# Object Tracker This example demonstrates spatial object tracking on the RGB stream using a YOLOv6-nano SpatialDetectionNetwork together with the [ObjectTracker](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/object_tracker.md) node. Detections are decoded on-device and fused with stereo depth to provide per-track X/Y/Z (mm), while the tracker assigns persistent IDs and status visible in the overlay. When a valid spatial state exists, the overlay also displays optional velocity and speed in m/s. The source includes a useSpatialAssociation flag. It is False by default, which means tracklets still carry spatial coordinates, but detection-to-track matching uses the standard 2D association path. Set it to True when depth is reliable and you want XYZ distance to help preserve IDs for overlapping or crossing objects. ## Demo This example requires the DepthAI v3 API, see [installation instructions](https://docs.luxonis.com/software-v3/depthai.md). ## Pipeline ### examples/object_tracker(daiv3).pipeline.json ```json { "pipeline": { "connections": [ { "node1Id": 0, "node1Output": "0", "node1OutputGroup": "dynamicOutputs", "node2Id": 5, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 1, "node1Output": "0", "node1OutputGroup": "dynamicOutputs", "node2Id": 3, "node2Input": "left", "node2InputGroup": "" }, { "node1Id": 2, "node1Output": "0", "node1OutputGroup": "dynamicOutputs", "node2Id": 3, "node2Input": "right", "node2InputGroup": "" }, { "node1Id": 3, "node1Output": "depth", "node1OutputGroup": "", "node2Id": 7, "node2Input": "input", "node2InputGroup": "" }, { "node1Id": 4, "node1Output": "out", "node1OutputGroup": "", "node2Id": 8, "node2Input": "inputDetections", "node2InputGroup": "" }, { "node1Id": 5, "node1Output": "out", "node1OutputGroup": "", "node2Id": 6, "node2Input": "in", "node2InputGroup": "" }, { "node1Id": 5, "node1Output": "passthrough", "node1OutputGroup": "", "node2Id": 4, "node2Input": "inputImg", "node2InputGroup": "" }, { "node1Id": 5, "node1Output": "passthrough", "node1OutputGroup": "", "node2Id": 7, "node2Input": "inputAlignTo", "node2InputGroup": "" }, { "node1Id": 5, "node1Output": "passthrough", "node1OutputGroup": "", "node2Id": 8, "node2Input": "inputTrackerFrame", "node2InputGroup": "" }, { "node1Id": 5, "node1Output": "passthrough", "node1OutputGroup": "", "node2Id": 8, "node2Input": "inputDetectionFrame", "node2InputGroup": "" }, { "node1Id": 6, "node1Output": "out", "node1OutputGroup": "", "node2Id": 4, "node2Input": "inputDetections", "node2InputGroup": "" }, { "node1Id": 7, "node1Output": "outputAligned", "node1OutputGroup": "", "node2Id": 4, "node2Input": "inputDepth", "node2InputGroup": "" } ], "globalProperties": { "calibData": null, "cameraTuningBlobSize": null, "cameraTuningBlobUri": "", "eepromId": 0, "leonCssFrequencyHz": 700000000.0, "leonMssFrequencyHz": 700000000.0, "pipelineName": null, "pipelineVersion": null, "sippBufferSize": 18432, "sippDmaBufferSize": 16384, "xlinkChunkSize": -1 }, "nodes": [ [ 0, { "alias": "", "id": 0, "ioInfo": [ [ [ "", "inputControl" ], { "blocking": true, "group": "", "id": 0, "name": "inputControl", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "dynamicOutputs", "0" ], { "blocking": false, "group": "dynamicOutputs", "id": 3, "name": "0", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "mockIsp" ], { "blocking": true, "group": "", "id": 1, "name": "mockIsp", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "raw" ], { "blocking": false, "group": "", "id": 2, "name": "raw", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "Camera", "parentId": -1, "properties": { "boardSocket": 0, "cameraName": "", "fps": -1.0, "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, "enableHdr": false, "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, "miscControls": [], "saturation": 0, "sceneMode": 0, "sharpness": 0, "strobeConfig": { "activeLevel": 0, "enable": 0, "gpioNumber": 0 }, "strobeTimings": { "durationUs": 0, "exposureBeginOffsetUs": 0, "exposureEndOffsetUs": 0 }, "wbColorTemp": 0 }, "isp3aFps": 