KR101921074B1 - Sensor fusion system for controlling autonomous emergency braking in car - Google Patents

Abstract

A sensor fusion system for operating an autonomous emergency braking (AEB) of a vehicle according to the present invention includes: a camera module mounted on the vehicle to photograph surroundings; a Lidar module mounted on the vehicle to recognize an object by scanning the surroundings to sense a distance to the recognized object; a voltage stabilization circuit for stabilizing a vehicle battery power to supply the power to the camera module and the Lidar module; a battery monitoring unit for monitoring whether the vehicle battery power is normally supplied to internal components of the sensor fusion system; a power monitoring unit for monitoring whether the power stabilized from the voltage stabilization circuit is normally supplied to the camera module and the Lidar module; a data synchronization unit for synchronizing camera data received from the camera module and Lidar data received from the Lidar module according to a time synchronization signal; a monitoring unit for determining a risky object around the vehicle by using the synchronized data from the data synchronization unit to determine whether a risk exists; and a micro controller unit (MCU) for controlling operations by transmitting a control signal to the components including the AEB, based on the risk determined by the monitoring unit.

Description

[0001] The present invention relates to a sensor fusion system for driving an AEB of a vehicle,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a sensor fusion system for driving an AEB (Autonomous Emergency Braking), and more particularly, to a sensor fusion system for driving an AEB based on a camera module and a LiDAR module mounted on a vehicle. Fusion systems.

A self-propelled vehicle refers to a smart car that incorporates self-propelled technology applied to aircraft and ships, such as a car that travels to its destination without requiring the driver to operate the steering wheel, accelerator pedal, or brake.

In order to realize the autonomous driving of the vehicle, it is necessary to use a highway driving assist (HDA) technology, a lane departure warning system (LDWS), a lane keeping assistance system (LKAS) Vehicle technologies such as Blind Spot Detection (BSD), Advanced Smart Cruise Control (ASCC), and Autonomous Emergency Braking (AEB) are required. In addition, Satellite communication technology, and so on.

On the other hand, in the autonomous driving situation, the driver does not operate the pedal (accelerator pedal or brake pedal) of the vehicle. If the driver operates the pedal during autonomous driving, the vehicle controller ends the autonomous driving of the driver, It is determined that the operation is desired and the control for the autonomous running is terminated.

The Advanced Emergency Braking (AEB) system technology is an automatic emergency braking system for vehicles. It attaches a sensor to the front or rear of the vehicle, detects other vehicles or obstacles around the vehicle, and uses this to detect the possibility Is a technique that automatically brakes the vehicle.

The recent AEB technology uses a combination of a video camera, a GPS, and the like beyond a step of recognizing an obstacle with a simple proximity sensor, thereby more accurately detecting other vehicles or obstacles around the vehicle, accurately determining the possibility of collision, To effectively braking the engine.

In this way, AEB technology is a technology to automatically braking a vehicle while recognizing an object ahead through a sensor. It is an active safety device that operates when the preceding vehicle is speeding down or stopping, or when obstacles such as pedestrians suddenly appear. These AEBs are reported to reduce collision accidents by about 27%, and they are classified into AEB for urban area, AEB for street, and AEB for pedestrian depending on the speed and detection distance.

In this regard, the Euro NCAP (New Car Assessment Program) has decided to include the AEB function in the category of automobile safety grade in 2014, and subsequently regulate the AEB's mandatory installation, We are starting production of vehicles equipped with AEB function. Thus, in recent years, there is a need for improving the safety of a self-driving vehicle when driving the vehicle.

Korean Patent Publication No. 10-2017-0077317

SUMMARY OF THE INVENTION The present invention has been conceived to solve the above-mentioned problems, and it is an object of the present invention to improve the driving stability by detecting an error of a camera module and a lidar module in order to drive AEB of a vehicle and apply a technical safety concept And to provide a sensor fusion system with improved stability.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, there is provided a sensor fusion system for driving an AEB (Autonomous Emergency Braking) of a vehicle according to the present invention. The sensor fusion system includes a camera module for photographing the surroundings, a camera module mounted on the vehicle, A voltage stabilizing circuit for stabilizing the vehicle battery power and supplying the stabilized battery to the camera module and the lidar module; a vehicle battery A power monitoring unit for monitoring whether the stabilized power is normally supplied to the camera module and the Raider module from the voltage stabilization circuit, a battery monitoring unit for monitoring whether the power supplied from the camera module And a receiving module A monitoring unit for determining a dangerous object around the vehicle using the data synchronized by the data synchronizing unit and for determining whether there is a danger through the synchronized data, And an MCU (Micro Controller Unit) for controlling the driving by transmitting a control signal to a component including the AEB according to the danger.

The monitoring unit monitors whether camera data is transmitted at a predetermined speed in the camera module, monitors whether the Lada data is transmitted at a predetermined speed in the Lada module, and determines whether the camera data and the Lada data are time- And a fault monitoring unit for monitoring the fault.

When the battery monitoring unit detects that there is an error in the supply of the vehicle battery power, the monitoring unit can transmit a fault message in ADAS (Advanced Driver Assistance System) within a predetermined time through CAN (Controller Area Network) communication.

When the power monitoring unit detects an error in the power supplied to the camera module and the Raider module, the monitoring unit can transmit a fault message to the ADAS within a predetermined time through the CAN communication.

The monitoring unit monitors whether the 12V power is supplied to the camera module and the Raidium module. If an error occurs, the monitoring unit reboots the sensor fusion system a predetermined number of times. If the error persists after rebooting, (Not shown).

The fault monitoring unit monitors whether the horizontal FOV (Field of View) detects an object within 140 ° and whether or not the object is recognized within 66.7 ms in the camera module. If an error is detected, a fault message is transmitted to the CAN It can be transmitted within a predetermined time to ADAS through communication.

The fault monitoring unit monitors whether the camera module transmits data at a transmission rate of 30 frames per second (FPS). If an error occurs, the fault monitoring unit transmits a fault message to the MCU. The MCU transmits a fault A control signal for a message may be transmitted to control the driving.

The fault monitoring unit monitors whether the horizontal FOV of the Lidar module has a viewing angle of 140 ° or less and a vertical FOV of 5 ° or less and transmits LIDAR data at a transmission rate of 15 FPS. If a fault occurs, The MCU transmits a control signal for a fault message to the AEB through CAN communication, and controls the driving.

Wherein the data synchronization unit synchronizes camera data transmitted at a transmission rate of 30 FPS in the camera module to a transmission rate of 15 FPS transmitted from the Lydia module, and the fault monitoring unit transmits the camera data at a rate of 15 FPS It can monitor whether it is synchronizing or not, and if an error occurs, it can be sent to ADAS within 50ms.

The MCU may include a watchdog timer for monitoring the operation of the monitoring unit at a predetermined period.

The MCU monitors the abnormal operation of the monitoring unit at regular intervals using the watchdog timer, resets the system when an error occurs, and transmits the error information to ADAS within 50 ms.

According to the present invention, in the sensor fusion system for driving the AEB of a vehicle, it is possible to improve the stability by sensing the error of the camera module and the lidar module, and to improve the stability by applying the technical safety concept .

1 is a block diagram illustrating an architecture of a sensor fusion system according to an embodiment of the present invention.
2 is a flowchart illustrating a synchronization process between a camera module and a Lada module according to an exemplary embodiment of the present invention.
3 is a flowchart illustrating a battery monitoring process according to an embodiment of the present invention.
4 is a flowchart illustrating a power monitoring process according to an embodiment of the present invention.
5 is a flowchart illustrating a fault monitoring process according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted in an ideal or overly formal sense unless expressly defined in the present application Do not.

In the following description of the present invention with reference to the accompanying drawings, the same components are denoted by the same reference numerals regardless of the reference numerals, and redundant explanations thereof will be omitted. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail.

The present invention relates to a sensor fusion system installed in a vehicle for driving an AEB (Autonomous Emergency Brake) of a vehicle.

