Abstract: A location anomaly for a mobile device can be detected using non-location information from the mobile device. The non-location information does not include data from a location based device, such as a GPS. A probabilistic model is created using historical non-location information accumulated from the mobile device. Current non-location data is compared with the probabilistic model to determine a probability associated with the current non-location information. If the probability is less than a predetermined or configurable threshold, a location anomaly is detected. A notification of the location anomaly may be displayed and/or transmitted in response to detecting the location anomaly.

Abstract: An online system builds a high definition (HD) map for a geographical region based on sensor data captured by a plurality of autonomous vehicles driving through a geographical region. The autonomous vehicles detect map discrepancies based on differences in the surroundings observed using sensor data compared to the high definition map and send messages describing these map discrepancies to the online system. The online system ranks the autonomous vehicles based on factors including an upload rate indicating how often the vehicle was used providing data to the online system. The sensor data from vehicles is uploaded to the online system (e.g., in the cloud) to create the HD map while spreading the burden of uploading this data as evenly as possible across a fleet of vehicles. Data uploads are expensive and time consuming, so the system makes this negligible for each vehicle by balancing/managing the uploads carefully across the fleet.

Abstract: A computer system receives a request to locate a vehicle within a facility. The computer system parses the request to identify one or more characteristics of the vehicle. The computer system identifies a sensor corresponding to the vehicle based on the one or more characteristics of the vehicle. The computer system identifies a most recent location of the vehicle based on the last registered position of the vehicle within the facility. The computer system transmits a signal to a parking spot sensor at the most recent location of the vehicle in the facility. The computer system receives the unique identification. The computer system determines that the unique identification of the vehicle sensor co-located with the parking spot sensor matches the sensor of the requested vehicle. The computer system reports to the user a current location of the vehicle within the facility based on a location of the parking spot sensor.

Abstract: Embodiments are disclosed for responding to an incoming alert using vehicle resources to scan and report on an environment of a vehicle. An example an in-vehicle computing system of a vehicle includes a sensor subsystem in communication with a sensor, a communication interface, a processor, and memory storing instructions executable by the processor to receive, via the communication interface, an alert including one or more alert parameters, instruct the sensor to scan an assigned region around the vehicle, receive, from the sensor, locally scanned data corresponding to the assigned region, determine that the scanned data includes an object having features matching a selected alert parameter of the one or more alert parameters, and transmit, to an alert service, a notification identifying the object and the features matching the selected alert parameter, the notification including a location of the object.

Abstract: A travel control method includes a detector that detects information on lane boundary lines of a lane around a subject vehicle as real boundary line information from an actual environment around the subject vehicle. The travel control method also includes integrating the real boundary line information and map boundary line information to generate integrated boundary line information. The map boundary line information is information on the lane boundary lines of the lane included in map information. The travel control method further includes outputting the generated integrated boundary line information.

Abstract: A train wireless system includes a train detecting apparatus on the ground and a controller on a train. The detecting apparatus includes a detector and a calculator. The detector detects that the train is on rails in a block. The calculator measures an on-rail time during which the detector detects the train in the block, and calculates an on-rail detecting time during which the train has been on the rails in the block. The controller includes a distance measurer, a time measurer, a recorder, and a train-length calculator. The distance measurer measures a travelling distance of the train from a beginning of the block, the time measurer measures an elapsed time since the distance measurer starts the measurement, the recorder records the elapsed time and the travelling distance, and the train-length calculator searches the recorder based on the detecting time, and calculates the train length using a selected travelling distance.

Abstract: A speed limit violation control system of the present disclosure includes: imaging units (320, 330) which image a running vehicle; recorder (420) that records one of videos imaged by the imaging units (320, 330); and controller (360) that calculates a speed of the vehicle based on the videos of imaging units (320, 330) and determines a starting point and an ending point of the one of the videos, which is to be recorded in recorder (420), based on the calculated speed.

Abstract: An information processing apparatus capable of assisting safe driving of a vehicle at a place such as an intersection where the view from the vehicle is obstructed or restricted is provided. A detection processing unit detects a traffic mirror in an image and an object in the traffic mirror on the basis of image information representing an image captured by an image capturing apparatus mounted in a vehicle. And a calculating unit calculates a difference between a size of the detected traffic mirror and a reference size and calculates a size of the object by using the calculated difference. Driving assist information for the vehicle is generated on the basis of the calculated size of the object, and the generated driving assist information is output.

