init

app.py

@@ -0,0 +1,184 @@
+import gradio as gr
+import numpy as np
+import cv2
+from ultralytics import YOLO
+from util.sort import Sort
+import time
+import psutil
+import tempfile
+import os
+from pathlib import Path
+
+def get_yolo_models():
+    models = {
+        'YOLOv8': ['n', 'm', 'x'],
+        'YOLOv9': ['t', 'm', 'e'],  # as of 2024
+        'YOLOv10': ['-N', '-M', '-X'],    
+        'YOLO11': ['n', 'm', 'x']   
+    }
+    
+    choices = []
+    for version, sizes in models.items():
+        v_num = version[4:]  # extract number
+        choices.extend([f"{version}{size}.pt" for size in sizes])
+    return choices
+
+def process_video(video_path, model_choice):
+    # Create temporary directory for outputs
+    temp_dir = tempfile.mkdtemp()
+    output_video_path = os.path.join(temp_dir, "output.mp4")
+    faces_dir = os.path.join(temp_dir, "faces")
+    os.makedirs(faces_dir, exist_ok=True)
+    
+    # Initialize models and tracker
+    model = YOLO(model_choice)
+    tracker = Sort()
+    all_tracked_ids = set()
+    face_images = []
+    
+    # Start timing and resource monitoring
+    start_time = time.time()
+    initial_memory = psutil.Process().memory_info().rss / 1024 / 1024  # MB
+    
+    # Video processing setup
+    cap = cv2.VideoCapture(video_path)
+    fps = int(cap.get(cv2.CAP_PROP_FPS))
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    
+    # Create video writer
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_video_path, fourcc, fps, (width, height))
+    
+    frame_count = 0
+    face_count = 0
+    
+    start_time = time.time()
+    while cap.isOpened():
+        status, frame = cap.read()
+        if not status:
+            break
+
+        elapsed_time = time.time() - start_time
+        print(f'time elapsed: {elapsed_time}')
+        if elapsed_time >= 60: break
+            
+        frame_count += 1
+        
+        # Create dark overlay for text
+        overlay_height = 80
+        overlay = frame.copy()
+        overlay[:overlay_height] = (0, 0, 0)
+        cv2.addWeighted(overlay, 0.5, frame, 0.5, 0, frame)
+        
+        results = model(frame, stream=True)
+        
+        for res in results:
+            detections = res.boxes.cpu().numpy()
+            person_indices = np.where((detections.cls == 0) & (detections.conf > 0.3))[0]
+            
+            if len(person_indices) > 0:
+                person_boxes = detections.xyxy[person_indices].astype(int)
+                tracks = tracker.update(person_boxes)
+                tracks = tracks.astype(int)
+                
+                current_ids = set(tracks[:, 4])
+                all_tracked_ids.update(current_ids)
+                
+                # Save face crops (simplified - using upper portion of bounding box)
+                for xmin, ymin, xmax, ymax, track_id in tracks:
+                    face_height = int((ymax - ymin) * 0.3)  # Take top 30% as face
+                    face_crop = frame[ymin:ymin+face_height, xmin:xmax]
+                    if face_crop.size > 0:  # Check if crop is valid
+                        face_path = os.path.join(faces_dir, f"face_{track_id}.jpg")
+                        if not os.path.exists(face_path):  # Save only first occurrence
+                            cv2.imwrite(face_path, face_crop)
+                            face_images.append(face_path)
+                            face_count += 1
+                
+                # Draw tracking info
+                cv2.putText(frame, f"Current People: {len(tracks)}", (20, 35),
+                           cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+                cv2.putText(frame, f"Total People: {len(all_tracked_ids)}", (20, 70),
+                           cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+                
+                for xmin, ymin, xmax, ymax, track_id in tracks:
+                    cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), (0, 255, 0), 2)
+                    cv2.putText(frame, f"Person #{track_id}", (xmin, ymin - 10),
+                              cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
+            
+            else:
+                cv2.putText(frame, "Current People: 0", (20, 35),
+                           cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+                cv2.putText(frame, f"Total People: {len(all_tracked_ids)}", (20, 70),
+                           cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+        
+        out.write(frame)
+    
+    # Cleanup
+    cap.release()
+    out.release()
+    
