0.19.0/detection/tools/line_zone/

[giscus[bot]]

0.19.0/detection/tools/line_zone/

A set of easy-to-use utilities that will come in handy in any computer vision project.

https://supervision.roboflow.com/0.19.0/detection/tools/line_zone/

[TaHa8Farag]

How can I change the place where the number is written from above or below the line to anywhere in the video?

[casperdias]

Hey, I have a question.
Can you provide an example using that line_zone
IF people_crossline
Do Something
??
Thx

[SkalskiP]

Take a look here. That's probably the simplest case. someone crossed will get printed only if someone crossed the line.

import supervision as sv
from ultralytics import YOLO

model = YOLO(<SOURCE_MODEL_PATH>)
tracker = sv.ByteTrack()
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)
start, end = sv.Point(x=0, y=1080), sv.Point(x=3840, y=1080)
line_zone = sv.LineZone(start=start, end=end)

for frame in frames_generator:
    result = model(frame)[0]
    detections = sv.Detections.from_ultralytics(result)
    detections = tracker.update_with_detections(detections)
    crossed_in, crossed_out = line_zone.trigger(detections)
    if np.any(crossed_in) or np.any(crossed_out):
        print("someone crossed")

[casperdias]

TY, i tried it and it work. I have another question.
I try to crop and save image of someone who crossed, but when i try it it save all detection image not just who crossed??

[SkalskiP]

Sure, we can help you with that as well :)

import supervision as sv
from ultralytics import YOLO

model = YOLO(<SOURCE_MODEL_PATH>)
tracker = sv.ByteTrack()
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)
start, end = sv.Point(x=0, y=1080), sv.Point(x=3840, y=1080)
line_zone = sv.LineZone(start=start, end=end)

for frame in frames_generator:
    result = model(frame)[0]
    detections = sv.Detections.from_ultralytics(result)
    detections = tracker.update_with_detections(detections)
    crossed_in, crossed_out = line_zone.trigger(detections)
    if np.any(crossed_in) or np.any(crossed_out):
        detections_crossed_in = detections[crossed_in]
        for xyxy in detections_crossed_in.xyxy:
            crop = sv.crop_image(frame, xyxy)