tracking

app.py

@@ -0,0 +1,156 @@
+# Ultralytics
+from ultralytics import YOLO
+import torch
+
+# Gradio
+import gradio as gr
+import moviepy.editor as moviepy
+
+
+# System and files
+import os
+import glob
+import uuid
+
+# Image manipulation
+import numpy as np
+import cv2
+
+print(torch.__version__)
+
+# Use GPU if available
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+else:
+    device = torch.device("cpu")
+
+os.system("nvidia-smi")
+
+print("[INFO]: Imported modules!")
+track_model = YOLO('yolov8n.pt')  # Load an official Detect model
+print("[INFO]: Downloaded models!")
+
+def check_extension(video):
+    split_tup = os.path.splitext(video)
+
+    # extract the file name and extension
+    file_name = split_tup[0]
+    file_extension = split_tup[1]
+
+    if file_extension != ".mp4":
+        print("Converting to mp4")
+        clip = moviepy.VideoFileClip(video)
+
+        video = file_name+".mp4"
+        clip.write_videofile(video)
+    
+    return video
+
+
+def tracking(video, model, boxes=True):
+    print("[INFO] Is cuda available? ", torch.cuda.is_available())
+    print(device)
+
+    print("[INFO] Loading model...")
+    # Load an official or custom model
+
+    # Perform tracking with the model
+    print("[INFO] Starting tracking!")
+    # https://docs.ultralytics.com/modes/predict/
+    annotated_frame = model(video, boxes=boxes, device=device)
+
+    return annotated_frame
+
+def show_tracking(video_content):
+
+        # https://docs.ultralytics.com/datasets/detect/coco/
+        video = cv2.VideoCapture(video_content)
+
+        # Track
+        video_track = tracking(video_content, track_model.track)
+
+        # Prepare to save video
+        #out_file = os.path.join(vis_out_dir, "track.mp4")
+        out_file = "track.mp4"
+        print("[INFO]: TRACK", out_file)
+
+        fourcc = cv2.VideoWriter_fourcc(*"mp4v")  # Codec for MP4 video
+        fps = video.get(cv2.CAP_PROP_FPS)
+        height, width, _ = video_track[0][0].orig_img.shape
+        size = (width,height)
+
+        out_track = cv2.VideoWriter(out_file, fourcc, fps, size)
+
+        # Go through frames and write them 
+        for frame_track in video_track:
+            result_track = frame_track[0].plot()  # plot a BGR numpy array of predictions
+            out_track.write(result_track)
+
+        print("[INFO] Done with frames")
+        #print(type(result_pose)) numpy ndarray
+    
+        out_track.release()
+
+        video.release()
+        cv2.destroyAllWindows() # Closing window
+
+        return out_file
+
+block = gr.Blocks()
+with block:
+    with gr.Column():       
+        with gr.Tab("Upload video"):
+            with gr.Column():
+                with gr.Row():
+                    with gr.Column():
+                        video_input = gr.Video(source="upload", type="filepath", height=612)
+                        with gr.Row():
+                            submit_detect_file = gr.Button("Detect and track objects", variant="primary")
+
+                with gr.Row():
+                    video_output4 = gr.Video(height=512, label = "Detection and tracking", show_label=True, format="mp4")
+
+        with gr.Tab("Record video with webcam"):
+            
+            with gr.Column():
+                with gr.Row():
+                    with gr.Column():
+                        webcam_input = gr.Video(source="webcam", height=612)
+                        
+                        with gr.Row():
+                            submit_detect_web = gr.Button("Detect and track objects", variant="primary")
+                with gr.Row():
+                    webcam_output4 = gr.Video(height=716, label = "Detection and tracking", show_label=True, format="mp4")
+
+        with gr.Tab("General information"):
+            gr.Markdown(""" 
+                        \n # Information about the models 
+
+                        \n ## Detection and tracking:                            
+                        
+                        \n The tracking method in the Ultralight's YOLOv8 model is used for object tracking in videos. It takes a video file or a camera stream as input and returns the tracked objects in each frame. The method uses the COCO dataset classes for object detection and tracking. 
+                        
+                        \n The COCO dataset contains 80 classes of objects such as person, car, bicycle, etc. See https://docs.ultralytics.com/datasets/detect/coco/ for all available classes. The tracking method uses the COCO classes to detect and track the objects in the video frames. The tracked objects are represented as bounding boxes with labels indicating the class of the object.""")
+            gr.Markdown("You can load the keypoints in python in the following way: ")
+
+
+        # From file        
+        submit_detect_file.click(fn=show_tracking, 
+                                inputs= video_input, 
+                                outputs = video_output4,
+                                queue=False)
+        
+    
+        submit_detect_web.click(fn=show_tracking, 
+                                inputs= webcam_input, 
+                                outputs = webcam_output4,
+                                queue=False)
+
+
+if __name__ == "__main__":
+    block.queue(#concurrency_count=5, # When you increase the concurrency_count parameter in queue(), max_threads() in launch() is automatically increased as well.
+                #max_size=25, # Maximum number of requests that the queue processes
+                api_open = False # When creating a Gradio demo, you may want to restrict all traffic to happen through the user interface as opposed to the programmatic API that is automatically created for your Gradio demo.  
+                    ).launch()
+
+

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+numpy
+opencv-python
+ultralytics
+lap
+MoviePy
+torch
+torchvision