+    # Calculate statistics
+    end_time = time.time()
+    process_time = end_time - start_time
+    final_memory = psutil.Process().memory_info().rss / 1024 / 1024
+    memory_used = final_memory - initial_memory
+    cpu_percent = psutil.Process().cpu_percent()
+    
+    # Prepare statistics text
+    stats = f"""
+    Processing Statistics:
+    ---------------------
+    Total People Detected: {len(all_tracked_ids)}
+    Total Frames Processed: {frame_count}
+    Processing Time: {process_time:.2f} seconds
+    FPS: {frame_count/process_time:.2f}
+    CPU Usage: {cpu_percent:.1f}%
+    Memory Usage: {memory_used:.1f} MB
+    Faces Captured: {face_count}
+    """
+    
+    return stats, output_video_path, face_images
+
+# Create Gradio interface
+with gr.Blocks(title="Person Tracking System") as demo:
+    gr.Markdown("# Person Tracking and Analysis System")
+    
+    with gr.Row():
+        with gr.Column():
+            video_input = gr.Video(label="Upload Video (Max. 30 seconds)")
+            model_choice = gr.Dropdown(
+                choices=get_yolo_models(),
+                value=0,
+                label="Select YOLO Model"
+            )
+            submit_btn = gr.Button("Process Video")
+        
+        with gr.Column():
+            stats_output = gr.Textbox(
+                label="Processing Statistics",
+                lines=10,
+                interactive=False
+            )
+    
+    with gr.Row():
+        video_output = gr.Video(label="Processed Video")
+        gallery_output = gr.Gallery(
+            label="Detected Faces",
+            show_label=True,
+            elem_id="gallery",
+            columns=5,
+            rows=2
+        )
+    
+    submit_btn.click(
+        fn=process_video,
+        inputs=[video_input, model_choice],
+        outputs=[stats_output, video_output, gallery_output]
+    )
+
+# Launch the interface
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,70 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+contourpy==1.3.1
+cycler==0.12.1
+fastapi==0.115.5
+ffmpy==0.4.0
+filelock==3.16.1
+filterpy==1.4.5
+fonttools==4.55.0
+fsspec==2024.10.0
+gradio==5.6.0
+gradio_client==1.4.3
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+Jinja2==3.1.4
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==1.26.4
+opencv-python==4.10.0.84
+orjson==3.10.11
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+psutil==6.1.0
+py-cpuinfo==9.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.2.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.9.4
+ruff==0.7.4
+safehttpx==0.1.1
+scipy==1.14.1
+seaborn==0.13.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.41.3
+sympy==1.13.3
+tomlkit==0.12.0
+torch==2.2.2
+torchvision==0.17.2
+tqdm==4.67.0
+typer==0.13.1
+typing_extensions==4.12.2
+tzdata==2024.2
+ultralytics==8.3.33
+ultralytics-thop==2.0.11
+urllib3==2.2.3
+uvicorn==0.32.0
+websockets==12.0

util/sort.py

@@ -0,0 +1,248 @@
+"""
+    SORT: A Simple, Online and Realtime Tracker
+    Copyright (C) 2016-2020 Alex Bewley alex@bewley.ai
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+"""
+from __future__ import print_function
+
+import os
+import numpy as np
+from filterpy.kalman import KalmanFilter
+
+np.random.seed(0)
+
+
+def linear_assignment(cost_matrix):
+    try:
+        import lap
+        _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
+        return np.array([[y[i], i] for i in x if i >= 0])  #
+    except ImportError:
+        from scipy.optimize import linear_sum_assignment
+        x, y = linear_sum_assignment(cost_matrix)
+        return np.array(list(zip(x, y)))
+
+
+def iou_batch(bb_test, bb_gt):
+    """
+    From SORT: Computes IOU between two bboxes in the form [x1,y1,x2,y2]
+    """
+    bb_gt = np.expand_dims(bb_gt, 0)
+    bb_test = np.expand_dims(bb_test, 1)
+
+    xx1 = np.maximum(bb_test[..., 0], bb_gt[..., 0])
+    yy1 = np.maximum(bb_test[..., 1], bb_gt[..., 1])
+    xx2 = np.minimum(bb_test[..., 2], bb_gt[..., 2])
+    yy2 = np.minimum(bb_test[..., 3], bb_gt[..., 3])
+    w = np.maximum(0., xx2 - xx1)
+    h = np.maximum(0., yy2 - yy1)
+    wh = w * h
+    o = wh / ((bb_test[..., 2] - bb_test[..., 0]) * (bb_test[..., 3] - bb_test[..., 1])
+              + (bb_gt[..., 2] - bb_gt[..., 0]) * (bb_gt[..., 3] - bb_gt[..., 1]) - wh)
+    return (o)
+
+
+def convert_bbox_to_z(bbox):
+    """
+    Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form
+      [x,y,s,r] where x,y is the centre of the box and s is the scale/area and r is
+      the aspect ratio
+    """
+    w = bbox[2] - bbox[0]
+    h = bbox[3] - bbox[1]
+    x = bbox[0] + w / 2.