1 is a block diagram illustrating an architecture of a sensor fusion system according to an embodiment of the present invention.

Referring to FIG. 1, a sensor fusion system 10 according to an embodiment of the present invention includes a camera module 110, a LiDAR module 120, and a board 20.

The board 20 includes an AP (Application Processor) 30, a battery monitoring unit 150, a voltage stabilization circuit 160, a power monitoring unit 170, an MCU (Micro Controller Unit)

The AP 30 includes a data synchronization unit 190 and a monitoring unit 40.

The camera module 110 is mounted on the vehicle and serves to photograph the surroundings.

The AHD decoder interface unit 130 converts the image data of the AHD standard captured by the camera module 210 into a MIPI (Mobile Industry Processor Interface) standard.

The Lidar module 120 is a laser module using an optical signal. The Lidar module 120 is mounted on a vehicle, recognizes an object by scanning the periphery thereof, and detects a distance to the recognized object.

The voltage stabilizing circuit 160 stabilizes the battery power for the vehicle and supplies the stabilized battery power to the camera module 110 and the Raider module 120.

The battery monitoring unit 150 monitors the internal components of the sensor fusion system 10 to determine whether the vehicle battery power is normally supplied. For example, the vehicle battery may be 12V.

The power monitoring unit 170 monitors whether the stabilized power from the voltage stabilization circuit 160 is normally supplied to the camera module 110 and the Raider module 120.

The data synchronization unit 190 synchronizes the camera data received from the AHD decoder interface unit 130 and the LADIR data received from the LADIR module 120 according to a time sync signal.

The monitoring unit 40 uses the data synchronized by the data synchronization unit 190 to identify a dangerous object in the vicinity of the vehicle, and determines whether the dangerous object is dangerous.

The MCU 50 controls the driving by transmitting a control signal to the component including the AEB according to the danger determined by the monitoring unit 40.

The CAN transceiver 250 converts a TTL (Transistor Transistor Logic) level CAN (Controller Area Network) signal of the MCU 50 into a 12V vehicle CAN signal.

The CAN data monitoring unit 260 monitors the error of the CAN signal output from the CAN transceiver 250.

The fault monitoring unit 200 monitors whether camera data is transmitted at a predetermined speed in the camera module 110, monitors whether the Lada data is transmitted at a predetermined rate in the Lada module 120, And monitors for abnormality in time synchronization of data.

ADAS (Advanced Driver Assistance System) is a vehicle driving auxiliary system including AEB (Autonomous Emergency Braking).

In the present invention, when the battery monitoring unit 150 detects that there is an error in supply of the vehicle battery power, the monitoring unit 40 transmits a fault message to the Advanced Driver Assistance (ADAS) within a predetermined time through CAN (Controller Area Network) System).

When the power monitoring unit 160 detects an error in the power supplied to the camera module 110 and the Raider module 120, the monitoring unit 40 transmits a fault message to the ADAS Lt; / RTI >

The monitoring unit 40 monitors whether or not 12 V power is supplied to the camera module 110 and the Raider module 120 through the voltage stabilization circuit 10 and monitors the sensor fusion system 10 It is possible to reboot the sensor fusion system 10 a predetermined number of times and turn off the power supplied to the sensor fusion system 10 if the error continues even after rebooting.

The fault monitoring unit 200 monitors whether the horizontal FOV (Field of View) of the camera module 110 detects an object within 140 占 and whether or not the object is recognized within 66.7 ms. If an error is detected, The fault message for CAN can be transmitted to the ADAS within a predetermined time via the CAN communication.

The fault monitoring unit 200 monitors whether the camera module 110 transmits data at a transmission rate of 30 frames per second (FPS), and transmits a fault message to the MCU 50 when an error occurs. Then, the MCU 50 transmits a control signal for the fault message to the AEB through the CAN communication, thereby controlling the driving.

The fault monitoring unit 200 monitors whether the horizontal FOV of the Lada module 120 has a viewing angle of 140 DEG or less and a vertical FOV of 5 DEG or less and transmits LADID data at a transmission rate of 15 FPS, And transmits a fault message to the MCU 50 when it occurs. Then, the MCU 50 transmits a control signal for the fault message to the AEB through the CAN communication, thereby controlling the driving.