Abstract: A camera controller for selectively controlling illumination around a vehicle comprises an image capture portion having a viewing area; an output for transmitting lighting control messages; and control logic. The control logic determines that a change in illumination is necessary in the viewing area and transmits a lighting control message at the output in response to the determination that illumination change is necessary. The lighting control message directs at least one lighting source associated with the vehicle in the viewing area of the camera controller to be adjusted.

Abstract: An image processing apparatus including a wide-angle camera, an auxiliary camera, and a controller is provided. The wide-angle camera has a first Field Of View (FOV), and captures a first image of a first area of a scene. The auxiliary camera has a second FOV which is narrower than the first FOV, and captures a second image of a second area of the scene. In particular, the wide-angle camera and the auxiliary camera are disposed on the same surface of the image processing apparatus, and synchronized to capture the first image and the second image, respectively. The controller determines a portion of the first image, which corresponds to the second area of the scene, and superimposes the second image on the portion of the first image to generate an enhanced image.

Abstract: A car wash with integrated diagnostic functions is provided that includes the ability to wash and dry a connected vehicle and perform various diagnostic functions. The various diagnostic functions such as tread depth measurement, measuring tire pressures, performing safety inspection, emissions testing and performing vehicle diagnostics and the like may be performed while the connected vehicle is at the car wash. The results of the diagnostic tests may be provided to the driver at the end of the car wash via the driver's wireless computing device.

Abstract: There is provided a kit comprising a base member adapted to be releasably attached to an upper region of a vehicle; a pole member comprising a first end that is adapted to be releasably coupled to the base member; an identification tag adapted to be mounted on the pole member and at a predetermined distance from the first end; and a light adapted to be positioned on the pole member. Such a kit is quite useful for tracking vehicles such as vehicles left outdoors that can be covered with ice and snow.

Abstract: A method of neural network operations by using a grid generator is provided for converting modes according to classes of areas to satisfy level 4 of autonomous vehicles. The method includes steps of: (a) a computing device instructing a pair detector to acquire information on locations and classes of pairs for testing by detecting the pairs for testing; (b) the computing device instructing the grid generator to generate section information by referring to the information on the locations of the pairs for testing; (c) the computing device instructing a neural network to determine parameters for testing by referring to parameters for training which have been learned by using information on pairs for training; and (d) the computing device instructing the neural network to apply the neural network operations to a test image by using each of the parameters for testing to thereby generate one or more neural network outputs.

Abstract: A mount for a roof-mounted autonomous vehicle sensor assembly includes a cap, a seal, and a plurality of support members. The mount is compatible in shape with a moonroof opening in a vehicle roof panel. The cap is sized to overlap the moonroof opening. The cap has a plurality of attachment features to connect to the sensor assembly. The seal is to be disposed between the cap and the roof panel. The plurality of support members connects the cap to roof rails.

Abstract: A headlight control data generation device that generates headlight control data of a vehicle including a headlight includes an electronic control unit. The electronic control unit sequentially acquires, when a manual mode is selected, set data including a detection value of an illuminance around the vehicle, and ON and OFF data indicating that the headlight is in an ON state or in an OFF state at the time of sampling of the detection value, and generates the headlight control data based on the acquired set data. The headlight control data includes data regarding information on a probability of the headlight being in an ON state.

Abstract: A communication region defining method is a method for defining a defined communication region in operation of a toll collection system having only an on-board unit present within the defined communication region as a communication target for toll collection and includes: a transmitter arrangement step of arranging reference transmitters capable of transmitting radio waves at a plurality of positions on a boundary line of a defined communication region; a position location step of locating a position of each of the plurality of reference transmitters on the basis of a position location signal obtained by receiving, through predetermined position location antennas, radio waves transmitted by the plurality of reference transmitters; and a determination condition setting step of setting conditions for determining whether to set an on-board unit as a communication target for toll collection on the basis of position location results with respect to the plurality of reference transmitters.

Abstract: The invention provides A light management system for an outdoor lighting network system, comprising a plurality of outdoor light units wherein at least one light unit includes at least one sensor type, a central management system in communication with light units, said central management system sends control commands to one or more of said outdoor light units, in response to received outdoor light unit status/sensor information from one or more of said outdoor light units and implement a lighting strategy relating to the lighting characteristics of the plurality of outdoor light units, wherein the central management system uses the light unit status/sensor information to form a user's behavior analyses, and determine or estimate or predict the user's motion trajectory and/or position and a change in a user-controlled light use and/or ambient light, and determine whether to modify the lighting strategy and/or reconfigure one or more of the lights units.

