Add files via upload

midpoint of bottom: (xc,yc)

Author: SebastianLevy

YOLO_Tracking.py

@@ -0,0 +1,38 @@
+import cv2
+import torch
+import numpy as np
+from ultralytics import YOLO
+
+
+model=YOLO('yolov8s.pt')
+
+
+sample_vids = ['CCTV_720p.mov', 'CCTV_1080p.mov', 'peopleCount.mp4']
+
+
+
+
+for vid in sample_vids:
+    # Capture video
+    cap = cv2.VideoCapture('SampleVideos/'+vid)
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Preprocess and model inference
+        results = model(frame)
+
+        # Filter for person class and extract midpoints
+        midpoints = []
+        for x1, y1, x2, y2, conf, cls in results.xyxy[0].numpy():
+            if int(cls) == 0:  # Person class
+                midpoint_x = (x1 + x2) / 2
+                midpoint_y = y2
+                midpoints.append((midpoint_x, midpoint_y))
+
+        # Further processing with midpoints
+
+    cap.release()
+    cv2.destroyAllWindows()

coco.txt

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorcycle
+airplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+couch
+potted plant
+bed
+dining table
+toilet
+tv
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

coco_person.txt

@@ -0,0 +1 @@
+person

main.py

@@ -0,0 +1,90 @@
+import cv2
+import pandas as pd
+import numpy as np
+from ultralytics import YOLO
+
+
+model=YOLO('yolov8s.pt')
+
+sample_vids = ['CCTV_720p.mov', 'CCTV_1080p.mov', 'peopleCount.mp4']
+
+vid = 'SampleVideos/' + sample_vids[1]
+
+area1=[(312,388),(289,390),(474,469),(497,462)]
+
+area2=[(279,392),(250,397),(423,477),(454,469)]
+def RGB(event, x, y, flags, param):
+    if event == cv2.EVENT_MOUSEMOVE :  
+        colorsBGR = [x, y]
+        print(colorsBGR)
+        
+
+cv2.namedWindow('RGB')
+cv2.setMouseCallback('RGB', RGB)
+
+cap=cv2.VideoCapture(vid)
+
+
+my_file = open("coco.txt", "r")
+data = my_file.read()
+class_list = data.split("\n") 
+#print(class_list)
+
+trackers = []
+count=0
+
+while True:    
+    ret, frame = cap.read()
+    if not ret:
+        break
+    count += 1
+    if count % 2 != 0:
+        continue
+    frame = cv2.resize(frame, (1020, 500))
+
+    results = model.predict(frame)
+
+    # Accessing the boxes, confidences, and class IDs
+    boxes = results[0].boxes.xyxy
+    confidences = results[0].boxes.conf
+    class_ids = results[0].boxes.cls
+
+    # Iterating through detections
+    for i in range(len(boxes)):
+        box = boxes[i]
+        confidence = confidences[i]
+        class_id = class_ids[i]
+
+        # Convert class_id to a Python integer
+        class_id = int(class_id)  # or class_id.item() if class_id is a single-element tensor
+
+        x1, y1, x2, y2 = map(int, box[:4])
+        xc = int((x1 + x2) / 2)
+        yc = y2
+
+        c = class_list[class_id]
+
+        if 'person' in c:
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            cv2.putText(frame, str(c), (x1, y1), cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 255, 255), 1)
+            cv2.circle(frame, (x1, y1), 5, (0, 0, 255), -1)  # Top-left in red
+            cv2.circle(frame, (x2, y1), 5, (0, 255, 0), -1)  # Top-right in green
+            cv2.circle(frame, (x1, y2), 5, (255, 0, 0), -1)  # Bottom-left in blue
+            cv2.circle(frame, (x2, y2), 5, (255, 255, 0), -1)  # Bottom-right in cyan
+            cv2.circle(frame, (xc, yc), 5, (255, 0, 255), -1)  # Bottom-Midpoint in pink
+            
+            
+        
+    cv2.polylines(frame,[np.array(area1,np.int32)],True,(255,0,0),2)
+    cv2.putText(frame,str('1'),(504,471),cv2.FONT_HERSHEY_COMPLEX,(0.5),(0,0,0),1)
+
+    cv2.polylines(frame,[np.array(area2,np.int32)],True,(255,0,0),2)
+    cv2.putText(frame,str('2'),(466,485),cv2.FONT_HERSHEY_COMPLEX,(0.5),(0,0,0),1)
+
+    cv2.imshow("RGB", frame)
+    if cv2.waitKey(1)&0xFF==27:
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+

