diff --git a/BANK_atm/ATM_det_pipeline.py b/BANK_atm/ATM_det_pipeline.py new file mode 100644 index 0000000..e69de29 diff --git a/BANK_atm/cut_img_bbox.py b/BANK_atm/cut_img_bbox.py new file mode 100644 index 0000000..828b10d --- /dev/null +++ b/BANK_atm/cut_img_bbox.py @@ -0,0 +1,16 @@ + + +def cut_img_bbox(img,bbox): + + # blist = bbox.tolist() + + x_min = bbox[0] + y_min = bbox[1] + x_max = bbox[2] + y_max = bbox[3] + + obj_img = img[int(y_min):int(y_max), int(x_min):int(x_max)] #cv2裁剪出目标框中的图片 + #保存图片 + # cut_images = obj_img_path + '\\' + '%s_%s'%(img_name, count) + '.jpg' + + return obj_img \ No newline at end of file diff --git a/BANK_atm/mediapipe_det.py b/BANK_atm/mediapipe_det.py new file mode 100644 index 0000000..5977084 --- /dev/null +++ b/BANK_atm/mediapipe_det.py @@ -0,0 +1,42 @@ + +from mediapipe.python.solutions import drawing_utils + + + + + +def analysis_mediapipe(images,hands,parameter): + + results = hands.process(images) + + re_list = [] + + if results.multi_hand_landmarks: + for hand_landmarks in results.multi_hand_landmarks: + # print(hand_landmarks) + point_list = drawing_utils.draw_landmarks( + images, hand_landmarks, parameter) + + re_list.append(point_list) + + # print(re_list) + + return re_list + +# if __name__ == '__main__': + +# mp_drawing = drawing_utils +# mp_hands = hands +# frame = cv2.imread("E:/BANK_XZ/data_file/4654613.png") + # parameter = mp_hands.HAND_CONNECTIONS + +# hands = mp_hands.Hands( +# static_image_mode=True, +# max_num_hands=4, +# min_detection_confidence=0.1, +# min_tracking_confidence=0.1) + +# analysis_mediapipe(frame,hands) + + + diff --git a/BANK_atm/pipeline1.py b/BANK_atm/pipeline1.py new file mode 100644 index 0000000..39e093b --- /dev/null +++ b/BANK_atm/pipeline1.py @@ -0,0 +1,307 @@ +import cv2 +from tqdm import tqdm +from ultralytics import YOLO +from ultralytics.yolo.utils.plotting import Annotator +import os + +import cv2 +from mediapipe.python.solutions import drawing_utils +from mediapipe.python.solutions import hands +import time +import os +import queue +import threading + +from yolov8_det import analysis_yolov8 +from cut_img_bbox import cut_img_bbox +from mediapipe_det import analysis_mediapipe + + + + +class atm_det: + + def __init__(self,imgPath,savePath,modellist): + + self.imgPath = imgPath + self.savePath = savePath + + self.imgList = os.listdir(self.imgPath) + + #定义加载好的模型 + self.model_person = modellist[0] + self.model_pp_hand = modellist[1] + self.model_blue = modellist[2] + self.model_screen = modellist[3] + + self.media_hands = modellist[4] + + # 队列 + self.imgQueue1 = queue.Queue(maxsize=len(self.imgList)) + self.imgQueue2 = queue.Queue(maxsize=len(self.imgList)) + self.imgQueue3 = queue.Queue(maxsize=len(self.imgList)) + self.imgQueue4 = queue.Queue(maxsize=len(self.imgList)) + self.imgQueue5 = queue.Queue(maxsize=len(self.imgList)) + self.imgQueue6 = queue.Queue(maxsize=len(self.imgList)) + + #线程 + self.get_imgThread = threading.Thread(target=self.get_img) + self.get_person_resultThread = threading.Thread(target=self.get_person_result) + self.get_hand_landmarkerThread = threading.Thread(target=self.get_hand_landmarker) + self.get_blue_resultThread = threading.Thread(target=self.get_blue_result) + self.get_pph_resultThread = threading.Thread(target=self.get_pph_result) + self.analysis_handThread = threading.Thread(target=self.analysis_hand) + self.draw_imagesThread = threading.Thread(target=self.draw_images) + self.analysis_hand_blueThread = threading.Thread(target=self.analysis_hand_blue) + self.get_screen_resultThread = threading.Thread(target=self.get_screen_result) + + + + def