yolov8旋转框+关键点检测（官方代码库集成版本）

一、Yolov8obb_kpt

-----------------------------------现已在v8官方库上更新旋转框分割算法和旋转框关键点检测算法--------------------------
------------------------------------------- https://github.com/yzqxy/ultralytics-obb_segment---------------------------------
记得给博主点上⭐，给予博主继续创作好用算法的动力。
可参考博主上一篇文章，Yolov8obb_kpt，旋转框+关键点检测，有向目标检测，判断目标正方向

旋转框关键点检测算法有一些小bug，由于博主的错误操作导致从v8代码库上拉取的提交修改后的代码直接消失了。。。。。。。。。
后续博主有空再重新上传供大家使用，以后就不从官方pull了英语不好理解不了太麻烦了，真TM无语---------------------------20240913

二、标注工具

标注软件：X-AnyLabeling，可查阅博客进行安装使用
标注旋转框和关键点，生成json文件。

三、json2txt转化为yolov8可训练标签的脚本

# COCO 格式的数据集转化为 YOLO 格式的数据集
# --json_path 输入的json文件路径
# --save_path 保存的文件夹名字，默认为当前目录下的labels。

import os
import json
from tqdm import tqdm
import argparse
import cv2
import numpy as np
parser = argparse.ArgumentParser()
# 这里根据自己的json文件位置，换成自己的就行
parser.add_argument('--json_path',
                    default=r'D:\Dataset\关键点\tading\coco_kpt_format\annotations\tading_kpt_val.json', type=str,
                    help="input: coco format(json)")
# 这里设置.txt文件保存位置
parser.add_argument('--save_path', default=r'D:\Dataset\关键点\tading\20220912_hailei\txt\val', type=str,
                    help="specify where to save the output dir of labels")
arg = parser.parse_args()


def convert(size, box):
    dw = 1. / (size[1])
    dh = 1. / (size[0])
    x = (box[0] + box[2]) / 2.0
    y = (box[1] + box[3] )/ 2.0
    w = box[2]-box[0]
    h = box[3]-box[1]

    x = round(x * dw, 6)
    w = round(w * dw, 6)
    y = round(y * dh, 6)
    h = round(h * dh, 6)
    return (x, y, w, h)


def check_points_in_rotated_boxes(points, boxes):
    """Check whether point is in rotated boxes

    Args:
        points (tensor): (1, L, 2) anchor points
        boxes (tensor): [B, N, 5] gt_bboxes
        eps (float): default 1e-9

    Returns:
        is_in_box (tensor): (B, N, L)

    """
    a = np.array(boxes[0])
    b = np.array(boxes[1])
    c = np.array(boxes[2])
    d = np.array(boxes[3])
    ab = b - a
    ad = d - a
    # [B, N, L, 2]
    ap = points - a
    # [B, N, L]
    norm_ab = np.sum(ab * ab)
    # [B, N, L]
    norm_ad = np.sum(ad * ad)
    # [B, N, L] dot product
    ap_dot_ab = np.sum(ap * ab)
    # [B, N, L] dot product
    ap_dot_ad = np.sum(ap * ad)
    # [B, N, L] <A, B> = |A|*|B|*cos(theta)
    is_in_box = (ap_dot_ab >= 0) & (ap_dot_ab <= norm_ab) & (ap_dot_ad >= 0) & (
            ap_dot_ad <= norm_ad)
    return is_in_box

def save_txt(data,ana_txt_save_path,obb_cls_kpt,obb_cls,width,heigth):
    with open(os.path.join(ana_txt_save_path, filename.split('.json')[0] + '.txt'), 'w', encoding='utf-8') as f:
        # 类别，obbbox，8个kpt
        for i in range(len(data['shapes'])):
            len_line = 9 + max(len(sublist) for sublist in obb_cls_kpt) * 3
            # len_line=9
            line = ['0' for _ in range(len_line)]
            for obb_i in range(len(obb_cls)):
                if data['shapes'][i]['label'] == obb_cls[obb_i]:
                    line[0] = str(obb_i)
                    print('obb_cls[obb_i]', obb_cls[obb_i])
                    # import  pdb
                    # pdb.set_trace()
                    x1 = data['shapes'][i]['points'][0][0]
                    y1 = data['shapes'][i]['points'][0][1]
                    x2 = data['shapes'][i]['points'][1][0]
                    y2 = data['shapes'][i]['points'][1][1]
                    x3 = data['shapes'][i]['points'][2][0]
                    y3 = data['shapes'][i]['points'][2][1]
                    x4 = data['shapes'][i]['points'][3][0]
                    y4 = data['shapes'][i]['points'][3][1]
                    # if x1>x2:
                    #     x3=x2
                    #     x2=x1
                    #     x1=x3
                    # if y1 > y2:
                    #     y3=y2
                    #     y2=y1
                    #     y1=y3

