model3.py

from model1 import reader, np, YOLO, car_detection, lp_detection
import torch
from PIL import Image
import cv2
from torchvision import transforms

char_dect = YOLO("models/yolov8n_lpchar_det.pt")
char_rec = torch.load("models/charrec.pt", map_location="cpu")

# function to detect cars in the given image
def detect_cars(inputs):
    cars = []
    # running the cars detection model with 50% confidence threshold
    car_results = car_detection.predict(source=inputs, classes=[2], conf=0.5, verbose=False)
    # iterating through each output (num of outputs will be same as num of inputs)
    for car_result in car_results:       
        # finding the bounding boxes of the cars detected
        boxes = car_result.boxes.xyxy.tolist()    
        # iterating through each car detected
        for box in boxes:
            # cropping car image from the input image
            car = car_result.orig_img[int(box[1]):int(box[3]), int(box[0]):int(box[2])]
            cars.append(car)            
    return cars

# function to detect licence plates in the given car images
def detect_lp(inputs):
    lps = []
    # running the license plate detection model with 50% confidence threshold
    lp_results = lp_detection.predict(source=inputs, conf=0.5, verbose=False)
    # iterating through each output (num of outputs will be same as num of inputs)
    for lp_result in lp_results:
        # finding the bounding boxes of the license plate detected
        lp_boxes = lp_result.boxes.xyxy.tolist()    
        # iterating through each license plate detected
        for lp_box in lp_boxes:
            # cropping license plate  image from the car image
            lp = lp_result.orig_img[int(lp_box[1]):int(lp_box[3]), int(lp_box[0]):int(lp_box[2])]
            lps.append(lp)
            # breaking as we only want to detect one licence plate per car
            break
        
        # if no licence plate is detected then we are adding a black image 
        if len(lp_boxes) == 0:
            lps.append(np.zeros((100,100,3), np.uint8))
            
    return lps

# function to detect licence plates character in the given LP images
def chars_lp_det(inputs):
    vis_lp = []
    chars = []
    # running the license plate detection model with 50% confidence threshold
    chars_results = char_dect.predict(source=inputs, conf=0.5, verbose=False)
    # iterating through each output (num of outputs will be same as num of inputs)
    for chars_result in chars_results:
        # finding the bounding boxes of the license plate detected
        chars_boxes = chars_result.boxes.xyxy.tolist()    
        # iterating through each license plate detected
        vis = chars_result.orig_img.copy()
        c_list  =[]
        for chars_box in chars_boxes:
            # cropping license plate  image from the car image
            cv2.rectangle(vis, (int(chars_box[0]),int(chars_box[1])), (int(chars_box[2]), int(chars_box[3])), (0,255,0), 1)
            chrs = chars_result.orig_img[int(chars_box[1]):int(chars_box[3]), int(chars_box[0]):int(chars_box[2])]            
            c_list.append(chrs)

        chars.append(c_list)
        vis_lp.append(vis)
        # if no licence plate is detected then we are adding a black image 
        if len(vis_lp) == 0:
            vis_lp.append(np.zeros((100,100,3), np.uint8))
            
    return vis_lp, chars

# function to detect licence plate number in the given licence plate images
def detect_lp_text(inputs):
    plate_number = []
    # iterating through each licence plate
    for input in inputs:
        # finding the number/text in licence plate
        result = reader.readtext(input)

        # if no text is found in the licence plate, then adding a default text not found
        if len(result) == 0:
            plate_number.append("not found")
        else:
            # adding the licence plate number to a list
            plate_number.append(result[0][1])
            
    return plate_number

def rec_lp_char(inputs):
    m = ['0','1','2','3','4','5','6','7','8','9','A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']
    transform = transforms.Compose([
        transforms.Resize((224, 224)),
        transforms.ToTensor(),
    ])
    lptexts = []
    for input in inputs:
        imgs = [transform(Image.fromarray(input[i])) for i in range(len(input))]
        if len(imgs) <= 1:
            lptexts.append("not found") 
            continue
        imgs = torch.stack(imgs)
        output = char_rec(imgs)
        preds = torch.argmax(output, dim=1).tolist()
        lptext = ""
        for pred in preds:
            lptext += m[int(pred)]
        lptexts.append(lptext)
    return lptexts
        

def run(inputs):
        
    # for future, to handle multiple inputs
    # currently using just one input
    inputs = inputs[0]
    
    # detecting cars, this function returns all detected car images
    cars = detect_cars(inputs)
    
    # if no car is detected black images are returned
    if len(cars) == 0:
        return [np.zeros((100,100,3), np.uint8)], [np.zeros((100,100,3), np.uint8)], "not found"
    
    # detecting licence plates from the car images
    # returns licence plate images, if it cant find a license plate a black image is returned
    lps = detect_lp(cars)
    
    vis_lp, chars_lp = chars_lp_det(lps)
    
    
    lptexts = rec_lp_char(chars_lp)
    
    # detecting licence plate number from licence plate images
    # returns text from the licence plate images, if none is detected "not found" text is returned
    # lp_text = detect_lp_text(lps)
        
    
    return cars, vis_lp, lptexts