get_img(self): + + for img in self.imgList: + + imgpath = os.path.join(self.imgPath,img) + images = cv2.imread(imgpath) + + imagesDict = {img:images} + + self.imgQueue1.put(imagesDict) + + + def get_person_result(self): + + while True: + + if ~self.imgQueue1.empty(): + + imagesDict = self.imgQueue1.get() + images = list(imagesDict.values())[0] + imgname = list(imagesDict.keys())[0] + + per_result = analysis_yolov8(images=images, + model_coco=self.model_person, + confidence=0.5 + ) + + for per in per_result: + + per_bbox = list(per.values())[0] + + imgcut = cut_img_bbox(images,per_bbox) + imgcutDict = {imgname:{"imgcut":imgcut,"per":per}} + + self.imgQueue2.put(imgcutDict) + + def get_blue_result(self): + while True: + + if ~self.imgQueue1.empty(): + + imagesDict = self.imgQueue1.get() + images = list(imagesDict.values())[0] + imgname = list(imagesDict.keys())[0] + + blue_result = analysis_yolov8(images=images, + model_coco=self.model_blue, + confidence=0.5 + ) + blues_list = [] + for blues in blue_result: + + blue = list(blues.values())[0] + blues_list.append(blue) + + if blues_list: + bluesDict = {imgname:blues_list} + + self.imgQueue4.put(bluesDict) + + def get_pph_result(self): + while True: + + if ~self.imgQueue1.empty(): + + imagesDict = self.imgQueue1.get() + images = list(imagesDict.values())[0] + imgname = list(imagesDict.keys())[0] + + blue_result = analysis_yolov8(images=images, + model_coco=self.model_pp_hand, + confidence=0.5 + ) + pph_list = [] + for blues in blue_result: + + blue = list(blues.values())[0] + pph_list.append(blue) + + if pph_list: + + pphDict = {imgname:pph_list} + self.imgQueue5.put(pphDict) + + def get_hand_landmarker(self): + while True: + + if ~self.imgQueue2.empty(): + + imgcutDict = self.imgQueue2.get() + + imgcut = list(imgcutDict.values())[0]["imgcut"] + + hand_landmarker_result = analysis_mediapipe(images=imgcut, + hands=self.media_hands, + parameter=hands.HAND_CONNECTIONS) + + handDict = {"hand_landmarker_result":hand_landmarker_result} + + list(imgcutDict.values())[0].update(handDict) + + self.imgQueue3.put(imgcutDict) + + + def get_screen_result(self): + while True: + if ~self.imgQueue1.empty(): + + imagesDict = self.imgQueue1.get() + images = list(imagesDict.values())[0] + imgname = list(imagesDict.keys())[0] + + screen_result = analysis_yolov8(images=images, + model_coco=self.model_screen, + confidence=0.5 + ) + print('screen_result:',screen_result) + + + def analysis_hand(self): + while True: + + if ~self.imgQueue3.empty(): + + imgcutDict2 = self.imgQueue3.get() + imgname = list(imgcutDict2.keys())[0] + + re_list = list(imgcutDict2.values())[0] + + pre_list = re_list['per'] + pre_list = list(pre_list.values())[0] + + # pre_x = int(pre_list[2] - pre_list[0]) + pre_x = int(pre_list[0]) + pre_y = int(pre_list[1]) + # pre_y = int(pre_list[3] - pre_list[1]) + + hand_list = re_list['hand_landmarker_result'] + + point_list = [] + for hand_point in hand_list: + + for point in hand_point: + # print(point) + + point_x = int(point[0]) + pre_x + point_y = int(point[1]) + pre_y + + point_list.append((point_x,point_y)) + + if point_list: + imgcutDict2.update({imgname:point_list}) + + self.imgQueue6.put(imgcutDict2) + + + def analysis_hand_blue(self): + while True: + if ~self.imgQueue4.empty() and ~self.imgQueue6.empty(): + + blue_list = self.imgQueue4.get() + hand_list = self.imgQueue6.get() + + print('blue_list:',blue_list) + print('hand_list:',hand_list) + + while list(blue_list.keys())[0] == list(hand_list.keys())[0]: + print(list(blue_list.keys())[0]) + + + + + + + + def draw_images(self): + while