# Mono & MobilenetSSD This example shows how to run MobileNetv2SSD on the right grayscale camera and how to display the neural network results on a preview of the right camera stream. ### Similar samples: * [RGB & MobilenetSSD](https://docs.luxonis.com/software/depthai/examples/rgb_mobilenet.md) * [RGB & MobileNetSSD @ 4K](https://docs.luxonis.com/software/depthai/examples/rgb_mobilenet_4k.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) ## Demo ## Setup Please run the [install script](https://github.com/luxonis/depthai-python/blob/main/examples/install_requirements.py) to download all required dependencies. Please note that this script must be ran from git context, so you have to download the [depthai-python](https://github.com/luxonis/depthai-python) repository first and then run the script ```bash git clone https://github.com/luxonis/depthai-python.git cd depthai-python/examples python3 install_requirements.py ``` For additional information, please follow the [installation guide](https://docs.luxonis.com/software/depthai/manual-install.md). ## Source code #### 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_6shave.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 monoRight = pipeline.create(dai.node.MonoCamera) manip = pipeline.create(dai.node.ImageManip) nn = pipeline.create(dai.node.MobileNetDetectionNetwork) manipOut = pipeline.create(dai.node.XLinkOut) nnOut = pipeline.create(dai.node.XLinkOut) manipOut.setStreamName("right") nnOut.setStreamName("nn") # Properties monoRight.setCamera("right") monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_720_P) # Convert the grayscale frame into the nn-acceptable form manip.initialConfig.setResize(300, 300) # The NN model expects BGR input. By default ImageManip output type would be same as input (gray in this case) manip.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p) nn.setConfidenceThreshold(0.5) nn.setBlobPath(nnPath) nn.setNumInferenceThreads(2) nn.input.setBlocking(False) # Linking monoRight.out.link(manip.inputImage) manip.out.link(nn.input) manip.out.link(manipOut.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 grayscale frames and nn data from the outputs defined above qRight = device.getOutputQueue("right", maxSize=4, blocking=False) qDet = device.getOutputQueue("nn", maxSize=4, blocking=False) frame = 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) while True: # Instead of get (blocking), we use tryGet (non-blocking) which will return the available data or None otherwise inRight = qRight.tryGet() inDet = qDet.tryGet() if inRight is not None: frame = inRight.getCvFrame() if inDet is not None: detections = inDet.detections if frame is not None: displayFrame("right", frame) if cv2.waitKey(1) == ord('q'): break ``` #### C++ ```cpp #include #include "utility.hpp" // 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 monoRight = pipeline.create(); auto manip = pipeline.create(); auto nn = pipeline.create(); auto manipOut = pipeline.create(); auto nnOut = pipeline.create(); manipOut->setStreamName("right"); nnOut->setStreamName("nn"); // Properties monoRight->setCamera("right"); monoRight->setResolution(dai::MonoCameraProperties::SensorResolution::THE_720_P); // Convert the grayscale frame into the nn-acceptable form manip->initialConfig.setResize(300, 300); // The NN model expects BGR input. By default ImageManip output type would be same as input (gray in this case) manip->initialConfig.setFrameType(dai::ImgFrame::Type::BGR888p); nn->setConfidenceThreshold(0.5); nn->setBlobPath(nnPath); nn->setNumInferenceThreads(2); nn->input.setBlocking(false); // Linking monoRight->out.link(manip->inputImage); manip->out.link(nn->input); manip->out.link(manipOut->input); nn->out.link(nnOut->input); // Connect to device and start pipeline dai::Device device(pipeline); // Output queues will be used to get the grayscale frames and nn data from the outputs defined above auto qRight = device.getOutputQueue("right", 4, false); auto qDet = device.getOutputQueue("nn", 4, false); cv::Mat frame; 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); }; while(true) { // Instead of get (blocking), we use tryGet (non-blocking) which will return the available data or None otherwise auto inRight = qRight->tryGet(); auto inDet = qDet->tryGet(); if(inRight) { frame = inRight->getCvFrame(); } if(inDet) { detections = inDet->detections; } if(!frame.empty()) { displayFrame("right", frame, detections); } int key = cv::waitKey(1); if(key == 'q' || key == 'Q') return 0; } return 0; } ``` ## Pipeline ### examples/mono_mobilenet.pipeline.json ```json { "pipeline": { "connections": [ { "node1Id": 0, "node1Output": "out", "node1OutputGroup": "", "node2Id": 1, "node2Input": "inputImage", "node2InputGroup": "" }, { "node1Id": 1, "node1Output": "out", "node1OutputGroup": "", "node2Id": 2, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 1, "node1Output": "out", "node1OutputGroup": "", "node2Id": 3, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 2, "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": [ [ [ "", "inputControl" ], { "blocking": true, "group": "", "id": 1, "name": "inputControl", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 2, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "raw" ], { "blocking": false, "group": "", "id": 3, "name": "raw", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "frameEvent" ], { "blocking": false, "group": "", "id": 4, "name": "frameEvent", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "name": "MonoCamera", "properties": { "boardSocket": -1, "cameraName": "right", "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 }, "isp3aFps": 0, "numFramesPool": 3, "numFramesPoolRaw": 3, "rawPacked": null, "resolution": 0 } } ], [ 1, { "id": 1, "ioInfo": [ [ [ "", "inputConfig" ], { "blocking": true, "group": "", "id": 5, "name": "inputConfig", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "inputImage" ], { "blocking": true, "group": "", "id": 6, "name": "inputImage", "queueSize": 8, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 7, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "name": "ImageManip", "properties": { "initialConfig": { "cropConfig": { "cropRatio": 1.0, "cropRect": { "xmax": 0.0, "xmin": 0.0, "ymax": 0.0, "ymin": 0.0 }, "cropRotatedRect": { "angle": 0.0, "center": { "x": 0.0, "y": 0.0 }, "size": { "height": 0.0, "width": 0.0 } }, "enableCenterCropRectangle": false, "enableRotatedRect": false, "normalizedCoords": true, "widthHeightAspectRatio": 1.0 }, "enableCrop": false, "enableFormat": true, "enableResize": true, "formatConfig": { "colormap": 0, "colormapMax": 255, "colormapMin": 0, "flipHorizontal": false, "flipVertical": false, "type": 8 }, "interpolation": -1, "resizeConfig": { "bgBlue": 0, "bgGreen": 0, "bgRed": 0, "enableRotation": false, "enableWarp4pt": false, "enableWarpMatrix": false, "height": 300, "keepAspectRatio": true, "lockAspectRatioFill": false, "normalizedCoords": true, "rotationAngleDeg": 0.0, "warpBorderReplicate": false, "warpFourPoints": [], "warpMatrix3x3": [], "width": 300 }, "reusePreviousImage": false, "skipCurrentImage": false }, "meshHeight": 0, "meshUri": "", "meshWidth": 0, "numFramesPool": 4, "outputFrameSize": 1048576 } } ], [ 2, { "id": 2, "ioInfo": [ [ [ "", "in" ], { "blocking": false, "group": "", "id": 8, "name": "in", "queueSize": 5, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 9, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthrough" ], { "blocking": false, "group": "", "id": 10, "name": "passthrough", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "name": "DetectionNetwork", "properties": { "blobSize": 14499200, "blobUri": "asset:__blob", "numFrames": 8, "numNCEPerThread": 0, "numThreads": 2, "parser": { "anchorMasks": {}, "anchors": [], "classes": 0, "confidenceThreshold": 0.5, "coordinates": 0, "iouThreshold": 0.0, "nnFamily": 1 } } } ], [ 3, { "id": 3, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 11, "name": "in", "queueSize": 8, "type": 3, "waitForMessage": true } ] ], "name": "XLinkOut", "properties": { "maxFpsLimit": -1.0, "metadataOnly": false, "streamName": "right" } } ], [ 4, { "id": 4, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 12, "name": "in", "queueSize": 8, "type": 3, "waitForMessage": true } ] ], "name": "XLinkOut", "properties": { "maxFpsLimit": -1.0, "metadataOnly": false, "streamName": "nn" } } ] ] } } ``` ### Need assistance? Head over to [Discussion Forum](https://discuss.luxonis.com/) for technical support or any other questions you might have.