In the present invention, the data synchronization unit 190 synchronizes the camera data transmitted from the camera module 110 at a transmission rate of 30 FPS to a transmission rate of 15 FPS transmitted from the Lada module. At this time, the fault monitoring unit 200 monitors whether the data synchronizing unit 190 synchronizes at a rate of 15 FPS or not, and transmits an error to the ADAS within 50 ms if an error occurs.

The MCU 50 includes a time clock 230 for generating a clock signal and a watchdog timer 240 for monitoring the operation of the monitoring unit 40 at a predetermined period.

In the present invention, the MCU 50 monitors the abnormal operation of the monitoring unit 40 at intervals of 100 ms using the watchdog timer 240, resets the sensor fusion system 10 when an error occurs, Information can be sent to ADAS within 50ms.

For example, the lidar module 120 processes more than 400,000 data points per second. In the present invention, the board 20 is connected to 1080p image data of the camera module 110, Can be matched and processed. At this time, 256 or more threads can be simultaneously processed in the board 20 so that there is no problem in processing the image information and the RDA object point information.

For example, the LD driver of the Lidar module 120 collects pulse lasers in units of 10 nanoseconds and processes the received data points with more than 400,000 data points per second (cloud points) do. Then, the RDA module data is synchronized with the image information obtained from the camera sensor of the front object, and performs a synchronization operation of recognizing and processing the front object. The synchronization task converts the 3D data of the time information and the space information of the lidar data into the 2D data and then maps the 2D data with the image information of the camera data.

The process of synchronizing the data of the Lada module 120 and the image data of the camera module 110 according to the present invention will be described in detail as follows.

2 is a flowchart illustrating a synchronization process between a camera module and a Lada module according to an exemplary embodiment of the present invention.

Referring to FIG. 2, the data synchronization unit 190 synchronizes data of the camera module 110 and the Lada module 120 according to time synchronization.

Then, data is parse the synchronized data.

Then, an image ROI (Region of Interest) of the camera data is set (S201), and an ROI of the Lada data is set (S203).

Then, relative speed and angle information are calculated through a point cloud (S205), the position of the 3D object is determined (S207), and the 3D coordinates are converted into 2D coordinates (S209). Here, 3D coordinates are converted into 2D coordinates by mapping time and space information.

Next, the ROI information and the camera ROI information are mapped (S211). Here, if the mapping fails, the failure information is notified (S213).

Next, the object is recognized (S215). For example, three dynamic objects and five static objects can be recognized.

Then, the dynamic object and the static object are discriminated (S217).

Then, object tracing is performed (S219), and a dangerous object is discriminated (S221). For example, a total of 8 objects and 31 objects can be tracked simultaneously. If the object tracing fails, the failure information is returned.

If it is determined that the risk of the identified dangerous object is dangerous, it is transmitted to the ADAS including the AEB (S223).

3 is a flowchart illustrating a battery monitoring process according to an embodiment of the present invention.

Referring to FIG. 3, the battery monitoring unit 150 performs fault monitoring to check an error of the vehicle battery (S301). If an error is detected, a fault message is transmitted to the fault monitoring unit 200 (S303). The fault monitoring unit 200 transmits a fault message to the MCU 50 in step S305 and the MCU 50 outputs a fault alarm message to the user in step S307 ).

The fault monitoring unit 200 transmits a fault message to the MCU 50 at steps S311 and S313 and the MCU 50 transmits a fault message to the CAN 30, And outputs a fault alarm message informing the user of the power abnormality through communication (S315).

The fault monitoring unit 200 transmits a fault message to the MCU 50 in steps S319 and S321 and detects an error of the vehicle battery power supplied to the voltage stabilization circuit 160 in step S317. And outputs a fault alarm message informing the user of the power abnormality via CAN communication (S323).

4 is a flowchart illustrating a power monitoring process according to an embodiment of the present invention.