0, "mockIspHeight": -1, "mockIspWidth": -1, "numFramesPoolIsp": 3, "numFramesPoolPreview": 4, "numFramesPoolRaw": 3, "numFramesPoolStill": 4, "numFramesPoolVideo": 4, "outputRequests": [ { "enableUndistortion": null, "fps": { "value": null }, "resizeMode": 0, "size": { "value": { "index": 0, "value": [ 512, 288 ] } }, "type": 10 } ], "resolutionHeight": -1, "resolutionWidth": -1, "sensorType": -1 } } ], [ 1, { "alias": "", "id": 1, "ioInfo": [ [ [ "", "inputControl" ], { "blocking": true, "group": "", "id": 4, "name": "inputControl", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "dynamicOutputs", "0" ], { "blocking": false, "group": "dynamicOutputs", "id": 7, "name": "0", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "mockIsp" ], { "blocking": true, "group": "", "id": 5, "name": "mockIsp", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "raw" ], { "blocking": false, "group": "", "id": 6, "name": "raw", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "Camera", "parentId": -1, "properties": { "boardSocket": 1, "cameraName": "", "fps": -1.0, "imageOrientation": -1, "initialControl": { "aeLockMode": false, "aeMaxExposureTimeUs": 6553701, "aeRegion": { "height": 103, "priority": 7602273, "width": 101, "x": 104, "y": 108 }, "afRegion": { "height": 97, "priority": 7602292, "width": 98, "x": 116, "y": 95 }, "antiBandingMode": 114, "autoFocusMode": 3, "awbLockMode": false, "awbMode": 101, "brightness": 0, "captureIntent": 0, "chromaDenoise": 101, "cmdMask": 0, "contrast": 105, "controlMode": 121, "effectMode": 0, "enableHdr": false, "expCompensation": 118, "expManual": { "exposureTimeUs": 6422630, "frameDurationUs": 7602274, "sensitivityIso": 6029437 }, "frameSyncMode": 0, "lensPosAutoInfinity": 51, "lensPosAutoMacro": 0, "lensPosition": 0, "lensPositionRaw": 0.0, "lowPowerNumFramesBurst": 123, "lowPowerNumFramesDiscard": 0, "lumaDenoise": 0, "miscControls": [], "saturation": 0, "sceneMode": 0, "sharpness": 99, "strobeConfig": { "activeLevel": 92, "enable": 0, "gpioNumber": 0 }, "strobeTimings": { "durationUs": 7077992, "exposureBeginOffsetUs": 6029375, "exposureEndOffsetUs": 7602274 }, "wbColorTemp": 35 }, "isp3aFps": 0, "mockIspHeight": -1, "mockIspWidth": -1, "numFramesPoolIsp": 3, "numFramesPoolPreview": 4, "numFramesPoolRaw": 3, "numFramesPoolStill": 4, "numFramesPoolVideo": 4, "outputRequests": [ { "enableUndistortion": null, "fps": { "value": null }, "resizeMode": 0, "size": { "value": { "index": 0, "value": [ 640, 400 ] } }, "type": null } ], "resolutionHeight": -1, "resolutionWidth": -1, "sensorType": -1 } } ], [ 2, { "alias": "", "id": 2, "ioInfo": [ [ [ "", "inputControl" ], { "blocking": true, "group": "", "id": 8, "name": "inputControl", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "dynamicOutputs", "0" ], { "blocking": false, "group": "dynamicOutputs", "id": 11, "name": "0", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "mockIsp" ], { "blocking": true, "group": "", "id": 9, "name": "mockIsp", "queueSize": 8, "type": 3, "waitForMessage": false } ], [ [ "", "raw" ], { "blocking": false, "group": "", "id": 10, "name": "raw", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "Camera", "parentId": -1, "properties": { "boardSocket": 2, "cameraName": "", "fps": -1.0, "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, "enableHdr": false, "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, "miscControls": [], "saturation": 0, "sceneMode": 0, "sharpness": 0, "strobeConfig": { "activeLevel": 0, "enable": 0, "gpioNumber": 0 }, "strobeTimings": { "durationUs": 0, "exposureBeginOffsetUs": 0, "exposureEndOffsetUs": 0 }, "wbColorTemp": 0 }, "isp3aFps": 0, "mockIspHeight": -1, "mockIspWidth": -1, "numFramesPoolIsp": 3, "numFramesPoolPreview": 4, "numFramesPoolRaw": 3, "numFramesPoolStill": 4, "numFramesPoolVideo": 4, "outputRequests": [ { "enableUndistortion": null, "fps": { "value": null }, "resizeMode": 0, "size": { "value": { "index": 0, "value": [ 640, 400 ] } }, "type": null } ], "resolutionHeight": -1, "resolutionWidth": -1, "sensorType": -1 } } ], [ 