return of ID and Class of detections triggering line counter

[maddust]

hello all,

im trying to get the frame,id and class of detections that tiggers a line_counter . the end goal is to export to a database or csv this data in order to do post processing analysis .

Can anyone provide some insight how to achieve this? so far i have been able only to get line_counter.out_count and line_counter.in_count values for every frame.

in addition i have noticed that by defaut in_count is triggered by TOP_CENTER and out_count by BOTTOM_CENTER of the bbox . not sure if this is intended to be like that but ideally im looking to tigger the lines by the CENTER of the bbox in both scenarios.

thanks in advance and sorry for my little knowledge about coding .

Script:
import cv2
import tqdm
from ultralytics import YOLO
import supervision as sv
import numpy as np
from supervision import VideoInfo, VideoSink
from supervision import get_video_frames_generator
LINE_START = sv.Point(372, 514)
LINE_END = sv.Point(1736, 718)
SOURCE_VIDEO_PATH ="/media/haroldpc/SSD01/videos/2023-04-12 16-46-26.mp4"

def main():
line_counter = sv.LineZone(start=LINE_START, end=LINE_END)
line_annotator = sv.LineZoneAnnotator(thickness=2, text_thickness=1, text_scale=0.5)
box_annotator = sv.BoxAnnotator(
thickness=2,
text_thickness=1,
text_scale=0.5,
text_padding=1
)

video_info = VideoInfo.from_video_path(video_path=SOURCE_VIDEO_PATH)
generator = get_video_frames_generator(SOURCE_VIDEO_PATH)
model = YOLO("yolov8s.pt")
with VideoSink(target_path='target_video.mp4', video_info=video_info) as s:
   for result in model.track(source=SOURCE_VIDEO_PATH, show=False, stream=True, agnostic_nms=True):
    
    frame = result.orig_img
    detections = sv.Detections.from_yolov8(result)

    if result.boxes.id is not None:
        detections.tracker_id = result.boxes.id.cpu().numpy().astype(int)
    
    

    labels = [
        f"{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
        for _, confidence, class_id, tracker_id
        in detections
    ]

    frame = box_annotator.annotate(
        scene=frame, 
        detections=detections,
        labels=labels
    )

    line_counter.trigger(detections=detections)
    line_annotator.annotate(frame=frame, line_counter=line_counter)

    cv2.imshow("yolov8", frame)
    
   
    #s.write_frame(frame)
    print("in_count: ")
    print(line_counter.in_count)
    print("out_count: ")
    print(line_counter.out_count)

    if (cv2.waitKey(30) == 27):
        break

if name == "main":
main()