import cv2
import numpy as np
import osclass CaffeModelLoader:    @staticmethoddef load(proto, model):net = cv2.dnn.readNetFromCaffe(proto, model)return netclass FrameProcessor:    def __init__(self, size, scale, mean):self.size = sizeself.scale = scaleself.mean = meandef get_blob(self, frame):img = frame(h, w, c) = frame.shapeif w>h :dx = int((w-h)/2)img = frame[0:h, dx:dx+h]resized = cv2.resize(img, (self.size, self.size), cv2.INTER_AREA)blob = cv2.dnn.blobFromImage(resized, self.scale, (self.size, self.size), self.mean, False, False)return blobclass Utils:    @staticmethoddef draw_object(obj, label, color, frame):(confidence, (x1, y1, w, h)) =  objx2 = x1+wy2 = y1+hcv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)y3 = y1-12text = label + " " + str(confidence)+"%"cv2.putText(frame, text, (x1, y3), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 1, cv2.LINE_AA)@staticmethoddef draw_objects(objects, label, color, frame):for (i, obj) in enumerate(objects):Utils.draw_object(obj, label, color, frame)

CaffeModelLoader类使用为原型和模型文件提供的路径从磁盘加载Caffe模型。

class SSD:    def __init__(self, frame_proc, ssd_net):self.proc = frame_procself.net = ssd_netdef detect(self, frame):blob = self.proc.get_blob(frame)self.net.setInput(blob)detections = self.net.forward()# detected object countk = detections.shape[2]obj_data = []for i in np.arange(0, k):obj = detections[0, 0, i, :]obj_data.append(obj)return obj_datadef get_object(self, frame, data):confidence = int(data[2]*100.0)(h, w, c) = frame.shaper_x = int(data[3]*h)r_y = int(data[4]*h)r_w = int((data[5]-data[3])*h)r_h = int((data[6]-data[4])*h)if w>h :dx = int((w-h)/2)r_x = r_x+dxobj_rect = (r_x, r_y, r_w, r_h)return (confidence, obj_rect)def get_objects(self, frame, obj_data, class_num, min_confidence):objects = []for (i, data) in enumerate(obj_data):obj_class = int(data[1])obj_confidence = data[2]if obj_class==class_num and obj_confidence>=min_confidence :obj = self.get_object(frame, data)objects.append(obj)return objects

该类中的关键方法是detect和get_objects。

class VideoSSD:    def __init__(self, ssd):self.ssd = ssddef detect(self, video, class_num, min_confidence, class_name):detection_num = 0;capture = cv2.VideoCapture(video)img = Nonedname = 'Pest detections'cv2.namedWindow(dname, cv2.WINDOW_NORMAL)cv2.resizeWindow(dname, 1280, 960)# Capture all frameswhile(True):    (ret, frame) = capture.read()if frame is None:breakobj_data = self.ssd.detect(frame)class_objects = self.ssd.get_objects(frame, obj_data, class_num, min_confidence)p_count = len(class_objects)detection_num += p_countif len(class_objects)>0:Utils.draw_objects(class_objects, class_name, (0, 0, 255), frame)# Display the resulting framecv2.imshow(dname,frame)if cv2.waitKey(1) & 0xFF == ord('q'):breakcapture.release()cv2.destroyAllWindows()    return detection_num

该类中唯一的方法是detect。它处理从视频文件提取的所有帧。在每个框架中，它检测由class_num参数指定的类的所有对象，然后在检测到的对象周围显示带有边界矩形的框架。

proto_file = r"C:\PI_PEST\net\mobilenet.prototxt"
model_file = r"C:\PI_PEST\net\mobilenet.caffemodel"
ssd_net = CaffeModelLoader.load(proto_file, model_file)mobile_proc_frame_size = 300
ssd_proc = FrameProcessor(mobile_proc_frame_size, 1.0/127.5, 127.5)pest_class = 12
pest_name = "DOG"ssd = SSD(ssd_proc, ssd_net)video_file = r"C:\PI_PEST\video\dog_1.mp4"video_ssd = VideoSSD(ssd)
detections = video_ssd.detect(video_file, pest_class, 0.2, pest_name)

我们将pest_class值设置为12，因为“dog”是MobileNet SSD模型中的第12类。这是运行上述代码时捕获的视频。