Referring to FIG. 4, the fault monitoring unit 200 monitors whether or not stable power is supplied from the voltage stabilizing circuit 160 to the camera module 110 and the Raider module 120 (S401). If an error occurs in the voltage stabilization circuit 160, the fault monitoring unit 200 transmits a fault message to the MCU 50 (S403 and S405), and the MCU 50 notifies the user of the power failure And outputs a fault alarm message indicating that the fault has occurred (S407).

If an error occurs in the power supplied to the camera module 110 in step S409, the fault monitoring unit 200 transmits a fault message to the MCU 50 in steps S411 and S413, And outputs a fault alarm message informing the user of the power abnormality (S415).

If an error occurs in the power supplied to the lidar module 120 at step S417, the fault monitoring unit 200 transmits a fault message to the MCU 50 at steps S419 and S421, And outputs a fault alarm message informing the user of the power abnormality via communication (S423).

5 is a flowchart illustrating a fault monitoring process according to an embodiment of the present invention.

Referring to FIG. 5, the sensor data processed by the camera module 100 is transmitted as raw data to the AHD decoder interface unit 130 (S501, S503).

In step S505, the fault monitoring unit 200 monitors the fault of the data and transmits a fault message to the MCU 50 in steps S507 and S535. Then, the MCU 50 transmits a fault message to the AEB through the CAN communication (S519), and outputs a fault alarm message informing the user of the abnormality (S537). For example, the fault monitoring unit 200 monitors whether seamless data of the camera module 110 is transmitted at 30 FPS.

Meanwhile, sensor data processed by the Lidar module 120 is transmitted as raw data to the fault monitoring unit 200 through Giga Ethernet (S521, S523).

The fault monitoring unit 200 monitors faults of the data (S525 and S529), and if there is an error, transmits a fault message to the MCU 50 (S527, S531, and S535). Then, the MCU 50 transmits a fault message to the AEB through the CAN communication (S519), and outputs a fault alarm message informing the user of the abnormality (S537). For example, the fault monitoring unit 200 monitors whether or not seamless data of the lidar module 120 is transmitted at 15 FPS.

The data synchronizer 190 receives the camera data and the ladder data in steps S509 and S533 and performs the synchronization processing on the camera data and the ladder data in step S511 and transmits the synchronized data to the AP 30 (S515), and the AP 30 transmits it to the MCU 50 (S517), and the MCU 50 transmits the CAN data to the AEB (S519).

The fault monitoring unit 200 monitors a fault for data synchronization, and if an error occurs, transmits a fault message to the MCU 50 (S534). Then, the MCU 50 transmits a fault message to the AEB through the CAN communication (S519), and outputs a fault alarm message informing the user of the abnormality (S537).

As described above, the feature of the sensor fusion system proposed in the present invention is that the data of the fusion sensor (the Lada sensor and the camera sensor) can be processed without any load in the system for front object recognition.

In addition, the sensor fusion system proposed in the present invention has a problem in that when processing object recognition (for example, forward 32 object recognition) algorithm with a large amount of sensor data (for example, front object recognition data) It does not.

In addition, the sensor fusion system proposed in the present invention includes a hardware safety function for each sensor operation, a data fusion for the fusion sensor to detect a dangerous object, a danger detection process, a recognition process, There is no load in performing a series of data processing operations leading to the data outputting process.

In addition, the sensor fusion system of the present invention can detect a physical failure in the system and inform the user or handle the failure internally.

While the present invention has been described with reference to several preferred embodiments, these embodiments are illustrative and not restrictive. It will be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit of the invention and the scope of the appended claims.

