技術標籤：DeepLearning深度學習計算機視覺

直接呼叫pytorch中的faster rcnn

會呼叫到下面的庫

from PIL import Image
from torchvision.transforms import transforms as T
import cv2
from matplotlib import pyplot as plt
from torchvision.models.detection.faster_rcnn import fasterrcnn_resnet50_fpn

分類的類別

COCO_INSTANCE_CATEGORY_NAMES = [
 

    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack'
 
, 'umbrella', 'N/A', 'N/A',
    'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
    'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
    'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
    'banana', 'apple', 'sandwich'
 
, 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
    'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
    'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]

讀入圖片，讓圖片通過模型，得到class，boxes和score

def get_prediction(img_path, threshold):
    img = Image.open(img_path)
    transform = T.Compose([T.ToTensor()])
    img = transform(img)
    pred = model([img])
    pred_class = [COCO_INSTANCE_CATEGORY_NAMES[i] for i in list(pred[0]['labels'].numpy())]
    pred_boxes = [[(i[0],i[1]), (i[2],i[3])] for i in list(pred[0]['boxes'].detach().numpy())]
    pred_score = list(pred[0]['scores'].detach().numpy())
    pred_t = [pred_score.index(x) for x in pred_score if x > threshold][-1]
    pred_boxes = pred_boxes[:pred_t+1]
    pred_class = pred_class[:pred_t+1]
    return pred_boxes, pred_class

把結果的目標框畫出來

def object_detection(img_path, threshold=0.5, rect_th=3, text_size=3, text_th=3):
    boxes, pred_cls = get_prediction(img_path, threshold)
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    for i in range(len(boxes)):

        cv2.rectangle(img, boxes[i][0], boxes[i][1], color=(0, 255, 0), thickness=rect_th)
        cv2.putText(img, pred_cls[i], boxes[i][0], cv2.FONT_HERSHEY_SIMPLEX, text_size, (0,255,0), thickness=text_th)
        plt.figure(figsize=(20, 30))
        #cv2.imshow('img', img)
        #cv2.waitKey(0)
        #
        plt.imshow(img)
        plt.xticks([])
        plt.yticks([])
        plt.show()

用PennPed資料集中的一張圖片做測試

測試圖片是這樣的

if __name__ == '__main__':
    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
    model.eval()
   
    object_detection('your folder/PennPed00096.png', threshold=0.8)

測試結果，整體效果不錯

參考資料