Welcome to AI Vision USB Camera repository
12.Edge detection algorithm
Edge detection algorithm
1.Use
Code path：~/yahboomcar_ws/src/opencv_apps/launch
- Start the camera
roslaunch yahboomcar_visual opencv_apps.launch img_flip:=false
- img_flip parameter: whether the image needs to be flipped horizontally, the default is false.
[usb_cam-test.launch] file opens the [web_video_server] node by default, and you can directly use the [IP:8080] web page to view images in real time.
- Start the corner detection function of Opencv_apps
roslaunch opencv_apps edge_detection.launch # Edge detection algorithmThe debug_view for some functions is disabled, and there is no screen appearing. You can view the effect in the following two ways.
xThe reason for closing debug_view is that it will generate errors on the terminal, but the actual effect has not been affected.
- Local View Screen
Enter the following command and select the corresponding topic to see the effect:
xxxxxxxxxxrqt_image_view
- LAN viewing screen
In the same local area network, enter IP+port (8080) in the browser, for example:
x192.168.2.150:8080 # IP is the IP of the host computer
2. Effect display
There will be a topic for subscribing images and publishing images.
| Parameter | Type | Default | Analyze |
|---|---|---|---|
| ~use_camera_info | bool | true | Subscribe to the topic [camera_info] to get the default coordinate system ID, otherwise use the image information directly. |
| ~debug_view | bool | false | Whether to create a window to display the node image |
| ~edge_type | int | 0 | Specify the edge detection method: 0: Sobel operator, 1: Laplacian operator, 2: Canny edge detection |
| ~canny_threshold1 | int | 100 | Specify the second canny threshold |
| ~canny_threshold2 | int | 200 | Specify the first canny threshold |
| ~apertureSize | int | 3 | Aperture size of the Sobel operator. |
| ~apply_blur_pre | bool | True | Whether to apply blur() to the input image |
| ~postBlurSize | double | 3.2 | Input image aperture size |
| ~apply_blur_post | bool | False | Whether to apply GaussianBlur() to the input image |
| ~L2gradient | bool | False | Canny's parameters |
| ~queue_size | int | 3 | Queue size |
Effect picture:
Node picture:
