MOT tracking component added to gradio app

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
 from classify_utils import classify_tab
 from detect_utils import detect_tab
+from tracker_utils import tracker_tab
 
 
 if __name__ == '__main__':
     gr.TabbedInterface(
-        [detect_tab, classify_tab],
-        tab_names=['Image Detection', 'Image Classification']
+        [detect_tab, classify_tab, tracker_tab],
+        tab_names=['Image Detection', 'Image Classification', "Multi Object Tracker"]
     ).queue().launch()

tracker_utils.py

@@ -0,0 +1,69 @@
+import os
+from ultralytics import YOLO
+import supervision as sv
+import gradio as gr
+
+os.system("wget https://raw.githubusercontent.com/spmallick/learnopencv/master/Understanding-Multiple-Object-Tracking-using-DeepSORT/yolov5/football-video.mp4")
+os.system("wget https://raw.githubusercontent.com/spmallick/learnopencv/master/MultiObjectTracker/videos/run.mp4")
+
+
+def process_video(
+        source_video_path: str,
+        source_weights_path: str,
+        confidence_threshold: float = 0.3,
+        iou_threshold: float = 0.7,):
+
+    model = YOLO(source_weights_path + '.pt')
+    tracker = sv.ByteTrack()
+    box_annotator = sv.BoxAnnotator()
+    frame_generator = sv.get_video_frames_generator(
+        source_path=source_video_path)
+    confidence_threshold = confidence_threshold / 100
+    iou_threshold = iou_threshold / 100
+    # video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)
+
+    # with sv.VideoSink(target_path=target_video_path, video_info=video_info) as sink:
+    for frame in frame_generator:
+        results = model(
+            frame, verbose=False, conf=confidence_threshold, iou=iou_threshold
+        )[0]
+        detections = sv.Detections.from_ultralytics(results)
+        detections = tracker.update_with_detections(detections)
+
+        labels = [
+            f"#{tracker_id} {model.model.names[class_id]}"
+            for _, _, _, class_id, tracker_id in detections
+        ]
+
+        annotated_frame = box_annotator.annotate(
+            scene=frame.copy(), detections=detections, labels=labels
+        )
+
+        yield annotated_frame
+        # sink.write_frame(frame=annotated_frame)
+
+
+inputs_thresh = [
+    gr.components.Video(type="filepath", label="Input Video"),
+    gr.inputs.Radio(label="Detection Methods",
+                    choices=[
+                        "yolov5s", "yolov8s"
+                    ]),
+    gr.components.Slider(label="Class Probability Value",
+                         value=30, minimum=1, maximum=100, step=1),
+    gr.components.Slider(label="IOU threshold Value",
+                         value=50, minimum=1, maximum=100, step=1),
+]
+
+outputs_thresh = [
+    gr.components.Image(type="numpy", label="Output")
+]
+
+tracker_tab = gr.Interface(
+    process_video,
+    inputs=inputs_thresh,
+    outputs=outputs_thresh,
+    title="supervision",
+    examples=[["run.mp4", "yolov5s"], ["football-video.mp4", "yolov8s"]],
+    description="Gradio based demo for <a href='https://github.com/roboflow/supervision' style='text-decoration: underline' target='_blank'>roboflow/supervision</a>, We write your reusable computer vision tools."
+)