+    y = bbox[1] + h / 2.
+    s = w * h  # scale is just area
+    r = w / float(h)
+    return np.array([x, y, s, r]).reshape((4, 1))
+
+
+def convert_x_to_bbox(x, score=None):
+    """
+    Takes a bounding box in the centre form [x,y,s,r] and returns it in the form
+      [x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the bottom right
+    """
+    w = np.sqrt(x[2] * x[3])
+    h = x[2] / w
+    if (score == None):
+        return np.array([x[0] - w / 2., x[1] - h / 2., x[0] + w / 2., x[1] + h / 2.]).reshape((1, 4))
+    else:
+        return np.array([x[0] - w / 2., x[1] - h / 2., x[0] + w / 2., x[1] + h / 2., score]).reshape((1, 5))
+
+
+class KalmanBoxTracker(object):
+    """
+    This class represents the internal state of individual tracked objects observed as bbox.
+    """
+    count = 0
+
+    def __init__(self, bbox):
+        """
+        Initialises a tracker using initial bounding box.
+        """
+        # define constant velocity model
+        self.kf = KalmanFilter(dim_x=7, dim_z=4)
+        self.kf.F = np.array(
+            [[1, 0, 0, 0, 1, 0, 0], [0, 1, 0, 0, 0, 1, 0], [0, 0, 1, 0, 0, 0, 1], [0, 0, 0, 1, 0, 0, 0],
+             [0, 0, 0, 0, 1, 0, 0], [0, 0, 0, 0, 0, 1, 0], [0, 0, 0, 0, 0, 0, 1]])
+        self.kf.H = np.array(
+            [[1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 0, 0], [0, 0, 1, 0, 0, 0, 0], [0, 0, 0, 1, 0, 0, 0]])
+
+        self.kf.R[2:, 2:] *= 10.
+        self.kf.P[4:, 4:] *= 1000.  # give high uncertainty to the unobservable initial velocities
+        self.kf.P *= 10.
+        self.kf.Q[-1, -1] *= 0.01
+        self.kf.Q[4:, 4:] *= 0.01
+
+        self.kf.x[:4] = convert_bbox_to_z(bbox)
+        self.time_since_update = 0
+        self.id = KalmanBoxTracker.count
+        KalmanBoxTracker.count += 1
+        self.history = []
+        self.hits = 0
+        self.hit_streak = 0
+        self.age = 0
+
+    def update(self, bbox):
+        """
+        Updates the state vector with observed bbox.
+        """
+        self.time_since_update = 0
+        self.history = []
+        self.hits += 1
+        self.hit_streak += 1
+        self.kf.update(convert_bbox_to_z(bbox))
+
+    def predict(self):
+        """
+        Advances the state vector and returns the predicted bounding box estimate.
+        """
+        if ((self.kf.x[6] + self.kf.x[2]) <= 0):
+            self.kf.x[6] *= 0.0
+        self.kf.predict()
+        self.age += 1
+        if (self.time_since_update > 0):
+            self.hit_streak = 0
+        self.time_since_update += 1
+        self.history.append(convert_x_to_bbox(self.kf.x))
+        return self.history[-1]
+
+    def get_state(self):
+        """
+        Returns the current bounding box estimate.
