城市管理违规行为智能识别_baseline学习心得

1、输入数据：

数据为城管视频监控，违规行为包括垃圾桶满溢、机动车违停、非机动车违停等

标注文件为json，包括违规行为帧编号，违规行为id，违规行为类别和bbox

2、代码部分：

!/opt/miniconda/bin/pip install opencv-python pandas matplotlib ultralytics

pip install各种需要用到的包

在第3 个cell下载数据并解压

第6个cell

video_path = '训练集(有标注第一批)/视频/45.mp4'
cap = cv2.VideoCapture(video_path)
while True:
    # 读取下一帧
    ret, frame = cap.read()
    if not ret:
        break
    break    

使用cv2.VideoCapture读取帧，ret是一个bool，表示是否成功读取，frame是帧信息

第8-9个cell：

int(cap.get(cv2.CAP_PROP_FRAME_COUNT))

# 结果：422

bbox = [746, 494, 988, 786]

pt1 = (bbox[0], bbox[1])
pt2 = (bbox[2], bbox[3])

color = (0, 255, 0) 
thickness = 2  # 线条粗细

cv2.rectangle(frame, pt1, pt2, color, thickness)

frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
plt.imshow(frame)

cap.get(cv2.CAP_PROP_FRAME_COUNT)获取帧数信息

cell 9 是把该帧上的框画出来并展示

cell10：创建yolo的yaml配置文件

if not os.path.exists('yolo-dataset/'):
    os.mkdir('yolo-dataset/')
if not os.path.exists('yolo-dataset/train'):
    os.mkdir('yolo-dataset/train')
if not os.path.exists('yolo-dataset/val'):
    os.mkdir('yolo-dataset/val')

dir_path = os.path.abspath('./') + '/'

# 需要按照你的修改path
with open('yolo-dataset/yolo.yaml', 'w', encoding='utf-8') as up:
    up.write(f'''
path: {dir_path}/yolo-dataset/
train: train/
val: val/

names:
    0: 非机动车违停
    1: 机动车违停
    2: 垃圾桶满溢
    3: 违法经营
''')

cell11：

train_annos = glob.glob('训练集(有标注第一批)/标注/*.json')
train_videos = glob.glob('训练集(有标注第一批)/视频/*.mp4')
train_annos.sort(); train_videos.sort();

category_labels = ["非机动车违停", "机动车违停", "垃圾桶满溢", "违法经营"]

train_annos, train_videos存储了标注和视频信息，并排序使得其一一对应 

cell12：

#用zip把前五个标注和视频配对，
for anno_path, video_path in zip(train_annos[:5], train_videos[:5]):
    print(video_path)
    anno_df = pd.read_json(anno_path)
    cap = cv2.VideoCapture(video_path)
    frame_idx = 0 
    #并且逐帧处理视频，
    while True:
        ret, frame = cap.read()
        if not ret:
            break

        img_height, img_width = frame.shape[:2]
        #根据帧索引找到标注数据，
        frame_anno = anno_df[anno_df['frame_id'] == frame_idx]
        #将每一帧图像保存为jpg，
        cv2.imwrite('./yolo-dataset/train/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.jpg', frame)

        if len(frame_anno) != 0:
            #并且生成标签保存标注的类别和边框
            with open('./yolo-dataset/train/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.txt', 'w') as up:
                for category, bbox in zip(frame_anno['category'].values, frame_anno['bbox'].values):
                    category_idx = category_labels.index(category)
                    
                    x_min, y_min, x_max, y_max = bbox
                    x_center = (x_min + x_max) / 2 / img_width
                    y_center = (y_min + y_max) / 2 / img_height
                    width = (x_max - x_min) / img_width
                    height = (y_max - y_min) / img_height

                    if x_center > 1:
                        print(bbox)
                    up.write(f'{category_idx} {x_center} {y_center} {width} {height}\n')
        
        frame_idx += 1

用zip把前五个标注和视频配对，并且逐帧处理视频，根据帧索引找到标注数据，将每一帧图像保存为jpeg，并且生成标签保存标注的类别和边框

cell14、15

# 下载预训练yolov8模型
!wget http://mirror.coggle.club/yolo/yolov8n-v8.2.0.pt -O yolov8n.pt

#下载字体
!mkdir -p ~/.config/Ultralytics/
!wget http://mirror.coggle.club/yolo/Arial.ttf -O ~/.config/Ultralytics/Arial.ttf

cell16

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"

import warnings
warnings.filterwarnings('ignore')


from ultralytics import YOLO
model = YOLO("yolov8n.pt")
results = model.train(data="yolo-dataset/yolo.yaml", epochs=2, imgsz=1080, batch=16)

训练模型

cell18

from ultralytics import YOLO
# 加载yolo模型
model = YOLO("runs/detect/train/weights/best.pt")
import glob

# 遍历视频文件
for path in glob.glob('测试集/*.mp4'):
    submit_json = []
    # 使用模型进行目标检测
    results = model(path, conf=0.05, imgsz=1080,  verbose=False)

    # 对每一帧检测结果进行处理
    for idx, result in enumerate(results):
        # 提取边界框、类别、概率等等
        boxes = result.boxes  # Boxes object for bounding box outputs
        masks = result.masks  # Masks object for segmentation masks outputs
        keypoints = result.keypoints  # Keypoints object for pose outputs
        probs = result.probs  # Probs object for classification outputs
        obb = result.obb  # Oriented boxes object for OBB outputs

        if len(boxes.cls) == 0:
            continue
        
        xywh = boxes.xyxy.data.cpu().numpy().round()
        cls = boxes.cls.data.cpu().numpy().round()
        conf = boxes.conf.data.cpu().numpy()

        # 将结果保存为json
        for i, (ci, xy, confi) in enumerate(zip(cls, xywh, conf)):
            submit_json.append(
                {
                    'frame_id': idx,
                    'event_id': i+1,
                    'category': category_labels[int(ci)],
                    'bbox': list([int(x) for x in xy]),
                    "confidence": float(confi)
                }
            )

    with open('./result/' + path.split('/')[-1][:-4] + '.json', 'w', encoding='utf-8') as up:
        json.dump(submit_json, up, indent=4, ensure_ascii=False)

3、心得：虽然是一键运行的代码，但是不代表可以点一个运行就算结束。之前没有玩过yolo和目标检测，这次对目标检测有了一个初步的认识，也对训练流程有了个大致的理解。接下来打算抽空学习学习各种yolo模型和其他目标检测模型