Abstract: Some aspects of the invention relate to a mobile apparatus including an image sensor configured to convert an optical image into an electrical signal. The optical image includes an image of a vehicle license plate. The mobile apparatus includes a license plate detector configured to process the electrical signal to recover information from the vehicle license plate image. The mobile apparatus includes an interface configured to transmit the vehicle license plate information to a remote apparatus and receive verification of vehicle ownership in response to the transmission.

Abstract: A sensor arrangement includes at least one sensor (7) as well as a housing (1) constructed of at least two plastic injection molded parts (2, 3), and a sensor electronics which are located on the circuit board (5) and which is secured by this housing. At least one absorption body (4) is provided within the housing (1) and is designed as a plastic injection molded part and serves for absorbing fluid which could get into the housing by diffusion.

Abstract: A method and system for processing requests for vehicular data, including receiving a vehicle request for a vehicle parameter from a client system (e.g., third party application); verifying client access to the vehicle parameter; determining one or more parameter values for the requested vehicle parameter; and transmitting the one or more parameter values to the client system.

Abstract: Comparing text strings with Unicode encoding includes receiving two text strings S1 and S2. The process computes, for the first text string S1, a first weight according to a weight function ƒ that computes an ASCII prefix ƒA(S1), computes a Unicode weight suffix ƒU(S1), and concatenates the weights to form the first weight ƒ(S1)=ƒA(S1)+ƒU(S1). Computing the ASCII prefix for the first string applies bitwise operations to n-byte contiguous blocks of the first string to determine whether each block contains only ASCII characters, and replaces accented Unicode characters with equivalent unaccented ASCII characters when comparison is designated as accent-insensitive. When there is a first block containing a non-replaceable non-ASCII character, the Unicode weight suffix is computed by performing a character-by-character Unicode weight lookup beginning with the first block. The same process is applied to the second string. The text string are compared by comparing their computed weights.

Abstract: A method includes obtaining data relating to operation of a first vehicle in a vehicle consist that includes the first vehicle and a second vehicle communicatively coupled with each other by a communication channel. The first vehicle includes a first electronic component performing functions for the first vehicle using the first data. The method also includes communicating the first data over the communication channel from the first vehicle to a second electronic component disposed onboard the second vehicle responsive to the first electronic component being unable to perform the one or more functions for the first vehicle using the first data. The method further includes performing the functions of the first electronic component with the second electronic component using the first data that is received from the first vehicle.

Abstract: A system and method for processing and reporting situational information to emergency service providers in an emergency service communications network is disclosed. An emergency situation is monitored. Responsive to detecting the emergency situation, information relating to the emergency situation is collected. Then, the information is processed and stored in a database. The processed information is then reported to emergency service providers.

Abstract: Disclosed herein is a detection apparatus including: a resonant circuit provided with a Q-factor measurement coil and one or more capacitors to serve as a circuit for receiving pulses; a response-waveform detecting section configured to detect the waveform of a response output by the resonant circuit in response to the pulses; and a Q-factor measuring section configured to measure a Q factor of the resonant circuit from the response waveform detected by the response-waveform detecting section. It is possible to increase the precision of detection of a metallic foreign substance existing between a power transmitting side and a power receiving side.

Abstract: Aspects of the disclosure relate generally to maneuvering autonomous vehicles. Specifically, the vehicle may use a laser to collect scan data for a section of roadway. The vehicle may access a detailed map including the section of the roadway. A disturbance indicative of an object and including a set of data points data may be identified from the scan data based on the detailed map. The detailed map may also be used to estimate a heading of the disturbance. A bounding box for the disturbance may be estimated using the set of data points as well as the estimated heading. The parameters of the bounding box may then be adjusted in order to increase or maximize the average density of data points of the disturbance along the edges of the bounding box visible to the laser. This adjusted bounding box may then used to maneuver the vehicle.