peopleTracking.py

@@ -0,0 +1,67 @@
+import cv2
+import numpy as np
+import time
+
+# Load YOLO
+net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
+layer_names = net.getLayerNames()
+output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
+
+classes = []
+with open("coco.names", "r") as f:
+    classes = [line.strip() for line in f.readlines()]
+
+# Loading camera
+cap = cv2.VideoCapture(0)
+
+while True:
+    _, frame = cap.read()
+
+    height, width, channels = frame.shape
+
+    # Detecting objects
+    blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
+    net.setInput(blob)
+    outs = net.forward(output_layers)
+
+    # Showing informations on the screen
+    class_ids = []
+    confidences = []
+    boxes = []
+    for out in outs:
+        for detection in out:
+            scores = detection[5:]
+            class_id = np.argmax(scores)
+            confidence = scores[class_id]
+            if confidence > 0.5:
+                # Object detected
+                center_x = int(detection[0] * width)
+                center_y = int(detection[1] * height)
+                w = int(detection[2] * width)
+                h = int(detection[3] * height)
+
+                # Rectangle coordinates
+                x = int(center_x - w / 2)
+                y = int(center_y - h / 2)
+
+                boxes.append([x, y, w, h])
+                confidences.append(float(confidence))
+                class_ids.append(class_id)
+
+    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
+
+    for i in range(len(boxes)):
+        if i in indexes:
+            x, y, w, h = boxes[i]
+            label = str(classes[class_ids[i]])
+            if label == "person":
+                # Draw rectangle for person
+                cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+
+    cv2.imshow("Image", frame)
+    key = cv2.waitKey(1)
+    if key == 27: # ESC key to break
+        break
+
+cap.release()
+cv2.destroyAllWindows()

tracker.py

@@ -0,0 +1,50 @@
+import math
+
+
+class Tracker:
+    def __init__(self):
+        # Store the center positions of the objects
+        self.center_points = {}
+        # Keep the count of the IDs
+        # each time a new object id detected, the count will increase by one
+        self.id_count = 0
+
+
+    def update(self, objects_rect):
+        # Objects boxes and ids
+        objects_bbs_ids = []
+
+        # Get center point of new object
+        for rect in objects_rect:
+            x, y, w, h = rect
+            cx = (x + x + w) // 2
+            cy = (y + y + h) // 2
+
+            # Find out if that object was detected already
+            same_object_detected = False
+            for id, pt in self.center_points.items():
+                dist = math.hypot(cx - pt[0], cy - pt[1])
+
+                if dist < 35:
+                    self.center_points[id] = (cx, cy)
+#                    print(self.center_points)
+                    objects_bbs_ids.append([x, y, w, h, id])
+                    same_object_detected = True
+                    break
+
+            # New object is detected we assign the ID to that object
+            if same_object_detected is False:
+                self.center_points[self.id_count] = (cx, cy)
+                objects_bbs_ids.append([x, y, w, h, self.id_count])
+                self.id_count += 1
+
+        # Clean the dictionary by center points to remove IDS not used anymore
+        new_center_points = {}
+        for obj_bb_id in objects_bbs_ids:
+            _, _, _, _, object_id = obj_bb_id
+            center = self.center_points[object_id]
+            new_center_points[object_id] = center
+
+        # Update dictionary with IDs not used removed
+        self.center_points = new_center_points.copy()
+        return objects_bbs_ids