3, { "alias": "", "id": 3, "ioInfo": [ [ [ "", "inputAlignTo" ], { "blocking": false, "group": "", "id": 13, "name": "inputAlignTo", "queueSize": 1, "type": 3, "waitForMessage": true } ], [ [ "", "inputConfig" ], { "blocking": true, "group": "", "id": 12, "name": "inputConfig", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "", "left" ], { "blocking": true, "group": "", "id": 14, "name": "left", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "", "debugExtDispLrCheckIt1" ], { "blocking": false, "group": "", "id": 25, "name": "debugExtDispLrCheckIt1", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "right" ], { "blocking": true, "group": "", "id": 15, "name": "right", "queueSize": 3, "type": 3, "waitForMessage": false } ], [ [ "", "depth" ], { "blocking": false, "group": "", "id": 16, "name": "depth", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "disparity" ], { "blocking": false, "group": "", "id": 17, "name": "disparity", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "syncedLeft" ], { "blocking": false, "group": "", "id": 18, "name": "syncedLeft", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "syncedRight" ], { "blocking": false, "group": "", "id": 19, "name": "syncedRight", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "rectifiedLeft" ], { "blocking": false, "group": "", "id": 20, "name": "rectifiedLeft", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "rectifiedRight" ], { "blocking": false, "group": "", "id": 21, "name": "rectifiedRight", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "confidenceMap" ], { "blocking": false, "group": "", "id": 28, "name": "confidenceMap", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "outConfig" ], { "blocking": false, "group": "", "id": 22, "name": "outConfig", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "debugDispLrCheckIt1" ], { "blocking": false, "group": "", "id": 23, "name": "debugDispLrCheckIt1", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "debugDispLrCheckIt2" ], { "blocking": false, "group": "", "id": 24, "name": "debugDispLrCheckIt2", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "debugDispCostDump" ], { "blocking": false, "group": "", "id": 27, "name": "debugDispCostDump", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "debugExtDispLrCheckIt2" ], { "blocking": false, "group": "", "id": 26, "name": "debugExtDispLrCheckIt2", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "StereoDepth", "parentId": -1, "properties": { "alphaScaling": null, "baseline": null, "depthAlignCamera": -1, "depthAlignmentUseSpecTranslation": null, "disparityToDepthUseSpecTranslation": null, "enableFrameSync": true, "enableRectification": true, "enableRuntimeStereoModeSwitch": false, "focalLength": null, "focalLengthFromCalibration": true, "height": null, "initialConfig": { "algorithmControl": { "centerAlignmentShiftFactor": null, "customDepthUnitMultiplier": 1000.0, "depthAlign": 1, "depthUnit": 2, "disparityShift": 0, "enableExtended": false, "enableLeftRightCheck": true, "enableSubpixel": true, "enableSwLeftRightCheck": false, "leftRightCheckThreshold": 10, "numInvalidateEdgePixels": 0, "subpixelFractionalBits": 5 }, "censusTransform": { "enableMeanMode": true, "kernelMask": 0, "kernelSize": -1, "noiseThresholdOffset": 1, "noiseThresholdScale": 1, "threshold": 0 }, "confidenceMetrics": { "flatnessConfidenceThreshold": 2, "flatnessConfidenceWeight": 8, "flatnessOverride": false, "motionVectorConfidenceThreshold": 1, "motionVectorConfidenceWeight": 4, "occlusionConfidenceWeight": 20 }, "costAggregation": { "divisionFactor": 1, "horizontalPenaltyCostP1": 250, "horizontalPenaltyCostP2": 500, "p1Config": { "defaultValue": 11, "edgeThreshold": 15, "edgeValue": 10, "enableAdaptive": true, "smoothThreshold": 5, "smoothValue": 22 }, "p2Config": { "defaultValue": 33, "edgeValue": 22, "enableAdaptive": true, "smoothValue": 63 }, "verticalPenaltyCostP1": 250, "verticalPenaltyCostP2": 500 }, "costMatching": { "confidenceThreshold": 55, "disparityWidth": 