Jetson Nano and OpenCV: Selecting ROI with a mouse

So in this project I’ve coded in an application where you can select a rectangular portion from the video display screen and create a copy of that selected portion

Demo:

Things Required:

1. Jetson Nano
2. Keyboard
3. Mouse
4. HDMI Screen
5. Raspberry Pi Camera
6. External Power Supply

Reference Material:

1. You can check out this video for the project: (LINK)

Code:

Note that code below is in python

View on/Download from Github: (LINK)

import cv2
goFlag=0
def mouse_click(event, x, y, flags, params):
    global x1,y1,x2,y2
    global goFlag
    if event == cv2.EVENT_LBUTTONDOWN:
        x1=x
        y1=y
        goFlag=0
    if event == cv2.EVENT_LBUTTONUP:
        x2=x
        y2=y
        goFlag=1

cv2.namedWindow('nanoCam')
cv2.setMouseCallback('nanoCam', mouse_click)

dispW=640
dispH=480
flip=2
camSet='nvarguscamerasrc !  video/x-raw(memory:NVMM), width=3264, height=2464, format=NV12, framerate=21/1 ! nvvidconv flip-method='+str(flip)+' ! video/x-raw, width='+str(dispW)+', height='+str(dispH)+', format=BGRx ! videoconvert ! video/x-raw, format=BGR ! appsink'
cam=cv2.VideoCapture(camSet)

while True:
    ret, frame = cam.read()
    if goFlag==1:
        frame=cv2.rectangle(frame, (x1,y1),(x2,y2),(0,0,0),3)
        roi=frame[y1:y2, x1:x2]
        cv2.imshow('Copy', roi)
    cv2.imshow('nanoCam', frame)
    if cv2.waitKey(1)==ord('q'):
        break
cam.release()
cv2.destroyAllWindows()

Stay Tuned for upcoming posts on Jetson Nano and AI Projects! Want to be the first to know when a new and amazing post comes up?? Then feel free to subscribe!

Happy Learning!!