TWI651696B - Systems and methods for monitoring traffic accident - Google Patents

Abstract

A traffic accident monitoring system includes: a plurality of three-dimensional image capturing units and a main control terminal. The three-dimensional image capturing unit captures a three-dimensional image stream corresponding to a road region, wherein the three-dimensional image stream includes at least one three-dimensional object located on the road region. The main control terminal includes a first communication interface and a processing unit. The first communication interface is electrically connected to the three-dimensional image capturing unit. The processing unit receives the three-dimensional image stream from the three-dimensional image capturing unit through the first communication interface, identifies at least one three-dimensional object from the three-dimensional image stream, and obtains an area change and an action of at least one three-dimensional object, and changes according to the area And/or the action determines whether an accident condition exists and outputs a determination result and/or a three-dimensional video stream.

Description

Traffic accident monitoring system and method thereof

The present invention relates to a traffic accident monitoring system and method therefor.

At present, most of the existing road safety monitoring systems are implemented manually, for example, using a monitor to manually determine the content of a screen or returning by a passerby, and a small part is based on a two-dimensional image obtained by a general camera lens. Automatically judged. However, when manual methods are used, it may happen that the monitoring manpower is insufficient or the notification is delayed. When making a judgment through a two-dimensional image, it may be misjudged due to interference such as misalignment, shadow, and road color. Therefore, how to solve the problem of non-immediate problems caused by manual identification or the misjudgment caused by two-dimensional images is currently a problem to be solved.

The invention provides a traffic accident monitoring system, which comprises: a plurality of three-dimensional image capturing units and a main control terminal. The three-dimensional image capturing unit captures a three-dimensional image stream corresponding to a road region, wherein the three-dimensional image stream includes at least one three-dimensional object located on the road region. The main control terminal includes a first communication interface to And a processing unit. The first communication interface is electrically connected to the three-dimensional image capturing unit. The processing unit receives the three-dimensional image stream from the three-dimensional image capturing unit through the first communication interface, identifies at least one three-dimensional object from the three-dimensional image stream, and obtains an area change and an action of at least one three-dimensional object, and changes according to the area And/or the action determines whether an accident condition exists and outputs a determination result and/or a three-dimensional video stream.

100‧‧‧Traffic accident monitoring system

110a~110n‧‧‧3D image capture unit

121‧‧‧Processing unit

122‧‧‧First Communication Interface

123‧‧‧Image display unit

124‧‧‧Second communication interface

130‧‧‧Management unit

140‧‧‧Rescue unit

S210~250‧‧‧Step process

1 is a system architecture diagram of a traffic accident monitoring system according to an embodiment of the invention.

2 is a flow chart showing a traffic accident monitoring method according to an embodiment of the present invention.

Other ranges for the systems and methods of the present invention will be apparent from the detailed description provided hereinafter. It is to be understood that the following detailed description, as well as specific embodiments, are intended to be illustrative of the embodiments of the invention.

1 is a system architecture diagram of a traffic accident monitoring system according to an embodiment of the invention. The traffic accident monitoring system includes at least a plurality of three-dimensional image capturing units 110a-110n, a master terminal 120, a traffic control unit 130, and a rescue unit 140. Each of the three-dimensional image capturing units 110a-110n is used A plurality of three-dimensional images corresponding to a road area are captured, and a three-dimensional image stream is output. The three-dimensional video stream includes at least one three-dimensional object located on the road area. The 3D image capturing unit 110a~110n may be a TOF (Time Of Flight) camera. The TOF camera calculates the depth of the object in the space to be tested according to the time information of the light emitted by the internal light emitting element in the space to be tested. The information is obtained to obtain the three-dimensional information corresponding to the object in the space of the object to be tested, and each of the three-dimensional image capturing units 110a-110n has an individual identification code, so that the main control terminal 120 receives the corresponding three-dimensional image. During streaming, the source of the image and the location of the road region may be determined based on the identification code included in the 3D video stream. The main control terminal 110 can be implemented on a desktop computer or other electronic device with computing power. The control terminal 110 includes at least one processing unit 121, a first communication interface 122, at least one image display unit 123, and a second communication interface 124. The processing unit 111 can be implemented in various manners, such as a dedicated hardware circuit or a general-purpose hardware (for example, a single processor, a multi-processor with parallel processing capability, a graphics processor, or other processor capable of computing power) When the code or software is used, the functions described later are provided. The first communication interface 122 and the second communication interface 124 can be a wireless telecommunication module, a local area network (LAN) communication module, or a wireless local area network communication module (WLAN). The first communication interface 122 is disposed between the processing unit 121 and the three-dimensional image capturing unit 110a-110n, and is electrically connected to the three-dimensional image capturing unit, so that the processing unit 121 can transmit the self-dimensional image capturing unit through the first communication interface 122. 110a~110n receive the 3D video stream. The second communication interface 124 is disposed between the processing unit 121 and the communication unit 130 and the rescue unit 140, so that the processing unit 121 A notification signal can be output to the traffic management unit 130 and/or the rescue unit 140. The image display unit 123 has a display panel (for example, a thin film liquid crystal display panel, an organic light emitting diode panel or other display panel) for displaying the three-dimensional image obtained by the three-dimensional image capturing units 110a to 110n. The display screen of one of the image display units 123 can be divided into a plurality of sub-pictures to respectively display the three-dimensional images corresponding to the different three-dimensional image capturing units 110a-110n. The traffic management unit 140 can be a police station or a patrol police car, and the rescue unit 140 can be 119, but is not limited thereto. In addition, the main control terminal 110 further includes a storage unit (not shown) for storing information required during the execution, for example, information about the three-dimensional image capturing units 110a-110n (for example, the three-dimensional image capturing units 110a-110n) The identification code corresponding to each one, the three-dimensional video stream received from the three-dimensional image capturing units 110a to 110n, the communication unit 130, and the contact information of the rescue unit 140 are not limited thereto.

