Add SAHI techniques to detect small object for tracking task.

[anhalu]

Search before asking

• [X] I have searched the Yolov8 Tracking issues and found no similar enhancement requests.

Description

Can you add sahi to detection small object for tracking ? sahi can be installed directly using pip. It would be really great if it could be integrated into the respo. Plz take a look, thanks a lot.

Use case

No response

Are you willing to submit a PR?

• [ ] Yes I'd like to help by submitting a PR!

[anhalu]

@mikel-brostrom Plz, take a look, it will be quite effective when tracking small objects and over large image sizes

[mikel-brostrom]

This works for me :smile:

from sahi import AutoDetectionModel
from sahi.predict import get_prediction, get_sliced_prediction, predict
from sahi.postprocess.utils import object_prediction_list_to_numpy
import cv2
import numpy as np
from pathlib import Path

from boxmot import DeepOCSORT

tracker = DeepOCSORT(
    model_weights=Path('osnet_x0_25_msmt17.pt'), # which ReID model to use
    device='cpu',
    fp16=False,
)

detection_model = AutoDetectionModel.from_pretrained(
    model_type='yolov8',
    model_path='/home/mikel.brostrom/yolo_tracking/examples/weights/yolov8n.pt',
    confidence_threshold=0.3,
    device="cpu",  # or 'cuda:0'
)

vid = cv2.VideoCapture(0)
color = (0, 0, 255)  # BGR
thickness = 2
fontscale = 0.5

while True:
    ret, im = vid.read()

    # get detections using sahi
    result = get_sliced_prediction(
        im,
        detection_model,
        slice_height=256,
        slice_width=256,
        overlap_height_ratio=0.2,
        overlap_width_ratio=0.2
    )
    num_predictions = len(result.object_prediction_list)
    dets = np.zeros([num_predictions, 6], dtype=np.float32)
    for ind, object_prediction in enumerate(result.object_prediction_list):
        dets[ind, :4] = np.array(object_prediction.bbox.to_xyxy(), dtype=np.float32)
        dets[ind, 4] = object_prediction.score.value
        dets[ind, 5] = object_prediction.category.id

    tracks = tracker.update(dets, im) # --> (x, y, x, y, id, conf, cls, ind)

    xyxys = tracks[:, 0:4].astype('int') # float64 to int
    ids = tracks[:, 4].astype('int') # float64 to int
    confs = tracks[:, 5].round(decimals=2)
    clss = tracks[:, 6].astype('int') # float64 to int
    inds = tracks[:, 7].astype('int') # float64 to int

    # print bboxes with their associated id, cls and conf
    if tracks.shape[0] != 0:
        for xyxy, id, conf, cls in zip(xyxys, ids, confs, clss):
            im = cv2.rectangle(
                im,
                (xyxy[0], xyxy[1]),
                (xyxy[2], xyxy[3]),
                color,
                thickness
            )
            cv2.putText(
                im,
                f'id: {id}, conf: {conf}, c: {cls}',
                (xyxy[0], xyxy[1]-10),
                cv2.FONT_HERSHEY_SIMPLEX,
                fontscale,
                color,
                thickness
            )

    # show image with bboxes, ids, classes and confidences
    cv2.imshow('frame', im)

    # break on pressing q
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

vid.release()
cv2.destroyAllWindows()

[mikel-brostrom]

Example of tiled inference tracking provided here: https://github.com/mikel-brostrom/yolo_tracking#custom-object-detection-model-example