102 based on the procedure defined by the object model. In some embodiments, at operation 308, the communication module 206 may additionally cause the gateway 104 to stream the sensor data from the portion of the sensor devices to the server system 108 for further analysis.

In certain example embodiments, the object model associated with a precursor to an event may identify one or more sensor devices to activate or access responsive to the precursor to the event. For example, in some embodiments, the event detection system 124 may be configured to access and record sensor data from a “primary” sensor device (e.g., a dashcam), and in response to detecting a precursor to an event, accessing one or more secondary sensor devices to retrieve sensor data.

FIG. 4 is a flowchart depicting a method 400 of accessing sensor data from a plurality of sensor devices 102 responsive to detecting an event, according to certain example embodiments. Operations of the method 400 may be performed by the modules described above with respect to FIG. 2. As shown in FIG. 4, the method 400 includes one or more operations 402, 404, 406, and 408. In some embodiments, the operations of the method 400 may be performed as a precursor to, or subroutine of, one or more of the operations of the method 300 depicted in FIG. 3, such as operation 302.

According to certain example embodiments, the sensor devices 102 may include one or more cameras, such as dashcams, wherein the dashcams may be directed inside a vehicle, to capture images and videos depicted occupants of the vehicle, as well as directed in front of and in some cases behind the vehicle.

At operation 402, the sensor data module 202 detects a feature within a frame of a video stream from one or more of the sensor devices 102. In some embodiments, the sensor data module 202 may include a neural network or machine learned model trained to recognize certain features that correspond to events and precursors to events. For example, the features may depict objects such as signs (e.g., a stop sign) as well as facial features and expressions of a driver of a vehicle.

At operation 404, in response to detecting a feature within the frame of the video stream from one or more of the sensor devices 102, the sensor data module 202 determines that the feature corresponds to a precursor to an event. For example, the feature may include a gaze direction of a driver of the vehicle, or a sign depicted within a frame of the video stream.

In some embodiments, the precursor to the event may correspond with an object model that defines conditions and thresholds associated with an event. For example, an event may include running a stop-sign or red light, while the precursor to the event is the detection of a sign or stop light within an image frame of the video stream generated by one or more of the sensor devices 102. Responsive to the sensor data module 202 detecting the precursor to the event, the object model module 204 accesses an object model that includes an event definition comprising a set of conditions and thresholds, and provides procedures and subroutines to be performed by one or more modules of the event detection system 124 in response to detecting the precursor to the event.

At operation 406, the sensor data module 202 accesses a portion of the sensor data generated by the sensor devices 102 based on the object model associated with the precursor to the event. For example, the portion of the sensor data identified by the object model based on the definition of the event associated with the precursor may include inertial data, GPS data, as well as vehicle ECU data. At operation 408, the sensor data module 202 detects the event based on the portion of the sensor data generated by the sensor devices 102. In some embodiments, the operations of the method 400 may be performed by one or more processors of the sensor devices 102 themselves, or by one or more processors associated with the gateway 104, or any combination thereof.

In certain example embodiments, the event detection system 124 may be configured to access and stream sensor data from the sensor devices 102 at a “baseline” data rate. For example, under normal operating conditions, in the absence of one or more event conditions, the event detection system 124 may be configured to cause the sensor devices 102 to generate sensor data at a reduced resolution, and to cause the gateway 104 to stream segments of sensor data to the server system 108 at predefined intervals based on the baseline data rate.

Accordingly, in some embodiments, the procedures defined by the object models may include instructions to cause one or more processors associated with the sensor devices 102, the gateway 104, and the client device 122 to increase the data rate and resolution in which sensor data is generated and accessed by the event detection system 124, responsive to detecting an event or precursor to an event.

FIG. 5 is a flowchart depicting a method 500 of detecting an event based on sensor data generated by a plurality of sensor devices 102, according to certain example embodiments. Operations of the method 500 may be performed by the modules described above with respect to FIG. 2. As shown in FIG. 5, the method 500 includes one or more operations 502, 504, and 506. The method 500 may be performed as a precursor to, or subroutine of, one or more of the operations of the methods 300 and 400, as depicted in FIGS. 3 and 4.

