responsive material is demarcated with laser light. In a second alternative embodiment, multiple spray heads apply paints having various optically reflective properties.
摘要:
A camera for capturing simultaneous images in the visible and non-visible light spectrums for use in videoing and tracking object movement is disclosed. The camera comprises a camera housing with a single lens capable of transmitting both visible and non-visible light frequencies; and a prism system for directing the non-visible frequencies to a first sensor and the visible frequencies to a second sensor. A processor relates the pixel data extracted from the first non-visible sensor with the pixel data from the second visible sensor.
摘要:
A camera for capturing simultaneous images in the visible and non-visible light spectrums for use in videoing and tracking object movement is disclosed. The camera comprises a camera housing with a single lens capable of transmitting both visible and non-visible light frequencies; and a prism system for directing the non-visible frequencies to a first sensor and the visible frequencies to a second sensor. A processor relates the pixel data extracted from the first non-visible sensor with the pixel data from the second visible sensor.
摘要:
A system for contextualizing disorganized content (2a) captured from any live session (1) using external devices 30-xd to first detect & record 30-1 session activities (1d) being conducted by session attendees (1c). Activities (1d) become normalized tracked object data 2-otd for differentiation 30-2 into normalized session marks 3-pm denoting thresholded activity (1d) changes. Normalized marks 3-pm are integrated 30-3 into normalized events 4-pe using a "mark creates, start or stops event" model. Events 4-pe may be synthesized 30-4 via waveform convolution forming new combined events 40se, or used as containers to summarize the occurrences of marks 3-pm or other events 4-pe, the results of which create new summary marks 3-sm. Calculation marks 3-tm may also be synthesized 30-4 for sampling various session data at various session times. During content expression 30- 5 events 4-pe and 4-se can be automatically named and foldered creating index (2i) and organized content (2b).
摘要:
Portable device (100) may be carried about by an operator within a prescribed area which contains one or more inventoried objects such as units of lumber (10). Within this area, the current location of both the units of lumber (10) and device (100) are constantly monitored by tracking computer system (80). As device (100) is carried about within the prescribed area, at any time it may be pointed at any unit (10) which is of interest to the operator. Device (100) will then employ distance measurement unit (108) to determine the distance between observation point (120) and projected spot (121). Once calculated, the location of spot (121) is then compared to the last known location of all surfaces of lumber units to determine which unit is currently being 'spotted'. All information is then communicated by device (100) via antenna (107) to stacking system (80).
摘要:
Portable device (100) may be carried about by an operator within a prescribed area which contains one or more inventoried objects such as units of lumber (10). Within this area, the current location of both the units of lumber (10) and device (100) are constantly monitored by tracking computer system (80). As device (100) is carried about within the prescribed area, at any time it may be pointed at any unit (10) which is of interest to the operator. Device (100) will then employ distance measurement unit (108) to determine the distance between observation point (120) and projected spot (121). Once calculated, the location of spot (121) is then compared to the last known location of all surfaces of lumber units to determine which unit is currently being 'spotted'. All information is then communicated by device (100) via antenna (107) to stacking system (80).
摘要:
A system for creating a composite view of a performance area by combining extracted foreground information from a grid of two or more cameras to be combined with a pre-known background view of the performance area is disclosed. Two or more video sensors are placed in a configuration such that their combined views cover the performance area, where the output of the sensors is provided to a video processing hub as a first stream of individual view video. A video processing hub analyzes the first stream of individual view video from one or more grid cameras that creates a second stream of extracted foreground view video for each first stream processed. The extracted foreground video represents the image difference between the first video captured by each camera and corresponding pre-known background data, and the second stream of extracted foreground view video is provided to a video aggregating computer. A video aggregating computer receives and combines the second stream of extracted foreground view video from one or more processing hubs with a pre-known background view of the performance area to form a third stream of composite view video.
摘要:
A system for creating objective sports measurements and statistics of a sporting event. The system analyzes the continuous on-going motion of the players, the game object and the state of the game. Continuous on-going motion of the players and game object can be obtained through any of several technologies including cameras, IR sensors, RFID, etc. The state of the game includes at least the determination of when the competition is officially on versus paused. For sports that include a game clock, the detection of a running clock indicates that the competition is on, whereas a stopped clock indicates that the competition is paused. The combination of these three data sets, i.e., player locations, game object locations and the state of the game, are both necessary and sufficient for objectively determining key sports metrics including when the game object is in possession of a given player, which expands into the cycle of possession flow.