# RGB & MobileNetSSD @ 4K 此示例演示了如何在 RGB 输入帧上运行 MobileNetv2SSD，以及如何在预览中同时显示 RGB 预览和来自 MobileNetv2SSD 的元数据结果。 预览尺寸设置为 4K 分辨率。 这是 [RGB & MobileNetSSD](https://docs.luxonis.com/software/depthai/examples/rgb_mobilenet.md) 的一个变体。 ### 类似示例： * [RGB & MobileNetSSD](https://docs.luxonis.com/software/depthai/examples/rgb_mobilenet.md) * [Mono & MobileNetSSD](https://docs.luxonis.com/software/depthai/examples/mono_depth_mobilenetssd.md) * [Video & MobileNetSSD](https://docs.luxonis.com/software/depthai/examples/video_mobilenet.md) * [Mono & MobileNetSSD & Depth](https://docs.luxonis.com/software/depthai/examples/mono_depth_mobilenetssd.md) ## 演示 ## 设置 请运行[安装脚本](https://github.com/luxonis/depthai-python/blob/main/examples/install_requirements.py)以下载所有必需的依赖项。请注意，此脚本必须在 git 上下文中运行，因此您需要先下载 [depthai-python](https://github.com/luxonis/depthai-python) 仓库，然后运行该脚本。 ```bash git clone https://github.com/luxonis/depthai-python.git cd depthai-python/examples python3 install_requirements.py ``` 更多信息，请参考[安装指南](https://docs.luxonis.com/software/depthai/manual-install.md)。 ## 源代码 #### Python ```python #!/usr/bin/env python3 from pathlib import Path import sys import cv2 import depthai as dai import numpy as np # Get argument first nnPath = str((Path(__file__).parent / Path('../models/mobilenet-ssd_openvino_2021.4_5shave.blob')).resolve().absolute()) if len(sys.argv) > 1: nnPath = sys.argv[1] if not Path(nnPath).exists(): import sys raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable} install_requirements.py"') # MobilenetSSD label texts labelMap = ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"] # Create pipeline pipeline = dai.Pipeline() # Define sources and outputs camRgb = pipeline.create(dai.node.ColorCamera) nn = pipeline.create(dai.node.MobileNetDetectionNetwork) xoutVideo = pipeline.create(dai.node.XLinkOut) xoutPreview = pipeline.create(dai.node.XLinkOut) nnOut = pipeline.create(dai.node.XLinkOut) xoutVideo.setStreamName("video") xoutPreview.setStreamName("preview") nnOut.setStreamName("nn") # Properties camRgb.setPreviewSize(300, 300) # NN input camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_4_K) camRgb.setInterleaved(False) camRgb.setPreviewKeepAspectRatio(False) # Define a neural network that will make predictions based on the source frames nn.setConfidenceThreshold(0.5) nn.setBlobPath(nnPath) nn.setNumInferenceThreads(2) nn.input.setBlocking(False) # Linking camRgb.video.link(xoutVideo.input) camRgb.preview.link(xoutPreview.input) camRgb.preview.link(nn.input) nn.out.link(nnOut.input) # Connect to device and start pipeline with dai.Device(pipeline) as device: # Output queues will be used to get the frames and nn data from the outputs defined above qVideo = device.getOutputQueue(name="video", maxSize=4, blocking=False) qPreview = device.getOutputQueue(name="preview", maxSize=4, blocking=False) qDet = device.getOutputQueue(name="nn", maxSize=4, blocking=False) previewFrame = None videoFrame = None detections = [] # nn data, being the bounding box locations, are in <0..1> range - they need to be normalized with frame width/height def frameNorm(frame, bbox): normVals = np.full(len(bbox), frame.shape[0]) normVals[::2] = frame.shape[1] return (np.clip(np.array(bbox), 0, 1) * normVals).astype(int) def displayFrame(name, frame): color = (255, 0, 0) for detection in detections: bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax)) cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color) cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color) cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2) # Show the frame cv2.imshow(name, frame) cv2.namedWindow("video", cv2.WINDOW_NORMAL) cv2.resizeWindow("video", 1280, 720) print("Resize video window with mouse drag!") while True: # Instead of get (blocking), we use tryGet (non-blocking) which will return the available data or None otherwise inVideo = qVideo.tryGet() inPreview = qPreview.tryGet() inDet = qDet.tryGet() if inVideo is not None: videoFrame = inVideo.getCvFrame() if inPreview is not None: previewFrame = inPreview.getCvFrame() if inDet is not None: detections = inDet.detections if videoFrame is not None: displayFrame("video", videoFrame) if previewFrame is not None: displayFrame("preview", previewFrame) if cv2.waitKey(1) == ord('q'): break ``` #### C++ ```cpp #include // Includes common necessary includes for development