At operation 502, the sensor data module 202 accesses sensor data from the plurality of sensor devices 102 at a first data rate. For example, the event detection system 124 may be configured to access and stream data from the plurality of sensor devices 102 at a baseline data rate.

In some embodiments, the event detection system 124 may be configured to cause the gateway 104 to stream snapshots of sensor data from the sensor devices 102 at a predefined interval or data rate. For example, at the baseline rate, the event detection system 124 may only stream a portion of the sensor data from the sensor devices 102 through the gateway 104 to the server system 108.

At operation 504, the sensor data module 202 detects an event, or a precursor to an event, based on the sensor data, as discussed in the methods 300 and 400 of FIGS. 3 and 4. In response to detecting the event or precursor to the event, at operation 506, the event detection system 124 may cause the sensor data module 202 to access the sensor data from the sensor devices 102 at a second data rate. In some embodiments, the second data rate may be based on an event type of the event or precursor to the event detected by the sensor data module 202.

In some embodiments, operation 506 may also include causing the sensor data module 202 to stream a sensor data from a specific set of sensor devices from among the sensor devices 102. For example, in response to detecting an event based on sensor data from a first sensor device, the sensor data module 202 may access and stream sensor data from the first sensor device, and a second and third sensor device from among a plurality of sensor devices.

FIG. 6 is a flowchart depicting a method 600 of detecting an event based on sensor data generated by a plurality of sensor devices 102, according to certain example embodiments. Operations of the method 600 may be performed by the modules described above with respect to FIG. 2. As shown in FIG. 6, the method 600 includes one or more operations 602, 604, and 606. The method 600 may be performed as a precursor to, or subroutine of, one or more of the operations of the methods 300, 400, and 500, as depicted in FIGS. 3, 4, and 5.

At operation 602, upon accessing the sensor data from the sensor devices 102, as in operation 302 of the method 300, and operation 502 of the method 500, the sensor data module 202 extracts a set of features from the sensor data. For example, the sensor data may include video data generated by a dashcam, wherein the dashcam is configured to capture images of occupants of a vehicle. The set of features extracted from the sensor data may therefore include facial landmarks and image features depicting the occupants of the vehicle.

In response to extracting the set of features from the sensor data generated by the sensor devices 102, at operation 604 the sensor data module 202 applies the set of features to a machine learning model trained to identify events and precursors to events based on features. For example, the machine learning model may be trained to identify a distracted driver based on gaze tracking features. At operation 606, the sensor data module 202 identifies an event or precursor to an event based on the machine learned model.

FIG. 7 is an interaction diagram 700 depicting a flow of sensor data generated by the sensor devices 102, according to certain example embodiments. Operations of the interaction diagram 700 may be performed by the modules described above with respect to FIG. 2.

At operation 702, the sensor devices 102 detects a precursor to an event based on a first portion of sensor data generated by the sensor devices 102. For example, the first portion of the sensor data may include video data generated by a dashcam, and the precursor to the event may include a feature within the sensor data. For example, sensor devices 102 may include a neural network trained to identify objects correlated with precursors to events.

At operation 704, based on detecting the precursor to the event, the sensor devices 102 determines an event type that corresponds with the precursor to the event. The event type identifies an object model that defines a data flow of the sensor data.

At operation 706, the sensor devices 102 streams a second portion of the sensor data to the system gateway 104, where the second portion of the sensor data is based on the object model associated with the event type. At operation 708, the system gateway 104 detects an event based on the precursor to the event detected by the sensor device 102 and the second portion of the sensor data streamed by the sensor devices 102 to the system gateway 104.

At operation 710, based on the system gateway 104 detecting the event based on the second portion of the sensor data, the sensor devices 102 multiplex the sensor data from the plurality of sensors 102 and stream the multiplexed sensor data to the server system 108. At operation 712, the system gateway 104 routes the sensor data from the plurality of sensors 102 to the server system 108. At operation 714, the server system 108 receives the multiplexed sensor data.

In some embodiments, a portion of the plurality of sensors 102 may be integrated into the system gateway 104. For example, the system gateway 104 may include one or more sensor devices configured to generate sensor data. In further embodiments, the system gateway 104 may access the plurality of sensors 102 responsive to detecting an event based on a portion (e.g., the second portion) of the sensor data, as depicted in operation 708.