Abstract: Camera pose optimization, which includes determining the position and orientation of a camera in three-dimensional space at different times, is improved by detecting a higher-confidence reference object in the photographs captured by the camera and using the object to increase consistency and accuracy of pose data. Higher-confidence reference objects include objects that are stationary, fixed, easily recognized, and relatively large. In one embodiment, street level photographs of a geographic area are collected by a vehicle with a camera. The captured images are geo-coded using GPS data, which may be inaccurate. The vehicle drives in a loop and captures the same reference object multiple times from the substantially same position. The trajectory of the vehicle is then closed by aligning the points of multiple images where the trajectory crosses itself. This creates an additional constraint on the pose data, which in turn improves the data's consistency and accuracy.

Abstract: A vehicle may include wireless signal sensors surrounding the doors of the vehicle. A processor of the vehicle may be programmed to capture, from the sensors, a first data snapshot when one of the doors is opened and a second data snapshot when the one of the door is closed, and assign a mobile device to a seating zone associated with the one of the doors when the first and second snapshots both indicate the mobile device is closest to the door.

Abstract: A camera calibration system for a vehicle includes a camera disposed at the vehicle and an image processor operable to process image data captured by the camera. The camera calibration system generates camera calibration parameters at least in part by iteratively refining calibration parameters starting from at least one of (i) an initial estimation and (ii) an intrinsic parameter of the camera. The camera calibration system uses a kinematic model of vehicle motion derived at least in part from image processing of multiple frames of captured image data. Responsive to such image processing, the camera calibration system extracts and matches features determined in multiple frames of captured image data. Responsive to image processing during movement of the vehicle along an arbitrary path, and responsive to generation of camera calibration parameters, the camera calibration system calibrates the camera as the vehicle navigates the arbitrary path.

Abstract: A method includes obtaining data relating to operation of a first vehicle in a vehicle consist that includes the first vehicle and a second vehicle communicatively coupled with each other by a communication channel. The first vehicle includes a first electronic component performing functions for the first vehicle using the first data. The method also includes communicating the first data over the communication channel from the first vehicle to a second electronic component disposed onboard the second vehicle responsive to the first electronic component being unable to perform the one or more functions for the first vehicle using the first data. The method further includes performing the functions of the first electronic component with the second electronic component using the first data that is received from the first vehicle.

Abstract: Lanes sensors are used to count the number of wheel assemblies on vehicles passing over roadway sensors. Lane sensors can also be used to classify vehicles at single and multiple lane sites for tolling and/or traffic planning. For counting vehicles, the Smart Loop Treadle of the present invention is designed for both tire and wheel assembly detection using inductive loop sensors for toll roads in single (Conventional) lane applications. The sensors detect the tire assemblies of both vehicles and vehicle trailers being towed to provide the sum of axle assemblies. For vehicle characterization, the sensor arrangement can have a combination of unique sensors that include tire/wheel detection sensors and vehicle lane position sensors. The characteristics of the vehicle, travel direction, speed, in lane position of the vehicle can be detected using combination of these sensors.

Abstract: The disclosure includes a camera array comprising camera modules, the camera modules comprising a master camera that includes a processor, a memory, a sensor, a lens, a status indicator, and a switch, the switch configured to instruct each of the camera modules to initiate a start operation to start recording video data using the lens and the sensor in the other camera modules and the switch configured to instruct each of the camera modules to initiate a stop operation to stop recording, the status indicator configured to indicate a status of at least one of the camera modules. The camera modules of the camera array are configured to provide a 3× field of view overlap.

Abstract: Systems and methods for vehicle detection and assessments of loop deterioration rely on changes in inductance of a loop sensor. The conductive element of the loop sensor is modeled using one or more inductances and one or more resistances. Sets of stimuli at different frequencies are provided to the loop sensor, and the resulting responses form the basis for vehicle detection and for an assessment whether the loop sensor has deteriorated.

Abstract: In a motor vehicle, a driver of the vehicle can identify himself or herself. A vehicle driver signal specific to the driver of the vehicle is then generated and transmitted by the motor vehicle by way of a transmitter. This allows devices situated in the vicinity of the vehicle to respond individually to a driver of a vehicle and to supply him or her with corresponding information.

Abstract: Tracking a vehicle using an unmanned aerial vehicle is disclosed. One or more first images may be received from a first camera of the first unmanned aerial vehicle located at a first location. A parking violation committed by a first vehicle may be determined in at least one of the one or more first images. The first unmanned aerial vehicle may be then repositioned. One or more second images having the second field of view and showing the first vehicle may then be received. A unique identifier of the first vehicle may then be determined based on at least one of the one or more second images.