2 is a flow chart showing a traffic accident monitoring method according to an embodiment of the present invention. In step S210, each of the three-dimensional image capturing units 110a-110n captures a three-dimensional video stream corresponding to a road area every predetermined time period. In step S220, the processing unit 121 of the control terminal receives the complex three-dimensional video stream corresponding to each of the three-dimensional image capturing units 110a-110n through the first communication interface. The three-dimensional video stream may include an identification code of each of the three-dimensional image capturing units 110a-110n, so that when the processing unit 121 receives the three-dimensional video stream, the three-dimensional image stream may be separately captured according to the identification code. The three-dimensional video stream of units 110a-110n is processed. In step S230, the processing unit 121 obtains an area change and an action corresponding to the at least one three-dimensional object according to the three-dimensional video stream. Among them, because the vehicle system protrudes from the road, This processing unit 121 determines a three-dimensional object protruding from the road as a vehicle. Next, the processing unit 121 further calculates an action and an area change corresponding to the three-dimensional object in the continuous three-dimensional video stream to determine whether an accident condition exists. In addition, in step S240, after receiving the three-dimensional video stream corresponding to each of the three-dimensional image capturing units 110a-110n, the processing unit 121 may further display the three-dimensional video stream through the at least one image display unit 123. The image display unit 123 can cut the original display image into a plurality of sub-pictures, and each of the sub-pictures displays a three-dimensional image corresponding to different three-dimensional image capturing units. According to another embodiment of the present invention, when the three-dimensional image capturing unit 110a-110n includes both the RGB lens and the depth of field lens, the image display unit 123 can display only the two-dimensional image obtained by the RGB lens to reduce the operation of the processing unit 121. burden.

Next, in step S250, the processing unit determines an accident condition based on the area change and/or the action. For example, according to an embodiment of the present invention, when the processing unit 121 determines that the speed of the three-dimensional object (ie, the vehicle) protruding from the road area exceeds the speed limit based on the continuous plurality of images, the processing unit 121 determines that the vehicle is overspeeded.

Or, according to another embodiment of the present invention, when there are at least two three-dimensional objects protruding from the road in the image, the processing unit 121 determines that at least two vehicles are included in the area corresponding to the three-dimensional image capturing unit. However, in the subsequent video stream, when the two objects in the streaming image show that they have changed from mutual contact to each other, the processing unit 121 determines that two vehicles have a collision accident. In addition, the processing unit 121 can further determine the severity of the accident condition according to the area change of the three-dimensional object. For example, when two three-dimensional objects (ie, vehicles) are in contact, if the area change corresponding to two three-dimensional objects is less than a predetermined value, then two vehicles are represented. The vehicle is only a slight collision, and the processing unit 121 determines that the accident condition is an ordinary car accident. On the other hand, when the area change corresponding to the two three-dimensional objects is larger than the predetermined value (that is, the area corresponding to the two three-dimensional objects is reduced), it means that two vehicles may have a serious collision, and the processing unit 121 determines that the accident condition is a serious automobile accident.