At operation 716, based on receiving the multiplexed sensor data, the server system 108 performs further analysis upon the sensor data, and in some embodiments may perform operations that include presenting a notification at a client device and causing display of a graphical user interface that comprises a presentation of visualizations based on the sensor data generated by the sensor devices 102.

For example, in some embodiments, the object model corresponding to the event may identify one or more client devices to be notified when an event is triggered and may also define notification features of the notifications to be presented. Responsive to detecting an event, the event detection system 124 presents the notification at the one or more client devices identified within the corresponding object model, wherein the notification includes a set of event attributes as defined based on the notification features from the object model.

FIG. 8 is an interface diagram depicting a GUI 800 to present sensor data from one or more sensor devices 102, according to certain example embodiments. As seen in the GUI 800, the presentation of the sensor data may include a video stream 805, depicting video data generated by a dashcam, a video stream 810, depicting video data generated by a driver facing dashcam, as well as a graph element 815, depicting sensor data captured by a vehicle ECU, and GPS data plotted over a period of time. In certain embodiments, the sensor data may also include an audio stream that comprises audio data collected by one or more sensor devices (i.e., microphones) in communication with the event detection system 124. For example, the audio data may be collected from a mobile device or device with similar audio recording capability, wherein the device may be coupled with one or more of the client device 122, the system gateway 104, the sensor devices 102, or the event detection system 124. Coupling may include wired as well as wireless connections. Accordingly, in such embodiments, a presentation of the audio data may be displayed at a position within the GUI 800, wherein the presentation of the audio data may include a visualization of the audio data, such as a display of a waveform, or an audio spectrum indicator.

In some embodiments, the period of time depicted by the graph element 815 may be based on temporal attributes of the video data depicted in the video streams 805 and 810. For example, the video stream 805 may include a display of a scrub bar, wherein a position of an indicator 820 on the scrub bar indicates a point in time of the video stream.

In some embodiments, the sensor data depicted in the graph element 815 may be scaled based on a length of the video data depicted in the video stream 805. For example, the position of the indicator 820 corresponds with a video frame of the video stream 805. As seen in the GUI 800, the position of the indicator 820 aligns vertically with corresponding sensor data in the graph element 815.

Similarly, the video stream 810 may be presented based on the video stream 805. For example, a user may provide an input moving the indicator 820 to a position that corresponds with a timestamped video frame of the video stream 805 along the scrub bar of the video stream 805. Based on receiving the input, the event detection system 124 updates the video stream 810 in the GUI 800 based on the position of the indicator 820 on the sub bar.

In some embodiments, the GUI 800 may include a display of an event log that includes a display of events detected by the event detection system 124, such as the event indicator 825. For example, based on detecting an event, as discussed in the methods 300 and 400 of FIGS. 3 and 4, the event detection system 124 may update the event log to include the event indicator 825, wherein properties of the event indicator 825 are based on attributes of the event.

In some embodiments, a user of the event detection system 124 may provide an input that selects an event indicator, such as the event indicator 825, and the event detection system 124 may update the GUI 800 to present the corresponding sensor data from the event. For example, updating the GUI 800 may include presenting a segment of the video streams 805 and 810 based on temporal attributes of the event associated with the event indicator 825.

In further embodiments, the GUI 800 may also include a map image 830. The map image 830 comprises indications of locations corresponding to the events from the event log. For example, the event indicator 825 comprises an identifier (“A”) that is also presented at a location that corresponds with the event indicator 825 on the map image 830. A user may therefore determine where the event associated with the event indicator occurred based on the position of the identifier within the map image 830.

FIG. 9 is an interface diagram depicting sensor data 900 from one or more sensor devices 102, according to certain example embodiments. As seen in FIG. 9, the sensor data 900 may include the video stream 810 depicted in FIG. 8 The video stream 810 includes video data from a dashcam.

In some embodiments, a dashcam may be positioned to record video of a driver of a vehicle. Based on receiving the video data from the dashcam, the event detection system 124 may perform facial recognition to the video data to identify one or more occupants of the vehicle. Based on identifying the one or more occupants of the vehicle based on the video data, the event detection system 124 may present an identification 910 that includes a display of an identifier of an occupant of the vehicle.

