Examples of techniques for anomaly detection in a grade crossing prediction system are disclosed. Aspects include receiving a training data set comprising a plurality of labelled time series of signal values from a track circuit in a grade crossing predictor system, removing one or more non-unique values from each labelled time series of signal values in the plurality of labelled time series of signal values, extracting a plurality of features from the plurality of labelled time series of signal values, the plurality of features comprising: a number of signal values for each labeled time series of signal values in the plurality of labelled time series of signal values that are larger than a first threshold and a standard deviation for each labelled time series of signal values in the plurality of labelled time series of signal values, and training a machine learning algorithm utilizing the plurality of features.

Examples of techniques for anomaly detection in a grade crossing prediction system are disclosed. Aspects include receiving a training data set comprising a plurality of labelled time series of signal values from a track circuit in a grade crossing predictor system, removing one or more non-unique values from each labelled time series of signal values in the plurality of labelled time series of signal values, extracting a plurality of features from the plurality of labelled time series of signal values, the plurality of features comprising: a number of signal values for each labeled time series of signal values in the plurality of labelled time series of signal values that are larger than a first threshold and a standard deviation for each labelled time series of signal values in the plurality of labelled time series of signal values, and training a machine learning algorithm utilizing the plurality of features.

A control system may be provided that may include one or more processors. The one or more processors may be configured to receive obstruction information related to a defined area from at least one optical sensor, determine an obstruction is in the defined area based on the obstruction information in response to actuation of a first safety device that is configured to prevent the obstruction from entering the defined area, and communicate an actuation signal to a second safety device to control movement of the second safety device based on the obstruction determined to be in the defined area.

A control system may be provided that may include one or more processors. The one or more processors may be configured to receive obstruction information related to a defined area from at least one optical sensor, determine an obstruction is in the defined area based on the obstruction information in response to actuation of a first safety device that is configured to prevent the obstruction from entering the defined area, and communicate an actuation signal to a second safety device to control movement of the second safety device based on the obstruction determined to be in the defined area.

A video analytic sensor system and methods for sensing an operating state of a railroad crossing gate processes images to detect and communicate railroad crossing gate position information to non-railroad systems such as vehicular traffic control systems. The sensor system may be retrofit to existing railroad crossing gates and does not require modification to or direct connection with existing railroad systems.

A video analytic sensor system and methods for sensing an operating state of a railroad crossing gate processes images to detect and communicate railroad crossing gate position information to non-railroad systems such as vehicular traffic control systems. The sensor system may be retrofit to existing railroad crossing gates and does not require modification to or direct connection with existing railroad systems.

A warning system for detecting approaching object and method thereof are provided. A detection unit detects a moving path of the approaching object; a storage unit stores a warning information including the warning area and the confirmation condition; and a processing unit receives the detection signal provided by the detection unit to acquire the current moving path of the approaching object. When the approaching object is detected as moving in the buffering zone, the confirmation operation of the confirmation condition is activated. When the moving path falls in the warning area and fulfills the confirmation condition, the processing unit sends out a warning signal. Therefore, a potentially dangerous approaching object is accurately identified, and the warning is correctly sent.

A railroad crossing safety assembly includes a plurality of object sensors that is each positioned on a respective one of four corners of a railroad crossing. The object sensors emit a sensing signal across the railroad crossing to detect an obstruction on the railroad crossing. A data storage unit is provided and each of the object sensors is in electrical communication with the data storage unit. The data storage unit is in electrical communication with emergency responders thereby facilitating the emergency responders to be notified of the obstruction on the railroad crossing. Additionally, the data storage unit is in communication with a railway operation department thereby facilitating the railway operation department to alter railway scheduling in response to the obstruction.

A railroad crossing safety assembly includes a plurality of object sensors that is each positioned on a respective one of four corners of a railroad crossing. The object sensors emit a sensing signal across the railroad crossing to detect an obstruction on the railroad crossing. A data storage unit is provided and each of the object sensors is in electrical communication with the data storage unit. The data storage unit is in electrical communication with emergency responders thereby facilitating the emergency responders to be notified of the obstruction on the railroad crossing. Additionally, the data storage unit is in communication with a railway operation department thereby facilitating the railway operation department to alter railway scheduling in response to the obstruction.

Railroad object detection systems and methods include radar sensors detecting object presence, speed and heading in a different manner. A controller compares signal outputs from the different sensors to make real time health assessments and self-diagnose sensor problems in a railroad application. The sensor devices may include an ultra-wideband (UWB) impulse radar device and at least one reflective device providing failsafe object presence detection and object non-presence detection in redundant fashion with at least a second sensor device such as a side-fired radar device.