According to another embodiment of the present invention, when the processing unit 121 determines that at least three three-dimensional objects (ie, vehicles) change from mutual contact to each other according to the three-dimensional video stream, the processing unit 121 determines that a serial car accident occurs in the area, that is, an accident. The condition was determined to be a serious car accident.

According to another embodiment of the present invention, when the processing unit 121 detects that the three-dimensional object in the three-dimensional video stream is rotated or flipped, it determines that the accident condition is a serious car accident.

According to another embodiment of the present invention, when the processing unit 121 determines that the three-dimensional object (ie, the vehicle) in the three-dimensional video stream stops for a predetermined period of time, it is determined that the vehicle may be faulty or the driver has an emergency condition, and the processing unit 121 determines the accident condition as a possible traffic condition. Alternatively, when at least two of the three-dimensional objects in the three-dimensional video stream remain in close contact with each other for a preset period of time, the processing unit 121 determines that the accident condition is the possible traffic condition.

According to another embodiment of the present invention, when the processing unit 121 determines that another three-dimensional object is separated from the original three-dimensional object (ie, the vehicle) according to the continuous three-dimensional video stream, it is determined that the vehicle has an item falling, and the processing unit 121 determines. The accident situation is an item drop event.

Next, proceeding to step S260, the processing unit 121 further notifies the traffic management unit and/or the rescue unit of the determination result of the accident condition. For example, when dealing with When the unit 121 determines that the vehicle is overspeed, the vehicle has a slight collision, the vehicle stops for more than a predetermined period of time, or the vehicle is dropped, the notification signal is output to the traffic control unit 130. However, when the processing unit 121 determines that a serious collision such as a serious collision, a serial car accident, or a vehicle out of control occurs in the vehicle, indicating that there may be a casualty, the processing unit 121 simultaneously outputs a notification signal including the determination result to the traffic control unit 130 and the rescue. Unit 140 to grasp the golden rescue time. In addition, in order to determine the actual situation of the area corresponding to the three-dimensional image capturing unit by the communication unit 130 and/or the rescue unit 140, the processing unit 121 can further transmit the image stream to the traffic management unit 130 when outputting the notification signal. / or rescue unit 140.

Finally, in step S270, in order to attract the attention of the monitoring personnel, when the processing unit 121 determines that the accident has occurred, it may generate a warning signal corresponding to the image screen and/or display the determination result on the image display unit. For example, the monitoring personnel may be notified of the occurrence of an accident by flashing the display screen or by enabling a warning device (such as a horn or a warning light).

In summary, according to the traffic accident monitoring system and the method thereof according to various embodiments of the present invention, the processing unit can quickly determine whether an accident condition exists by determining an area change and an action change of an object corresponding to the vehicle in the three-dimensional image. And by automatically reporting the accident status to the traffic control unit and/or the rescue unit, the accident can be accelerated, and the gold rescue time can be further grasped to reduce the casualties of the personnel.

The algorithm for identifying the three-dimensional object, the area change of the three-dimensional object, and the action of the embodiments of the present invention can be implemented by the known techniques in the related art of the present invention, which is not limited by the present invention.

The method of the invention, or a particular type or portion thereof, may exist in the form of a code. The code may be included in a physical medium such as a floppy disk, a CD, a hard disk, or any other machine readable (such as computer readable) storage medium, or is not limited to an external computer program product, wherein When the code is loaded and executed by a machine, such as a computer, the machine becomes a device for participating in the present invention. The code can also be transmitted over some transmission medium, such as a wire or cable, fiber optics, or any transmission type, where the machine becomes available when the code is received, loaded, and executed by a machine, such as a computer. The device of the invention. When implemented in a general purpose processing unit, the code combination processing unit provides a unique means of operation similar to application specific logic.

In addition, various illustrative logic blocks, modules, and circuits, and the various aspects disclosed herein may be implemented in an integrated circuit (IC), an access terminal, an access point, or by an integrated circuit, Access terminal, access point execution. The integrated circuit can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA), or the like. Programmable logic device, discrete gate or transistor logic, discrete hardware components, electronic components, optical components, mechanical components, or any combination of the above to perform the functions described herein And may execute an execution code or instruction that exists in the integrated circuit, outside the integrated circuit, or both. A general purpose processor may be a microprocessor, but could be any conventional processor, controller, microcontroller, or state machine. The processor may be composed of a combination of computer devices, such as a combination of a digital signal processor and a microcomputer, a plurality of sets of microcomputers, A set of at most one set of microcomputers and a digital signal processor core, or any other similar configuration.