FIG. 10 is an interface diagram depicting sensor data 1000 from one or more sensor devices 102, according to certain example embodiments. As seen in FIG. 9, the sensor data 1000 may include the video stream 810 depicted in FIG. 8. The video stream 810 includes video data from a dashcam.

In some embodiments, a dashcam may be positioned to record video of a driver of a vehicle. Based on receiving the video data from the dashcam, the event detection system 124 may perform gaze detection on the video data to determine a point of attention of an occupant of the vehicle. Based on performing the gaze detection on the video data, the event detection system 124 may cause display of the gaze indicator 1005 within the video stream 810.

FIG. 11 is a block diagram illustrating components of a machine 1100, according to some example embodiments, able to read instructions from a machine-readable medium (e.g., a machine-readable storage medium) and perform any one or more of the methodologies discussed herein. Specifically, FIG. 11 shows a diagrammatic representation of the machine 1100 in the example form of a computer system, within which instructions 1110 (e.g., software, a program, an application, an applet, an app, or other executable code) for causing the machine 1100 to perform any one or more of the methodologies discussed herein may be executed. As such, the instructions 1110 may be used to implement modules or components described herein. The instructions 1110 transform the general, non-programmed machine 1100 into a particular machine 1100 programmed to carry out the described and illustrated functions in the manner described. In alternative embodiments, the machine 1100 operates as a standalone device or may be coupled (e.g., networked) to other machines. In a networked deployment, the machine 1100 may operate in the capacity of a server machine or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine 1100 may comprise, but not be limited to, a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a personal digital assistant (PDA), an entertainment media system, a cellular telephone, a smart phone, a mobile device, a wearable device (e.g., a smart watch), other smart devices, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing the instructions 1110, sequentially or otherwise, that specify actions to be taken by machine 1100. Further, while only a single machine 1100 is illustrated, the term “machine” shall also be taken to include a collection of machines that individually or jointly execute the instructions 1110 to perform any one or more of the methodologies discussed herein.

The machine 1100 may include processors 1104, memory memory/storage 1106, and I/O components 1118, which may be configured to communicate with each other such as via a bus 1102. The memory/storage 1106 may include a memory 1114, such as a main memory, or other memory storage, and a storage unit 1116, both accessible to the processors 1104 such as via the bus 1102. The storage unit 1116 and memory 1114 store the instructions 1110 embodying any one or more of the methodologies or functions described herein. The instructions 1110 may also reside, completely or partially, within the memory 1114, within the storage unit 1116, within at least one of the processors 1104 (e.g., within the processor's cache memory), or any suitable combination thereof, during execution thereof by the machine 1100. Accordingly, the memory 1114, the storage unit 1116, and the memory of processors 1104 are examples of machine-readable media.

The I/O components 1118 may include a wide variety of components to receive input, provide output, produce output, transmit information, exchange information, capture measurements, and so on. The specific I/O components 1118 that are included in a particular machine 1100 will depend on the type of machine. For example, portable machines such as mobile phones will likely include a touch input device or other such input mechanisms, while a headless server machine will likely not include such a touch input device. It will be appreciated that the I/O components 1118 may include many other components that are not shown in FIG. 11. The I/O components 1118 are grouped according to functionality merely for simplifying the following discussion and the grouping is in no way limiting. In various example embodiments, the I/O components 1118 may include output components 1126 and input components 1128. The output components 1126 may include visual components (e.g., a display such as a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT)), acoustic components (e.g., speakers), haptic components (e.g., a vibratory motor, resistance mechanisms), other signal generators, and so forth. The input components 1128 may include alphanumeric input components (e.g., a keyboard, a touch screen configured to receive alphanumeric input, a photo-optical keyboard, or other alphanumeric input components), point based input components (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, or other pointing instrument), tactile input components (e.g., a physical button, a touch screen that provides location and/or force of touches or touch gestures, or other tactile input components), audio input components (e.g., a microphone), and the like.