+        """
+        return convert_x_to_bbox(self.kf.x)
+
+
+def associate_detections_to_trackers(detections, trackers, iou_threshold=0.3):
+    """
+    Assigns detections to tracked object (both represented as bounding boxes)
+
+    Returns 3 lists of matches, unmatched_detections and unmatched_trackers
+    """
+    if (len(trackers) == 0):
+        return np.empty((0, 2), dtype=int), np.arange(len(detections)), np.empty((0, 5), dtype=int)
+
+    iou_matrix = iou_batch(detections, trackers)
+
+    if min(iou_matrix.shape) > 0:
+        a = (iou_matrix > iou_threshold).astype(np.int32)
+        if a.sum(1).max() == 1 and a.sum(0).max() == 1:
+            matched_indices = np.stack(np.where(a), axis=1)
+        else:
+            matched_indices = linear_assignment(-iou_matrix)
+    else:
+        matched_indices = np.empty(shape=(0, 2))
+
+    unmatched_detections = []
+    for d, det in enumerate(detections):
+        if (d not in matched_indices[:, 0]):
+            unmatched_detections.append(d)
+    unmatched_trackers = []
+    for t, trk in enumerate(trackers):
+        if (t not in matched_indices[:, 1]):
+            unmatched_trackers.append(t)
+
+    # filter out matched with low IOU
+    matches = []
+    for m in matched_indices:
+        if (iou_matrix[m[0], m[1]] < iou_threshold):
+            unmatched_detections.append(m[0])
+            unmatched_trackers.append(m[1])
+        else:
+            matches.append(m.reshape(1, 2))
+    if (len(matches) == 0):
+        matches = np.empty((0, 2), dtype=int)
+    else:
+        matches = np.concatenate(matches, axis=0)
+
+    return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
+
+
+class Sort(object):
+    def __init__(self, max_age=1, min_hits=3, iou_threshold=0.3):
+        """
+        Sets key parameters for SORT
+        """
+        self.max_age = max_age
+        self.min_hits = min_hits
+        self.iou_threshold = iou_threshold
+        self.trackers = []
+        self.frame_count = 0
+
+    def update(self, dets=np.empty((0, 5))):
+        """
+        Params:
+          dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...]
+        Requires: this method must be called once for each frame even with empty detections (use np.empty((0, 5)) for frames without detections).
+        Returns the a similar array, where the last column is the object ID.
+
+        NOTE: The number of objects returned may differ from the number of detections provided.
+        """
+        self.frame_count += 1
+        # get predicted locations from existing trackers.
+        trks = np.zeros((len(self.trackers), 5))
+        to_del = []
+        ret = []
+        for t, trk in enumerate(trks):
+            pos = self.trackers[t].predict()[0]
+            trk[:] = [pos[0], pos[1], pos[2], pos[3], 0]
+            if np.any(np.isnan(pos)):
+                to_del.append(t)
+        trks = np.ma.compress_rows(np.ma.masked_invalid(trks))
+        for t in reversed(to_del):
+            self.trackers.pop(t)
+        matched, unmatched_dets, unmatched_trks = associate_detections_to_trackers(dets, trks, self.iou_threshold)
+
+        # update matched trackers with assigned detections
+        for m in matched:
+            self.trackers[m[1]].update(dets[m[0], :])
+
+        # create and initialise new trackers for unmatched detections
+        for i in unmatched_dets:
+            trk = KalmanBoxTracker(dets[i, :])
+            self.trackers.append(trk)
+        i = len(self.trackers)
+        for trk in reversed(self.trackers):
+            d = trk.get_state()[0]
+            if (trk.time_since_update < 1) and (trk.hit_streak >= self.min_hits or self.frame_count <= self.min_hits):
+                ret.append(np.concatenate((d, [trk.id + 1])).reshape(1, -1))  # +1 as MOT benchmark requires positive
+            i -= 1
+            # remove dead tracklet
+            if (trk.time_since_update > self.max_age):
+                self.trackers.pop(i)
+        if (len(ret) > 0):
+            return np.concatenate(ret)
+        return np.empty((0, 5))