                    tatou = [[x1, y1], [x2, y2], [x3, y3], [x4, y4]]

                    line[1] = str(round(x1 / width, 6))
                    line[2] = str(round(y1 / heigth, 6))
                    line[3] = str(round(x2 / width, 6))
                    line[4] = str(round(y2 / heigth, 6))
                    line[5] = str(round(x3 / width, 6))
                    line[6] = str(round(y3 / heigth, 6))
                    line[7] = str(round(x4 / width, 6))
                    line[8] = str(round(y4 / heigth, 6))
                    print(line)
                    for j in range(len(data['shapes'])):
                        if len(obb_cls_kpt[obb_i]) > 0:
                            for kpt_i in range(len(obb_cls_kpt[obb_i])):
                                if data['shapes'][j]['label'] == obb_cls_kpt[obb_i][kpt_i]:
                                    print('data[]',data['shapes'][j]['label'])
                                    x = data['shapes'][j]['points'][0][0]
                                    y = data['shapes'][j]['points'][0][1]
                                    if check_points_in_rotated_boxes([x, y], tatou):
                                        print('obb_cls_kpt[obb_i][kpt_i]',obb_cls_kpt[obb_i][kpt_i])
                                        x = round(x / width, 6)
                                        y = round(y / heigth, 6)
                                        line[9 + 3 * (kpt_i + 1) - 3] = str(x)
                                        line[9 + 3 * (kpt_i + 1) - 2] = str(y)
                                        line[9 + 3 * (kpt_i + 1) - 1] = '2'

                    print('line', line)
                    str_line = ' '.join(line)
                    print('str_line', str_line)
                    f.write(str_line + "\n")
        f.close()


if __name__ == '__main__':
    obb_cls=['旋转框类别一','旋转框类别二','旋转框类别三']
    #对应某类别旋转框中关键点，比如旋转框类别一中有4个点，类别二中2个点，三中没有点
    obb_cls_kpt=[['1', '2', '3', '4'],[ 'point1', 'point2'],[]]
    # obb_cls_kpt = [[], [], []]
    json_root = r'D:\Dataset\jsons'  # COCO Object Instance 类型的标注
    ana_txt_save_path = r'D:\Dataset\labels'  # 保存的路径
    image_root=r'D:\Dataset\imgs'


    for filename in os.listdir(json_root):
        json_file=json_root+'\\'+filename
        data = json.load(open(json_file, 'r',encoding='utf-8'))

        image_file=image_root+'\\'+filename.split('.json')[0]+'.jpg'
        # if  os.path.exists(image_file)==False:
        image=cv2.imdecode(np.fromfile(image_file, dtype=np.uint8), -1)
        print(image.shape)
        print('image_file',image_file)
        width=image.shape[1]
        heigth=image.shape[0]
        if not os.path.exists(ana_txt_save_path):
            os.makedirs(ana_txt_save_path)

        save_txt(data,ana_txt_save_path,obb_cls_kpt,obb_cls,width,heigth)

标注格式为：cls+box+n*kpt
图片示例包括：3个类别+4个角点坐标+4个关键点（4x3)

四、运行命令

yolo obb_pose  mode=train model=ultralytics/cfg/models/v8/yolov8n-obb-pose.yaml  data=ultralytics/cfg/datasets/project/kpt/obb_kpt.yaml batch=8 epochs=100 imgsz=640 workers=0 device=0

 yolo task=obb_pose mode=predict model=runs/obb_pose/train/weights/best.pt  source=images/train