In further example embodiments, the I/O components 1118 may include biometric components 1130, motion components 1134, environmental environment components 1136, or position components 1138 among a wide array of other components. For example, the biometric components 1130 may include components to detect expressions (e.g., hand expressions, facial expressions, vocal expressions, body gestures, or eye tracking), measure biosignals (e.g., blood pressure, heart rate, body temperature, perspiration, or brain waves), identify a person (e.g., voice identification, retinal identification, facial identification, fingerprint identification, or electroencephalogram based identification), and the like. The motion components 1134 may include acceleration sensor components (e.g., accelerometer), gravitation sensor components, rotation sensor components (e.g., gyroscope), and so forth. The environment components 1136 may include, for example, illumination sensor components (e.g., photometer), temperature sensor components (e.g., one or more thermometer that detect ambient temperature), humidity sensor components, pressure sensor components (e.g., barometer), acoustic sensor components (e.g., one or more microphones that detect background noise), proximity sensor components (e.g., infrared sensors that detect nearby objects), gas sensors (e.g., gas detection sensors to detection concentrations of hazardous gases for safety or to measure pollutants in the atmosphere), or other components that may provide indications, measurements, or signals corresponding to a surrounding physical environment. The position components 1138 may include location sensor components (e.g., a Global Position system (GPS) receiver component), altitude sensor components (e.g., altimeters or barometers that detect air pressure from which altitude may be derived), orientation sensor components (e.g., magnetometers), and the like.

Communication may be implemented using a wide variety of technologies. The I/O components 1118 may include communication components 1140 operable to couple the machine 1100 to a network 1132 or devices 1120 via coupling 1122 and coupling 1124 respectively. For example, the communication components 1140 may include a network interface component or other suitable device to interface with the network 1132. In further examples, communication components 1140 may include wired communication components, wireless communication components, cellular communication components, Near Field Communication (NFC) components, Bluetooth® components (e.g., Bluetooth® Low Energy), Wi-Fi® components, and other communication components to provide communication via other modalities. The devices 1120 may be another machine or any of a wide variety of peripheral devices (e.g., a peripheral device coupled via a Universal Serial Bus (USB)).

Moreover, the communication components 1140 may detect identifiers or include components operable to detect identifiers. For example, the communication components 1140 may include Radio Frequency Identification (RFID) tag reader components, NFC smart tag detection components, optical reader components (e.g., an optical sensor to detect one-dimensional bar codes such as Universal Product Code (UPC) bar code, multi-dimensional bar codes such as Quick Response (QR) code, Aztec code, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D bar code, and other optical codes), or acoustic detection components (e.g., microphones to identify tagged audio signals). In addition, a variety of information may be derived via the communication components 1140, such as, location via Internet Protocol (IP) geo-location, location via Wi-Fi® signal triangulation, location via detecting a NFC beacon signal that may indicate a particular location, and so forth.

Glossary

“CARRIER SIGNAL” in this context refers to any intangible medium that is capable of storing, encoding, or carrying instructions for execution by the machine, and includes digital or analog communications signals or other intangible medium to facilitate communication of such instructions. Instructions may be transmitted or received over the network using a transmission medium via a network interface device and using any one of a number of well-known transfer protocols.

“CLIENT DEVICE” in this context refers to any machine that interfaces to a communications network to obtain resources from one or more server systems or other client devices. A client device may be, but is not limited to, a mobile phone, desktop computer, laptop, portable digital assistants (PDAs), smart phones, tablets, ultra books, netbooks, laptops, multi-processor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user may use to access a network.

“COMMUNICATIONS NETWORK” in this context refers to one or more portions of a network that may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a wireless WAN (WWAN), a metropolitan area network (MAN), the Internet, a portion of the Internet, a portion of the Public Switched Telephone Network (PSTN), a plain old telephone service (POTS) network, a cellular telephone network, a wireless network, a Wi-Fi® network, another type of network, or a combination of two or more such networks. For example, a network or a portion of a network may include a wireless or cellular network and the coupling may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile communications (GSM) connection, or other type of cellular or wireless coupling. In this example, the coupling may implement any of a variety of types of data transfer technology, such as Single Carrier Radio Transmission Technology (1×RTT), Evolution-Data Optimized (EVDO) technology, General Packet Radio Service (GPRS) technology, Enhanced Data rates for GSM Evolution (EDGE) technology, third Generation Partnership Project (3GPP) including 3G, fourth generation wireless (4G) networks, Universal Mobile Telecommunications System (UMTS), High Speed Packet Access (HSPA), Worldwide Interoperability for Microwave Access (WiMAX), Long Term Evolution (LTE) standard, others defined by various standard setting organizations, other long range protocols, or other data transfer technology.