using depthai library #include "depthai/depthai.hpp" // MobilenetSSD label texts static const std::vector labelMap = {"background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"}; int main(int argc, char** argv) { using namespace std; // Default blob path provided by Hunter private data download // Applicable for easier example usage only std::string nnPath(BLOB_PATH); // If path to blob specified, use that if(argc > 1) { nnPath = std::string(argv[1]); } // Print which blob we are using printf("Using blob at path: %s\n", nnPath.c_str()); // Create pipeline dai::Pipeline pipeline; // Define sources and outputs auto camRgb = pipeline.create(); auto nn = pipeline.create(); auto xoutVideo = pipeline.create(); auto xoutPreview = pipeline.create(); auto nnOut = pipeline.create(); xoutVideo->setStreamName("video"); xoutPreview->setStreamName("preview"); nnOut->setStreamName("nn"); // Properties camRgb->setPreviewSize(300, 300); // NN input camRgb->setResolution(dai::ColorCameraProperties::SensorResolution::THE_4_K); camRgb->setInterleaved(false); camRgb->setPreviewKeepAspectRatio(false); // Define a neural network that will make predictions based on the source frames nn->setConfidenceThreshold(0.5); nn->setBlobPath(nnPath); nn->setNumInferenceThreads(2); nn->input.setBlocking(false); // Linking camRgb->video.link(xoutVideo->input); camRgb->preview.link(xoutPreview->input); camRgb->preview.link(nn->input); nn->out.link(nnOut->input); // Connect to device and start pipeline dai::Device device(pipeline); // Output queues will be used to get the frames and nn data from the outputs defined above auto qVideo = device.getOutputQueue("video", 4, false); auto qPreview = device.getOutputQueue("preview", 4, false); auto qDet = device.getOutputQueue("nn", 4, false); cv::Mat previewFrame; cv::Mat videoFrame; std::vector detections; // Add bounding boxes and text to the frame and show it to the user auto displayFrame = [](std::string name, cv::Mat frame, std::vector& detections) { auto color = cv::Scalar(255, 0, 0); // nn data, being the bounding box locations, are in <0..1> range - they need to be normalized with frame width/height for(auto& detection : detections) { int x1 = detection.xmin * frame.cols; int y1 = detection.ymin * frame.rows; int x2 = detection.xmax * frame.cols; int y2 = detection.ymax * frame.rows; uint32_t labelIndex = detection.label; std::string labelStr = to_string(labelIndex); if(labelIndex < labelMap.size()) { labelStr = labelMap[labelIndex]; } cv::putText(frame, labelStr, cv::Point(x1 + 10, y1 + 20), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); std::stringstream confStr; confStr << std::fixed << std::setprecision(2) << detection.confidence * 100; cv::putText(frame, confStr.str(), cv::Point(x1 + 10, y1 + 40), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::rectangle(frame, cv::Rect(cv::Point(x1, y1), cv::Point(x2, y2)), color, cv::FONT_HERSHEY_SIMPLEX); } // Show the frame cv::imshow(name, frame); }; cv::namedWindow("video", cv::WINDOW_NORMAL); cv::resizeWindow("video", 1280, 720); cout << "Resize video window with mouse drag!" << endl; while(true) { // Instead of get (blocking), we use tryGet (non-blocking) which will return the available data or None otherwise auto inVideo = qVideo->tryGet(); auto inPreview = qPreview->tryGet(); auto inDet = qDet->tryGet(); if(inVideo) { videoFrame = inVideo->getCvFrame(); } if(inPreview) { previewFrame = inPreview->getCvFrame(); } if(inDet) { detections = inDet->detections; } if(!videoFrame.empty()) { displayFrame("video", videoFrame, detections); } if(!previewFrame.empty()) { displayFrame("preview", previewFrame, detections); } int key = cv::waitKey(1); if(key == 'q' || key == 'Q') { return 0; } } return 0; } ``` ## 管道 ### examples/rgb_mobilenet_4k.pipeline.json ```json { "pipeline": { "connections": [ { "node1Id": 0, "node1Output": "video", "node1OutputGroup": "", "node2Id": 2, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 0, "node1Output": "preview", "node1OutputGroup": "", "node2Id": 3, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 0, "node1Output": "preview", "node1OutputGroup": "", "node2Id": 1, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 1, "node1Output": "out", "node1OutputGroup": "", "node2Id": 4, "node2Input": "in", "node2InputGroup": "" } ], "globalProperties": { "calibData": null, "cameraTuningBlobSize": null, "cameraTuningBlobUri": "", "leonCssFrequencyHz": 