yolov10_det改為yolov10_det_webcam相關問題

[HsiaoCH]

        public void yolov10_det_webcam(string model_path, string device)
        {
            // Initialize webcam
            VideoCapture capture = new VideoCapture(0);  // 0 is usually the default camera index
            if (!capture.IsOpened())
            {
                Slog.ERROR("Failed to open the webcam.");
                return;
            }

            // -------- Step 1. Initialize OpenVINO Runtime Core --------
            Core core = new Core();
            Slog.INFO("1. Initialized OpenVINO Runtime Core.");

            // -------- Step 2. Read inference model --------
            Model model = core.read_model(model_path);
            Slog.INFO("2. Read inference model.");
            OvExtensions.printf_model_info(model);

            // -------- Step 3. Load the model onto the device --------
            CompiledModel compiled_model = core.compile_model(model, device);
            Slog.INFO("3. Loaded model onto the device.");

            // -------- Step 4. Create an infer request --------
            InferRequest infer_request = compiled_model.create_infer_request();
            Slog.INFO("4. Created infer request.");

            Mat frame = new Mat();
            Mat max_image;
            Mat input_mat;
            Rect roi;
            Tensor input_tensor;
            Shape input_shape;
            Tensor output_tensor;
            Rect box;
            while (true)
            {
                // Capture frame from webcam
                capture.Read(frame);
                if (frame.Empty()) continue;

                // -------- Step 5. Process input images --------
                int max_image_length = frame.Cols > frame.Rows ? frame.Cols : frame.Rows;
                max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
                roi = new Rect(0, 0, frame.Cols, frame.Rows);
                frame.CopyTo(new Mat(max_image, roi));
                float factor = (float)(max_image_length / 640.0);

                // -------- Step 6. Set up input data --------
                input_tensor = infer_request.get_input_tensor();
                input_shape = input_tensor.get_shape();
                input_mat = CvDnn.BlobFromImage(max_image, 1.0 / 255.0, new OpenCvSharp.Size(input_shape[2], input_shape[3]), new Scalar(0, 0, 0), true, false);
                float[] input_data = new float[input_shape[1] * input_shape[2] * input_shape[3]];
                Marshal.Copy(input_mat.Ptr(0), input_data, 0, input_data.Length);

                input_tensor.set_data<float>(input_data);

                // -------- Step 7. Do inference synchronously --------
                infer_request.infer();

                // -------- Step 8. Get infer result data --------
                output_tensor = infer_request.get_output_tensor();
                int output_length = (int)output_tensor.get_size();
                float[] output_data = output_tensor.get_data<float>(output_length);

                // -------- Step 9. Process results --------
                List<Rect> position_boxes = new List<Rect>();
                List<int> class_ids = new List<int>();
                List<float> confidences = new List<float>();

                for (int i = 0; i < output_data.Length / 6; i++)
                {
                    int s = 6 * i;
                    if (output_data[s + 4] > 0.5)
                    {
                        float cx = output_data[s + 0];
                        float cy = output_data[s + 1];
                        float dx = output_data[s + 2];
                        float dy = output_data[s + 3];
                        int x = (int)((cx) * factor);
                        int y = (int)((cy) * factor);
                        int width = (int)((dx - cx) * factor);
                        int height = (int)((dy - cy) * factor);
                        box = new Rect(x, y, width, height);

                        position_boxes.Add(box);
                        class_ids.Add((int)output_data[s + 5]);
                        confidences.Add(output_data[s + 4]);
                    }
                }

                // Draw detection results
                for (int i = 0; i < class_ids.Count; i++)
                {
                    int index = i;
                    Cv2.Rectangle(frame, position_boxes[index], new Scalar(0, 0, 255), 2, LineTypes.Link8);
                    Cv2.Rectangle(frame, new OpenCvSharp.Point(position_boxes[index].TopLeft.X, position_boxes[index].TopLeft.Y + 30),
                            new OpenCvSharp.Point(position_boxes[index].BottomRight.X, position_boxes[index].TopLeft.Y), new Scalar(255, 0, 255), -1);
                    Cv2.PutText(frame, class_ids[index] + "-" + confidences[index].ToString("0.00"),
                            new OpenCvSharp.Point(position_boxes[index].X, position_boxes[index].Y + 25),
                            HersheyFonts.HersheySimplex, 0.8, new Scalar(0, 0, 0), 2);
                }

                // Display the frame with detections
                Cv2.ImShow("YOLOv10 Webcam Detection", frame);
                if (Cv2.WaitKey(1) == 27) // Break on 'ESC'
                {
                    break;
                }

                input_mat?.Dispose();
                max_image?.Dispose();
                input_tensor = null;
                output_tensor = null;
            }

            frame.Dispose(); // Release frame at the end
            capture.Release();
            Cv2.DestroyAllWindows();
        }

你好，
先感謝你釋出這麼好用的資源
但我在使用時遇到了一點問題:
上列code是修改成支援webcam，期望進行連續yolov10偵測
在執行時遇到下列問題
在前幾秒時偵測皆為正常運行(如上圖)
但在幾秒後偵測框不正常出現，class_ids.Count固定是300(如下圖)
我想問題是與資源未釋放相關嗎?還是code用法有誤?

謝謝你