going somewhere

dodgeballtracker/logic.py

@@ -29,17 +29,43 @@ class DetectedObjectBox:
         return cls(min_threshold, color)
 
 
+def get_court_perspective_transform():
+    """
+    """
+    empirical_top_left = np.float32([416, 175])
+    empirical_top_right = np.float32([905, 173])
+    empirical_bottom_left = np.float32([51, 702])
+    empirical_bottom_right = np.float32([1188, 695])
+
+    court_top_left = np.float32([0, 0])
+    court_top_right = np.float32([9, 0])
+    court_bottom_left = np.float32([0, 18])
+    court_bottom_right = np.float32([9, 18])
+
+    empirical_source = np.float32([empirical_top_left,
+                                   empirical_top_right,
+                                   empirical_bottom_left,
+                                   empirical_bottom_right])
+    pixel_per_meter = 50
+    empirical_target = np.float32([court_top_left,
+                                   court_top_right,
+                                   court_bottom_left,
+                                   court_bottom_right]) * pixel_per_meter
+    return cv2.getPerspectiveTransform(empirical_source, empirical_target)
+
+
 class DodgeballTracker:
 
     def __init__(self,
                  input_file: Path,
                  output_file: Path,
-                 detected_box_objects: list[DetectedObjectBox]):
+                 detected_box_objects: list[DetectedObjectBox],
+                 transformation_matrix):
         self.input_path = input_file
         self.output_path = output_file
         self.output_json_path = output_file.with_suffix(".json")
         self.detected_box_objects = sorted(detected_box_objects, reverse=True)
-        self.transformation_matrix = self.get_court_perspective_transform()
+        self.transformation_matrix = transformation_matrix
         self.points = []
 
     def write_frame(self, writer, frame) -> None:
@@ -49,30 +75,6 @@ class DodgeballTracker:
     def extract_box(self, data) -> tuple[int, int, int, int]:
         return int(data[0]), int(data[1]), int(data[2]), int(data[3])
 
-    def get_court_perspective_transform(self):
-        """
-        """
-        empirical_top_left = np.float32([416, 175])
-        empirical_top_right = np.float32([905, 173])
-        empirical_bottom_left = np.float32([51, 702])
-        empirical_bottom_right = np.float32([1188, 695])
-
-        court_top_left = np.float32([0, 0])
-        court_top_right = np.float32([9, 0])
-        court_bottom_left = np.float32([0, 18])
-        court_bottom_right = np.float32([9, 18])
-
-        empirical_source = np.float32([empirical_top_left,
-                                       empirical_top_right,
-                                       empirical_bottom_left,
-                                       empirical_bottom_right])
-        pixel_per_meter = 50
-        empirical_target = np.float32([court_top_left,
-                                       court_top_right,
-                                       court_bottom_left,
-                                       court_bottom_right]) * pixel_per_meter
-        return cv2.getPerspectiveTransform(empirical_source, empirical_target)
-
     def print_box(self, data, frame_idx, frame_ts):
         xmin, ymin, xmax, ymax = self.extract_box(data)
         xavg = (xmax + xmin) / 2
@@ -80,16 +82,26 @@ class DodgeballTracker:
         ret = self.transformation_matrix @ v
         x, y = ret[0] / ret[2], ret[1] / ret[2]
         object_id = data[-1]
-        self.points.append({"x": x, "y": y, "frameIndex": frame_idx, "frameTimestamp": frame_ts, "objectId": object_id})
+        self.points.append({"x": x,
+                            "y": y,
+                            "frameIndex": frame_idx,
+                            "frameTimestamp": frame_ts,
+                            "objectId": int(object_id)
+                            })
 
-    def plot_boxe_to_frame(self, data, frame, frame_idx, frame_ts):
+    def print_tracker_data(self, tracker_data, frame_idx, frame_ts):
+        for d in tracker_data:
+            self.print_box(d, frame_idx, frame_ts)
+
+    def plot_boxe_to_frame(self, data, frame):
         confidence = float(data[4])
         for detected_box_object in self.detected_box_objects:
 
             if detected_box_object.min_threshold < confidence:
                 xmin, ymin, xmax, ymax = self.extract_box(data)
                 cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), detected_box_object.color, 2)
-                return data  # [[xmin, ymin, xmax - xmin, ymax - ymin], confidence, int(data[5])]
+                return True
+        return False
 
     def run_model_on_frame(self, model, frame):
         return model(frame)[0]
@@ -108,43 +120,45 @@ class DodgeballTracker:
         cv2.polylines(frame, pts, True, (0, 255, 255), 8)
 
     def persist_points(self):
-        nbr_id = max((p["objectId"] for p in self.points))
-        cm = matplotlib.colormaps['viridis']
-        for p in self.points:
-            value = p["objectId"] / nbr_id
-            color: Color = tuple((int(255 * cm(value)[i]) for i in range(3)))
-            p["color"] = f"rgb({color[0]}, {color[2]}, {color[1]})"
-
         with open(self.output_json_path, "wt") as file_:
             json.dump({"points": self.points}, file_, indent=4)
 
+    def _get_tracker(self):
+
+        return DeepOCSORT(
+            model_weights=Path('lmbn_n_cuhk03_d.pt'),  # which ReID model to use
+            device=torch.device("mps"),
+            fp16=True,
+        )
+
+    def _get_detection_model(self):
+        """
+        load the pre-trained YOLOv8n model
+        """
+        return YOLO("yolov8n.pt")
+
     def main(self):
         # define some constants
 
         video_cap = cv2.VideoCapture(str(self.input_path))
         writer = create_video_writer(video_cap, str(self.output_path))
-        tracker = DeepOCSORT(
-            model_weights=Path('osnet_x0_25_msmt17.pt'),  # which ReID model to use
-            device=torch.device("mps"),
-            fp16=True,
-        )
+        tracker = self._get_tracker()
 
         # load the pre-trained YOLOv8n model
-        model = YOLO("yolov8n.pt")
+        model = self._get_detection_model()
 
         for i, (frame, ts) in enumerate(iter_frames(video_cap)):
             # run the YOLO model on the frame
             res = []
             detections = self.run_model_on_frame(model, frame)
             for data in detections.boxes.data.tolist():
-                selected_data = self.plot_boxe_to_frame(data, frame, i, ts)
-                if selected_data:
-                    res.append(selected_data)
+                is_good_box = self.plot_boxe_to_frame(data, frame)
+                if is_good_box:
+                    res.append(data)
 
             # show the frame to our screen
             data_ = tracker.update(np.array(res), frame)
-            for d in data_:
-                self.print_box(d, i, ts)
+            self.print_tracker_data(data_, i, ts)
 
             self.write_frame(writer, frame)
 
@@ -155,6 +169,3 @@ class DodgeballTracker:
         writer.release()
         cv2.destroyAllWindows()
         self.persist_points()
-
-
-