700000000.0, "leonMssFrequencyHz": 700000000.0, "pipelineName": null, "pipelineVersion": null, "sippBufferSize": 18432, "sippDmaBufferSize": 16384, "xlinkChunkSize": -1 }, "nodes": [ [ 0, { "id": 0, "ioInfo": [ [ [ "", "inputConfig" ], { "blocking": false, "group": "", "id": 1, "name": "inputConfig", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "raw" ], { "blocking": false, "group": "", "id": 6, "name": "raw", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "still" ], { "blocking": false, "group": "", "id": 7, "name": "still", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "inputControl" ], { "blocking": true, "group": "", "id": 2, "name": "inputControl", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "video" ], { "blocking": false, "group": "", "id": 3, "name": "video", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "isp" ], { "blocking": false, "group": "", "id": 4, "name": "isp", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "preview" ], { "blocking": false, "group": "", "id": 5, "name": "preview", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "frameEvent" ], { "blocking": false, "group": "", "id": 8, "name": "frameEvent", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "name": "ColorCamera", "properties": { "boardSocket": -1, "cameraName": "", "colorOrder": 0, "fp16": false, "fps": 30.0, "imageOrientation": -1, "initialControl": { "aeLockMode": false, "aeMaxExposureTimeUs": 0, "aeRegion": { "height": 0, "priority": 0, "width": 0, "x": 0, "y": 0 }, "afRegion": { "height": 0, "priority": 0, "width": 0, "x": 0, "y": 0 }, "antiBandingMode": 0, "autoFocusMode": 3, "awbLockMode": false, "awbMode": 0, "brightness": 0, "captureIntent": 0, "chromaDenoise": 0, "cmdMask": 0, "contrast": 0, "controlMode": 0, "effectMode": 0, "expCompensation": 0, "expManual": { "exposureTimeUs": 0, "frameDurationUs": 0, "sensitivityIso": 0 }, "frameSyncMode": 0, "lensPosAutoInfinity": 0, "lensPosAutoMacro": 0, "lensPosition": 0, "lensPositionRaw": 0.0, "lowPowerNumFramesBurst": 0, "lowPowerNumFramesDiscard": 0, "lumaDenoise": 0, "saturation": 0, "sceneMode": 0, "sharpness": 0, "strobeConfig": { "activeLevel": 0, "enable": 0, "gpioNumber": 0 }, "strobeTimings": { "durationUs": 0, "exposureBeginOffsetUs": 0, "exposureEndOffsetUs": 0 }, "wbColorTemp": 0 }, "interleaved": false, "isp3aFps": 0, "ispScale": { "horizDenominator": 0, "horizNumerator": 0, "vertDenominator": 0, "vertNumerator": 0 }, "numFramesPoolIsp": 3, "numFramesPoolPreview": 4, "numFramesPoolRaw": 3, "numFramesPoolStill": 4, "numFramesPoolVideo": 4, "previewHeight": 300, "previewKeepAspectRatio": false, "previewWidth": 300, "rawPacked": null, "resolution": 1, "sensorCropX": -1.0, "sensorCropY": -1.0, "stillHeight": -1, "stillWidth": -1, "videoHeight": -1, "videoWidth": -1 } } ], [ 1, { "id": 1, "ioInfo": [ [ [ "", "in" ], { "blocking": false, "group": "", "id": 9, "name": "in", "queueSize": 5, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 10, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthrough" ], { "blocking": false, "group": "", "id": 11, "name": "passthrough", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "name": "DetectionNetwork", "properties": { "blobSize": 14517568, "blobUri": "asset:__blob", "numFrames": 8, "numNCEPerThread": 0, "numThreads": 2, "parser": { "anchorMasks": {}, "anchors": [], "classes": 0, "confidenceThreshold": 0.5, "coordinates": 0, "iouThreshold": 0.0, "nnFamily": 1 } } } ], [ 2, { "id": 2, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 12, "name": "in", "queueSize": 8, "type": 3, "waitForMessage": true } ] ], "name": "XLinkOut", "properties": { "maxFpsLimit": -1.0, "metadataOnly": false, "streamName": "video" } } ], [ 3, { "id": 3, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 13, "name": "in", "queueSize": 8, "type": 3, "waitForMessage": true } ] ], "name": "XLinkOut", "properties": { "maxFpsLimit": -1.0, "metadataOnly": false, "streamName": "preview" } } ], [ 4, { "id": 4, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 14, "name": "in", "queueSize": 8, "type": 3, "waitForMessage": true } ] ], "name": "XLinkOut", "properties": { "maxFpsLimit": -1.0, "metadataOnly": false, "streamName": "nn" } } ] ] } } ``` ### 需要帮助？ 请前往 [OAKChina 官网](https://www.oakchina.cn/) 获取技术支持或解答您的任何疑问。