Abstract: A drive safety application (app) that is controls other mobile app(s) and/or functionality of a communication device is centrally regulated via a network device. A manual override instruction can be provided to the network device by an authorized subscriber (e.g., via an online portal) and accordingly, the network device can instruct the communication device to disable the drive safety app. Profiling data is collected from various sources, such as, but not limited to, device sensors, location calculators, a vehicle's onboard diagnostic system (e.g., OBD2) sensors (e.g., via wireless link), scanned access points, etc. The profiling data can be utilized to calibrate device sensors of the communication device and to determine a location and/or context of the user. Further, a set of the mobile apps can be disabled/enabled based on an analysis of the location and/or context.

Abstract: A method for determining the weight G of a vehicle (1) while the vehicle is travelling on a section (3) of road (4) uses at least one weigh-in-motion (WIM) sensor (5) that is narrower than the length of the footprint of a wheel in the direction of vehicle travel. When the vehicle (1) travels along this section (3) of road (4) both the wheel loads Fi(t) of all the wheels (2) or twin wheels i, and the speed vi(t) of the vehicle (1) during the entire passing are acquired as time functions, and during evaluation of the data for determining the weight G the speeds vi(t) and their change over time are used as weighting of the simultaneously determined wheel loads Fi(t).

Abstract: A laser sensor module array for vehicle identification, speed monitoring and traffic safety applications. Each of the laser sensor modules comprise a laser signal transmitting and receiving port with the array comprising a basic row of N laser sensor modules, wherein N is greater than 1 and wherein each of the N laser sensor modules in the basic row is displaced at an acute angle with respect to adjacent ones of the laser sensor modules. An additional row of N laser sensor modules may adjoin the basic row of N laser sensor modules in a parallel or acute angular relationship to corresponding ones in the basic row.

Abstract: Some aspects of the invention relate to a mobile apparatus including an image sensor configured to convert an optical image into an electrical signal. The optical image includes an image of a vehicle license plate. The mobile apparatus includes a license plate detector configured to process the electrical signal to recover information from the vehicle license plate image. The mobile apparatus includes an interface configured to transmit the vehicle license plate information to a remote apparatus and receive verification of vehicle ownership in response to the transmission.

Abstract: Systems and method are disclosed for adaptive and/or autonomous traffic control. In one illustrative implementation, there is provided a method for processing traffic information. Moreover, the method may include receiving data regarding travel of vehicles associated with an intersection, using neural network technology to recognize types and/or states of traffic, and using the neural network technology to process/determine/memorize optimal traffic flow decisions as a function of experience information. Exemplary implementations may also include using the neural network technology to achieve efficient traffic flow via recognition of the optimal traffic flow decisions.

Abstract: A traffic indicator warning unit for preventing collisions in blind corners has a weather-resistant chassis, a rechargeable battery within the chassis configured to power the unit, an indicator assembly mounted to the chassis comprising a first indicator light configured to indicate to a driver to stop and wait, and a second indicator light configured to indicate to a driver that the unit is non-operational, and further a motion-detector mounted to the chassis, configured to detect a moving vehicle near the unit, a metal detector mounted to the chassis, configured to detect the metal in a vehicle near the unit, and a transmitter/receiver within the chassis having an antenna, wherein the transmitter/receiver is configured to communicate with one or more other traffic warning units. A method of use of a traffic indicator warning system for a blind corner system is also disclosed.

Abstract: A system and method for customs inspection and release are disclosed. In one aspect, a system includes a device layer of devices for inspection and release, at least some of which generate subject detection data. The system also includes an adaptor layer of adaptors corresponding to the devices that receive detection data from its corresponding device and convert it into an event in a formatted message. The system also includes a message service layer including a bus that receives events from the adaptor layer and constructs event messages based on them. The system also includes a processing control layer that receives and processes event messages, generates instructions associated with them, and transmits the instructions to the message service layer, which constructs instruction messages based on the received instructions and transmits them to the adaptor layer. The adaptor layer converts them into device instructions that operate based on them.