10 sensor fusion system 20 board
30 AP 40 Monitoring Department
50 MCU 110 Camera module
120 LADA module 130 AHD decoder interface part
190 data synchronization unit 200 fault monitoring unit

Claims (10)

In a sensor fusion system installed in a vehicle for driving an AEB (Autonomous Emergency Brake) of a vehicle,
A camera module mounted on the vehicle for photographing the surroundings;
A lidar module mounted on a vehicle, for recognizing an object by scanning the periphery thereof and detecting a distance to the recognized object;
A voltage stabilizing circuit for stabilizing the vehicle battery power and supplying the stabilized battery power to the camera module and the lidar module;
A battery monitoring unit for monitoring whether the vehicle battery power is normally supplied to internal components of the sensor fusion system;
A power monitoring unit for monitoring whether the stabilized power from the voltage stabilization circuit is normally supplied to the camera module and the Raider module;
A data synchronization unit for synchronizing the camera data received from the camera module and the LADIR data received from the LADIR module according to a time synchronization signal;
A monitoring unit for discriminating a dangerous object in the vicinity of the vehicle using the data synchronized by the data synchronizing unit and for determining a danger through the dangerous object; And
And an MCU (Micro Controller Unit) for controlling the driving by transmitting a control signal to the component including the AEB according to the danger determined by the monitoring unit,
The monitoring unit monitors whether camera data is transmitted at a predetermined speed in the camera module, monitors whether the Lada data is transmitted at a predetermined speed in the Lada module, and determines whether the camera data and the Lada data are time- And a fault monitoring unit for monitoring the fault,
When the battery monitoring unit detects that there is an error in the supply of the vehicle battery power, the monitoring unit transmits a fault message to the Advanced Driver Assistance System (ADAS) within a predetermined time through CAN (Controller Area Network) communication,
Wherein the monitoring unit transmits a fault message to the ADAS within a predetermined time through the CAN communication when the power monitoring unit detects an error in the power supplied to the camera module and the LOWER module,
The monitoring unit monitors whether the 12V power is supplied to the camera module and the Raidium module. If an error occurs, the monitoring unit reboots the sensor fusion system a predetermined number of times. If the error persists after rebooting, Off the power supplied to the power source,
The fault monitoring unit monitors whether the horizontal FOV (Field of View) detects an object within 140 ° and whether or not the object is recognized within 66.7 ms in the camera module. If an error is detected, a fault message is transmitted to the CAN To the ADAS through the communication within a predetermined time,
The fault monitoring unit monitors whether the camera module transmits data at a transmission rate of 30 frames per second (FPS). If an error occurs, the fault monitoring unit transmits a fault message to the MCU. The MCU transmits a fault A control signal for the message is transmitted to control the driving,
The fault monitoring unit monitors whether the horizontal FOV of the Lidar module has a viewing angle of 140 ° or less and a vertical FOV of 5 ° or less and transmits LIDAR data at a transmission rate of 15 FPS. If a fault occurs, The MCU transmits a control signal for a fault message to the AEB through CAN communication to control driving,
Wherein the data synchronization unit synchronizes the camera data transmitted at a transmission rate of 30 FPS in the camera module according to a transmission rate of 15 FPS transmitted from the Lydia module,
The fault monitoring unit monitors whether the data synchronizing unit synchronizes at a speed of 15 FPS or not, and transmits an error to the ADAS within 50 ms when an error occurs.
Wherein the MCU includes a watchdog timer for monitoring the operation of the monitoring unit at a predetermined cycle,
The MCU monitors the abnormal operation of the monitoring unit at regular intervals using the watchdog timer, resets the sensor fusion system when an error occurs, and transmits the error information to the ADAS within 50 ms,
Wherein the battery monitoring unit, the voltage stabilization circuit, the power monitoring unit, the data synchronizing unit, the monitoring unit, and the MCU are arranged and driven on one board,
The data synchronization unit synchronizes the data of the camera module and the data of the Lydia module according to time synchronization, performs data parsing on the synchronized data, of interest, sets the ROI of the ladder data, calculates relative speed and angle information through a point cloud, determines the position of the 3D object, the 3D ROI information and the camera ROI information are mapped by mapping the space information to the 2D coordinates and recognizing the object through the ROI information and the camera ROI information, It identifies the object, performs object tracing, identifies the dangerous object, determines the risk of the identified dangerous object, and sends it to the ADAS if it is determined to be dangerous. Sensor fusion system.
delete delete delete delete delete delete delete delete delete

Images