The features of many embodiments are described above to enable those of ordinary skill in the art to clearly understand the form of the specification. Those having ordinary skill in the art will appreciate that the objectives of the above-described embodiments and/or advantages consistent with the above-described embodiments can be accomplished by designing or modifying other processes and structures based on the present disclosure. It is also to be understood by those skilled in the art that <RTIgt; </ RTI> <RTIgt; </ RTI> <RTIgt; </ RTI> <RTIgt; </ RTI> <RTIgt;

Claims (12)

A traffic accident monitoring system includes: a plurality of three-dimensional image capturing units for capturing a three-dimensional image stream corresponding to a road region, the three-dimensional image stream comprising at least one three-dimensional object located on the road region And a main control terminal, comprising: a first communication interface electrically connected to the three-dimensional image capturing unit; and a processing unit configured to receive from the three-dimensional image capturing unit through the first communication interface Depicting the three-dimensional video stream, identifying the at least one three-dimensional object from the three-dimensional video stream, and obtaining an area change and an action of the at least one three-dimensional object, and changing according to the area and/or The action determines whether there is an accident condition, and outputs a determination result and/or the three-dimensional video stream; wherein the processing unit is further configured to determine whether two three-dimensional objects in the three-dimensional video stream change from non-contact Contacting each other, and when it is determined that the two three-dimensional objects are in contact with each other and the area change corresponding to the two three-dimensional objects is less than a predetermined value, The accident situation is given a conventional accident; and the processing unit is further configured to, when determining that the change corresponds to the two dimensional area of the object is greater than the predetermined value, it determines that the accident is a serious accident condition. A traffic accident monitoring system includes: a plurality of three-dimensional image capturing units for capturing a road area corresponding to a three-dimensional image stream, the three-dimensional image stream includes at least one three-dimensional object located on the road area; and a master terminal, comprising: a first communication interface electrically connected to the three-dimensional image capturing unit; And a processing unit, configured to receive the three-dimensional video stream from the three-dimensional image capturing unit through the first communication interface, identify the at least one three-dimensional object from the three-dimensional video stream, and obtain a Determining an area change and an action of at least one of the three-dimensional objects, and determining whether an accident condition exists according to the area change and/or the action, and outputting the determination result and/or the three-dimensional image stream; wherein the processing The unit is further configured to determine whether at least three three-dimensional objects in the three-dimensional video stream change from mutual contact to mutual contact, and determine that the accident condition is a serious automobile accident when it is determined that at least three three-dimensional objects are in contact with each other. . A traffic accident monitoring system includes: a plurality of three-dimensional image capturing units for capturing a three-dimensional image stream corresponding to a road region, the three-dimensional image stream comprising at least one three-dimensional object located on the road region And a main control terminal, comprising: a first communication interface electrically connected to the three-dimensional image capturing unit; and a processing unit configured to receive from the three-dimensional image capturing unit through the first communication interface Depicting a three-dimensional video stream from the three-dimensional video stream Identifying the at least one three-dimensional object, and obtaining an area change and an action of the at least one three-dimensional object, and determining whether an accident condition exists according to the area change and/or the action, and outputting the determination result and/or Or the three-dimensional video stream; wherein the processing unit is further configured to determine whether the three-dimensional object is inverted or tumbled in the three-dimensional video stream, and when it is determined that the three-dimensional object is flipped or rolled, The accident condition is determined to be a serious car accident. A traffic accident monitoring system includes: a plurality of three-dimensional image capturing units for capturing a three-dimensional image stream corresponding to a road region, the three-dimensional image stream comprising at least one three-dimensional object located on the road region And a main control terminal, comprising: a first communication interface electrically connected to the three-dimensional image capturing unit; and a processing unit configured to receive from the three-dimensional image capturing unit through the first communication interface Depicting the three-dimensional video stream, identifying the at least one three-dimensional object from the three-dimensional video stream, and obtaining an area change and an action of the at least one three-dimensional object, and changing according to the area and/or Determining whether there is an accident condition, and outputting the determination result and/or the three-dimensional image stream; wherein the processing unit is further configured to determine whether another three-dimensional object exists in the three-dimensional image stream to be separated from a three-dimensional object, And when it is determined that another three-dimensional object is separated from a three-dimensional object, the accident condition is determined as An item dropped. The traffic accident monitoring system according to any one of claims 1 to 4, wherein the processing unit is further configured to