Abstract: A fault tolerant controller system includes a first controller and a second controller. One of the first and second controllers designated as a primary controller for generating control signals intended to control actuation devices on a vehicle under non-fault operating conditions, and the other of the first and second controllers designated as a secondary controller generating control signals intended to control actuation devices on the vehicle. The actuation devices are responsive only to the designated primary controller. An error is detected in the primary controller and a message is transmitted from the faulty controller to the non-faulty controller identifying the error. The non-faulty controller is subsequently designated as the primary controller. The control signals including an identifier that identifies the non-faulty controller as the designated primary controller. In response to detecting the error, the faulty controller is reset to operate in a safe operating mode as the secondary controller.

Abstract: A system and method for detecting electronic device use by a driver of a vehicle including acquiring an image including a vehicle from an associated image capture device positioned to view oncoming traffic, locating a windshield region of the vehicle in the captured image, processing pixels of the windshield region of the image for computing a feature vector describing the windshield region of the vehicle, applying the feature vector to a classifier for classifying the image into respective classes including at least classes for candidate electronic device use and candidate electronic device non-use, and outputting the classification.

Abstract: In a midst of switching light distribution patterns from a first light distribution pattern to a second light distribution pattern, in the event that a situation is detected in which the first light distribution pattern needs to be switched to a third light distribution pattern which differs from the second light distribution pattern, and in switching from the second light distribution pattern to the third light distribution pattern, in the event that in a plurality of partial areas which make up the third light distribution pattern, there exist a plurality of switching partial areas where an upward trend in illuminance changes to a downward trend, a control unit of a vehicle lamp system controls the drive of semiconductor light emitting devices which illuminate the plurality of switching partial areas so that the switching to the third light distribution pattern can be executed within a predetermined length of time.

Abstract: A computing device with multiple image capture elements can selectively activate those elements in order to keep an object of interest within the field of view of at least one of those elements, while conserving resources by not keeping all the image capture elements active. The object can be located using an appropriate object recognition process. The location, and thus the motion, of the object then can be tracked over time using one or the image capture elements. The motion can be monitored to determine when the object is likely to pass into the field of view of another image capture element. The determination can be made based upon factors such as location, direction, speed, acceleration, and predicted time within the current field of view. Such an approach allows an identified object to be tracked and kept in a field of view while conserving resources on the device.

Abstract: Methods of estimating vehicle location in a roadway using an automatic vehicle identification system are described. The methods involve receiving a set of response signals from a vehicle-mounted transponder at points in time and determining a range rate of the transponder relative to the antenna at each point in time; identifying a minima in the magnitude of the range rate; estimating a first position of the transponder at a first time corresponding to the occurrence of the minima; estimating a velocity of the vehicle based upon one or more of the determined range rates; and estimating a second position of the transponder based upon the first position and the velocity.

Abstract: A method for sensing the surroundings of a vehicle with a number of sensors, in which method during at least one echo cycle at least one echo information item about the surroundings is sensed by at least one sensor and is compressed using an algorithm, and in which the at least one compressed echo information item is transferred to at least one processing unit.

Abstract: An electronic flight strip system and method of detecting and indicating runway incursions are disclosed. One such method receives an aircraft location, compares the location to a geofenced area, and generates an indication on the touchscreen display in response to the aircraft location being within the geofenced area without an indication of clearance to enter the geofenced area. The indication may be part of the electronic flight strip associated with the offending aircraft.

Abstract: A diagnostic system for a vehicle, includes a computer storing software on a computer readable media, configurable for setting up recording of vehicle operations, selecting from a plurality of customizable triggering operations according to Boolean logic, and a vehicle communication interface detachably connected to the computer, being setup by the computer for recording of vehicle operation while the vehicle is operating and recorded information stored in a computer readable media of the vehicle communication interface being reviewed by the computer, and detachably connected to the vehicle for recording of the vehicle operations.

Abstract: The disclosure includes a method for traffic flow prediction based on data mining on spatio-temporal correlations. The method includes establishing a prediction model, data mining on spatio-temporal correlations, and traffic flow prediction based on spatio-temporal correlated data. The prediction model can be a linear regression model with multiple variables. The data mining on spatio-temporal correlations is based on a multi-factor linear regression model and by means of the optimization method in terms of sparse representation. The data from the spatio-temporal correlated sensors that are relevant to the prediction task are determined automatically. The traffic flow prediction based on spatio-temporal correlated data refers to that the prediction is performed with the input to the prediction model to be the data from the spatio-temporal correlated sensors.