True: + if ~self.imgQueue6.empty(): + + img_hand_point = self.imgQueue6.get() + imgname = list(img_hand_point.keys())[0] + + img = cv2.imread(os.path.join(self.imgPath,imgname)) + + point_list = list(img_hand_point.values())[0] + + for point in point_list: + + cv2.circle(img, point, 1,(0,0,255), 2) + + cv2.imwrite(os.path.join(self.savePath,imgname),img) + + + + + + + def run(self): + + self.get_imgThread.start() + self.get_person_resultThread.start() + self.get_hand_landmarkerThread.start() + self.get_blue_resultThread.start() + # self.get_pph_resultThread.start() + self.analysis_handThread.start() + # self.draw_imagesThread.start() + self.analysis_hand_blueThread.start() + self.get_screen_resultThread.start() + + + +if __name__ == '__main__': + + + model_person = YOLO("model_files/bk1.pt") + model_pp_hand = YOLO("model_files/best_pph.pt") + model_blue = YOLO("model_files/best_butten.pt") + model_screen = YOLO("model_files/best_screen.pt") + + + media_hands = hands.Hands( + static_image_mode=True, + max_num_hands=4, + min_detection_confidence=0.1, + min_tracking_confidence=0.1) + + modelList = [model_person,model_pp_hand,model_blue,model_screen,media_hands] + + q = atm_det(imgPath='E:/BANK_XZ/data_file', + savePath='E:/BANK_XZ/output_data', + modellist=modelList) + + q.run() + + + + + + + + + + + + + + + diff --git a/BANK_atm/t.py b/BANK_atm/t.py new file mode 100644 index 0000000..be00104 --- /dev/null +++ b/BANK_atm/t.py @@ -0,0 +1,52 @@ +[{'imgcut': array([[[193, 194, 184], + [193, 194, 184], + [194, 198, 187], + ..., + [ 89, 92, 97], + [ 89, 92, 97], + [ 89, 92, 97]], + + [[189, 188, 178], + [190, 191, 181], + [193, 197, 186], + ..., + [ 89, 92, 97], + [ 89, 92, 97], + [ 89, 92, 97]], + + [[189, 187, 179], + [196, 195, 185], + [196, 197, 187], + ..., + [ 89, 92, 97], + [ 89, 92, 97], + [ 89, 92, 97]], + + ..., + + [[117, 131, 129], + [115, 131, 130], + [114, 132, 133], + ..., + [192, 189, 184], + [190, 191, 182], + [188, 191, 182]], + + [[115, 131, 130], + [116, 132, 131], + [115, 133, 134], + ..., + [193, 190, 185], + [191, 192, 183], + [189, 192, 183]], + + [[116, 132, 131], + [116, 132, 131], + [115, 133, 134], + ..., + [193, 190, 185], + [191, 192, 183], + [189, 192, 183]]], dtype=uint8), + 'per': {'wrong': [1006.59521484375, 429.05950927734375, 1710.3988037109375, 1078.1298828125]}, + 'hand_landmarker_result': [[(175, 136), (246, 38), (195, 35), (164, 44), (169, 99)]] + }] \ No newline at end of file diff --git a/BANK_atm/yolov8_det.py b/BANK_atm/yolov8_det.py new file mode 100644 index 0000000..b9139bf --- /dev/null +++ b/BANK_atm/yolov8_det.py @@ -0,0 +1,50 @@ +import cv2 +from tqdm import tqdm +from ultralytics import YOLO +from ultralytics.yolo.utils.plotting import Annotator +import os + +def analysis_yolov8(images, model_coco,confidence): + + frame = images + + # 第一步：用COCO数据集推理 + results_coco = model_coco(frame) + # print(results_coco) + + if results_coco: + + for r in results_coco: + + boxes = r.boxes + + re_list = [] + for box in boxes: + + b = box.xyxy[0] # get box coordinates in (top, left, bottom, right) format + c = box.cls + + # 保存标签和坐标值作为返回结果 + blist = b.tolist() + labels_name = model_coco.names[int(c)] + + confidence = float(box.conf) + + confidence = round(confidence, 2) + + # 过滤置信度0.5以下目标 + if confidence < confidence: + + continue + + re_dict = {labels_name:blist} + re_list.append(re_dict) + + return re_list + + +# if __name__ == '__main__': + +# model_coco = YOLO("model_files/bk1.pt") +# frame = cv2.imread("E:/BANK_XZ/data_file/0000162.jpg") +# analysis_video(frame, model_coco,confidence=0.5) \ No newline at end of file