Abstract: A framework for modeling traffic speed in a transportation network analyzes both the spatial and temporal dependencies in probe-based traffic speeds, historical weather data, and forecasted weather data, using multiple machine learning models.

Abstract: A framework for modeling traffic speed in a transportation network analyzes both the spatial and temporal dependencies in probe-based traffic speeds, historical weather data, and forecasted weather data, using multiple machine learning models. A decentralized partial least squares (PLS) regression model predicts short-term speed using localized, historical probe-based traffic data, and a deep learning model applies the predicted short-term speed to further estimate traffic speed at specified times and at specific locations in the transportation network for predicting traffic bottlenecks and other future traffic states.

Abstract: Systems, methods, and computer-executable instructions for collecting traffic data from devices. A data collection node determines a scanning algorithm. Multiple channels of a spectrum are scanning simultaneously. An advertising packet is detected on a channel. A MAC address is extracted from the advertising packet and at least one byte is removed from the MAC address. An identifier is created based on the reduced MAC address. A message including the identifier, RSSI of the advertising packet and timestamp is sent to a remote server. The remote server uses the received data from multiple data collection units to create traffic data associated with devices.

Abstract: A framework for modeling traffic speed in a transportation network analyzes both the spatial and temporal dependencies in probe-based traffic speeds, historical weather data, and forecasted weather data, using multiple machine learning models. A decentralized partial least squares (PLS) regression model predicts short-term speed using localized, historical probe-based traffic data, and a deep learning model applies the predicted short-term speed to further estimate traffic speed at specified times and at specific locations in the transportation network for predicting traffic bottlenecks and other future traffic states.

Abstract: A platform for visualization of traffic information at an observed roadway or traffic intersection converts data collected from sensors for rendering as dynamic animations on a virtual map of the observed roadway or traffic intersection. The platform parses and curates incoming sensor data from either a single or multiple sensors representing one or more objects at the observed roadway or traffic intersection, and translates at least location data of each object for correlation of the object's movement relative to the observed roadway or traffic intersection. The platform then generates dynamic animations of the movement of each object and displays the animations as an overlay on the virtual map.

Abstract: A framework for precision traffic analysis estimates vehicle queue length at an observed roadway and calculates vehicle delay for improvements in traffic flow efficiency at a corresponding traffic intersection. The framework identifies a traffic detection area for a roadway at or near the traffic intersection and detects objects in the traffic detection area from sensors located proximate to the roadway. The framework then analyzes sensor data to determine the efficiency of the traffic network and to determine adjustments to timing of various phases of the signal timing plan for the traffic intersection.

Abstract: Systems, methods, and computer-executable instructions for collecting traffic data from devices. A data collection node determines a scanning algorithm. Multiple channels of a spectrum are scanning simultaneously. An advertising packet is detected on a channel. A MAC address is extracted from the advertising packet and at least one byte is removed from the MAC address. An identifier is created based on the reduced MAC address. A message including the identifier, RSSI of the advertising packet and timestamp is sent to a remote server. The remote server uses the received data from multiple data collection units to create traffic data associated with devices.

Abstract: A platform for visualization of traffic information at an observed roadway or traffic intersection converts data collected from sensors for rendering as dynamic animations on a virtual map of the observed roadway or traffic intersection. The platform parses and curates incoming sensor data from either a single or multiple sensors representing one or more objects at the observed roadway or traffic intersection, and translates at least location data of each object for correlation of the object's movement relative to the observed roadway or traffic intersection. The platform then generates dynamic animations of the movement of each object and displays the animations as an overlay on the virtual map.

Abstract: A framework for precision traffic analysis estimates dilemma zone activity to dynamically adjust phase cycle timing for improved efficiency of traffic flow at a roadway intersection. The framework identifies a traffic detection area at or near a traffic intersection, and detects objects in the traffic detection area from sensors located proximate to the traffic intersection. The framework then correlates lapsed phase cycle times for the traffic signal with associations between object characteristics and known speed characteristics for the roadway for a determination of whether there is dilemma zone activity for the remainder of that phase cycle. The framework then determines whether to adjust a timing of the current phase cycle.

Abstract: An augmented reality visualization framework for precision traffic analysis combines traffic data with content representative of physical-world characteristics, such as conditions in an intersection or roadway in which traffic activity occurs, and images of the intersection and roadway itself. The framework includes a visualization platform that enables display of the combined traffic data and content representing physical-world characteristics, and continual augmentations of such information in response to adjustments directed by users or automatically detected from actions such as user movement, other user manipulation, or movement of the visualization platform itself. The framework enables traffic applications such that a user can, when the platform is interfaced with intersection or roadway equipment, adjust machine activity or signal timing based upon the visualizations or data presented via the visualization platform.