generate a warning signal when the accident condition exists. The traffic accident monitoring system of any one of claims 1 to 4, further comprising a preset time period; the processing unit is further configured to determine whether the three-dimensional object in the three-dimensional video stream stops Determining the preset time period, and after determining that the three-dimensional object stops the preset time period, determining that the accident condition is a possible traffic situation; or the processing unit is further configured to determine the three-dimensional video string Whether there is at least two three-dimensional objects in the flow that remain in close contact with each other for a predetermined period of time, and it is determined that the presence of the at least two three-dimensional objects remains almost in contact with each other for a predetermined period of time At the time, the accident condition is determined to be a possible traffic situation. The traffic accident monitoring system according to any one of claims 1 to 4, further comprising at least one image display unit for displaying the determination result and/or the three-dimensional image stream. The traffic accident monitoring system according to any one of claims 1 to 4, further comprising: a traffic control unit and/or a rescue unit for receiving the determination result from the master terminal to respond. A traffic accident monitoring method is applied to a traffic accident monitoring system including a plurality of three-dimensional image capturing units and a processing unit, comprising: capturing, by the three-dimensional image capturing unit, a three-dimensional image stream corresponding to a road region The three-dimensional video stream includes at least one of the road regions And locating the at least one three-dimensional object from the three-dimensional image stream through the processing unit, and obtaining an area change and an action of the at least one three-dimensional object, and changing according to the area and/or Or the action determines whether an accident condition exists, and outputs a determination result and/or the three-dimensional video stream; wherein the processing unit determines whether there are two three-dimensional objects in the three-dimensional video stream that are not in contact with each other. Changing into contact with each other, and determining that the two dimensional objects are in contact with each other and the area change corresponding to the two three-dimensional objects is less than a predetermined value, determining that the accident condition is an ordinary car accident; When the processing unit determines that the area change corresponding to the two three-dimensional objects is greater than the predetermined value, determining that the accident condition is a serious car accident. A traffic accident monitoring method is applied to a traffic accident monitoring system including a plurality of three-dimensional image capturing units and a processing unit, comprising: capturing, by the three-dimensional image capturing unit, a three-dimensional image stream corresponding to a road region The three-dimensional video stream includes at least one three-dimensional object located on the road area; and the at least one three-dimensional object is identified from the three-dimensional video stream through the processing unit, and the at least one is obtained An area change and an action of the one-dimensional object, and determining whether an accident condition exists according to the area change and/or the action, and outputting the determination result and/or the three-dimensional image stream; wherein the processing unit is further Determining whether at least three three-dimensional objects in the three-dimensional video stream change from mutual contact to mutual contact, and determining that the accident condition is serious when it is determined that at least three three-dimensional objects are in contact with each other Car accident. A traffic accident monitoring method is applied to a traffic accident monitoring system including a plurality of three-dimensional image capturing units and a processing unit, comprising: capturing, by the three-dimensional image capturing unit, a three-dimensional image stream corresponding to a road region The three-dimensional video stream includes at least one three-dimensional object located on the road area; and the at least one three-dimensional object is identified from the three-dimensional video stream through the processing unit, and the at least one is obtained An area change and an action of the one-dimensional object, and determining whether an accident condition exists according to the area change and/or the action, and outputting the determination result and/or the three-dimensional image stream; wherein the processing unit is further Determining whether the three-dimensional object is inverted or tumbled in the three-dimensional video stream, and determining that the accident occurs as a serious car accident when it is determined that the three-dimensional object is turned over or rolled. A traffic accident monitoring method is applied to a traffic accident monitoring system including a plurality of three-dimensional image capturing units and a processing unit, comprising: capturing, by the three-dimensional image capturing unit, a three-dimensional image stream corresponding to a road region The three-dimensional video stream includes at least one three-dimensional object located on the road area; and the at least one three-dimensional object is identified from the three-dimensional video stream through the processing unit, and the at least one is obtained An area change and an action of the one-dimensional object, and determining whether an accident condition exists according to the area change and/or the action, and outputting the determination result and/or the three-dimensional image stream; wherein the processing unit is further Determining whether there is another three-dimensional object in the three-dimensional image stream separated from a three-dimensional object, and determining that another three-dimensional object exists When the object is separated from a three-dimensional object, the accident condition is determined to be an item drop event.