Abstract: A framework for precision traffic analysis combines traffic sensor data from multiple sensor types, combining the strengths of each sensor type within various conditions in an intersection or roadway in which traffic activity occurs. The framework calibrates coordinate systems in images taken of the same area by multiple sensors, so that fields of view from one sensor system are transposed onto fields of view from other sensor systems to fuse the images taken into a combined detection zone, and so that objects are properly detected and classified for enhanced traffic signal control.

Abstract: A framework for precision traffic analysis combines traffic sensor data from multiple sensor types, combining the strengths of each sensor type within various conditions in an intersection or roadway in which traffic activity occurs. The framework calibrates coordinate systems in images taken of the same area by multiple sensors, so that fields of view from one sensor system are transposed onto fields of view from other sensor systems to fuse the images taken into a combined detection zone, and so that objects are properly detected and classified for enhanced traffic signal control.

Abstract: A framework for precision traffic analysis combines traffic sensor data from multiple sensor types, combining the strengths of each sensor type within various conditions in an intersection or roadway in which traffic activity occurs. The framework calibrates coordinate systems in images taken of the same area by multiple sensors, so that fields of view from one sensor system are transposed onto fields of view from other sensor systems to fuse the images taken into a combined detection zone, and so that objects are properly detected and classified for enhanced traffic signal control.

Abstract: Bicycle identification and cyclist notification at a traffic intersection includes determining a presence of a bicycle in a traffic detection zone and communicating an indicator that notifies the cyclist of both successful detection and that the presence has been communicated to the traffic system controller, so that a green light will be provided at the appropriate time for safe passage. Detectors at or near a roadway approach sense the presence or absence of a bicycle, and when a bicycle is detected, a signal communicated to the traffic signal controller for conversion to a suitable output signal that actuates notifications for cyclists.

Abstract: A data visualization technique rapidly loads images to decrease data transfer time and associated bandwidth cost for animation effects in displays of data, and includes initially loading raster imagery at a coarser zoom level than a current view on the display, and then manipulating the imagery using general-purpose image manipulation algorithms to interpolate data points as a user adjusts the zoom level. In this manner, the data visualization technique intentionally displays a coarser view than that selected, rather than transferring entirely new imagery or datasets, and manipulates the imagery as necessary to avoid loading more data from a remote server to the local client each time the user adjusts the view.

Abstract: Pedestrian detection and counting for traffic intersection control analyzes characteristics of a field of view of a traffic detection zone to determine a location and size of a pedestrian area, and applies protocols for evaluating pixel content in the field of view to identify individual pedestrians. The location and size of a pedestrian area is determined based either on locations of vehicle and bicycle detection areas or on movement of various objects within the field of view. Automatic pedestrian speed calibration with a region of interest for pedestrian detection is accomplished using lane and other intersection markings in the field of view. Detection and counting further includes identifying a presence, volume, velocity and trajectory of pedestrians in the pedestrian area of the traffic detection zone.

Abstract: A comparative traffic data analytics framework and visualization tool utilizes multiple data processing functions to manipulate traffic information from a plurality of sources and enable users to configure comparative analyses in a dashboard-style format for arterial and intersection performance monitoring and management. The comparative visualization tool provides a plurality of user-configurable functions to view corridor travel and delay times, an animated map, overall network statistics, and intersection performance using a graphical user interface to guide decision-making processes for traffic management in an arterial transportation network.

Abstract: A data visualization technique rapidly loads images to decrease data transfer time and associated bandwidth cost for animation effects in displays of data, and includes initially loading raster imagery at a coarser zoom level than a current view on the display, and then manipulating the imagery using general-purpose image manipulation algorithms to interpolate data points as a user adjusts the zoom level. In this manner, the data visualization technique intentionally displays a coarser view than that selected, rather than transferring entirely new imagery or datasets, and manipulates the imagery as necessary to avoid loading more data from a remote server to the local client each time the user adjusts the view.

Abstract: A vehicular observation and detection apparatus and system incorporates a detection framework using video analysis to differentiate between motorized vehicles and bicycles for improved traffic flow and safety at intersections. The detection framework creates virtual zones overlaid on lanes of a roadway and analyzes input data representing objects in the virtual zones collected from one or more cameras positioned at or near the roadway.

Abstract: Pedestrian detection and counting for traffic intersection control analyzes characteristics of a field of view of a traffic detection zone to determine a location and size of a pedestrian area, and applies protocols for evaluating pixel content in the field of view to identify individual pedestrians. The location and size of a pedestrian area is determined based either on locations of vehicle and bicycle detection areas or on movement of various objects within the field of view. Automatic pedestrian speed calibration with a region of interest for pedestrian detection is accomplished using lane and other intersection markings in the field of view. Detection and counting further includes identifying a presence, volume, velocity and trajectory of pedestrians in the pedestrian area of the traffic detection zone.