1, "enableCompanding": false, "enableSwConfidenceThresholding": false, "invalidDisparityValue": 0, "linearEquationParameters": { "alpha": 0, "beta": 2, "threshold": 127 } }, "filtersBackend": 2, "postProcessing": { "adaptiveMedianFilter": { "confidenceThreshold": 200, "enable": true }, "bilateralSigmaValue": 0, "brightnessFilter": { "maxBrightness": 256, "minBrightness": 0 }, "decimationFilter": { "decimationFactor": 1, "decimationMode": 0 }, "filteringOrder": [ 3, 1, 2, 4, 5 ], "holeFilling": { "enable": true, "fillConfidenceThreshold": 200, "highConfidenceThreshold": 210, "invalidateDisparities": true, "minValidDisparity": 1 }, "median": 0, "spatialFilter": { "alpha": 0.5, "delta": 3, "enable": false, "holeFillingRadius": 2, "numIterations": 1 }, "speckleFilter": { "differenceThreshold": 2, "enable": false, "speckleRange": 50 }, "temporalFilter": { "alpha": 0.4000000059604645, "delta": 3, "enable": false, "persistencyMode": 3 }, "thresholdFilter": { "maxRange": 65535, "minRange": 0 } } }, "mesh": { "meshLeftUri": "", "meshRightUri": "", "meshSize": null, "stepHeight": 16, "stepWidth": 16 }, "numFramesPool": 3, "numPostProcessingMemorySlices": -1, "numPostProcessingShaves": -1, "outHeight": null, "outKeepAspectRatio": true, "outWidth": null, "rectificationUseSpecTranslation": null, "rectifyEdgeFillColor": 0, "useHomographyRectification": null, "width": null } } ], [ 4, { "alias": "", "id": 4, "ioInfo": [ [ [ "", "inputDepth" ], { "blocking": false, "group": "", "id": 29, "name": "inputDepth", "queueSize": 4, "type": 3, "waitForMessage": true } ], [ [ "", "boundingBoxMapping" ], { "blocking": false, "group": "", "id": 33, "name": "boundingBoxMapping", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "inputImg" ], { "blocking": true, "group": "", "id": 30, "name": "inputImg", "queueSize": 2, "type": 3, "waitForMessage": true } ], [ [ "", "inputDetections" ], { "blocking": true, "group": "", "id": 31, "name": "inputDetections", "queueSize": 1, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 32, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthroughDepth" ], { "blocking": false, "group": "", "id": 34, "name": "passthroughDepth", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "spatialLocationCalculatorOutput" ], { "blocking": false, "group": "", "id": 35, "name": "spatialLocationCalculatorOutput", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "SpatialDetectionNetwork", "parentId": -1, "properties": { "calculationAlgorithm": 4, "depthThresholds": { "lowerThreshold": 100, "upperThreshold": 5000 }, "detectedBBScaleFactor": 0.5 } } ], [ 5, { "alias": "neuralNetwork", "id": 5, "ioInfo": [ [ [ "", "in" ], { "blocking": false, "group": "", "id": 36, "name": "in", "queueSize": 3, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 37, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthrough" ], { "blocking": false, "group": "", "id": 38, "name": "passthrough", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "NeuralNetwork", "parentId": 4, "properties": { "backend": "", "backendProperties": {}, "blobSize": null, "blobUri": "", "modelSource": 1, "modelUri": "asset:__model", "numFrames": 8, "numNCEPerThread": 0, "numShavesPerThread": 0, "numThreads": 0 } } ], [ 6, { "alias": "detectionParser", "id": 6, "ioInfo": [ [ [ "", "in" ], { "blocking": true, "group": "", "id": 39, "name": "in", "queueSize": 1, "type": 3, "waitForMessage": true } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 40, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "DetectionParser", "parentId": 4, "properties": { "networkInputs": {}, "numFramesPool": 8, "parser": { "anchorMasks": {}, "anchors": [], "anchorsV2": [], "classNames": [ "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush" ], "classes": 80, "confidenceThreshold": 0.6000000238418579, "coordinates": 4, "iouThreshold": 0.5, "nnFamily": 0, "subtype": "yolov6r2" } } } ], [ 7, { "alias": "depthAlign", "id": 7, "ioInfo": [ [ [ "", "inputConfig" ], { "blocking": false, "group": "", "id": 41, "name": "inputConfig", "queueSize": 4, "type": 3, "waitForMessage": false } ], [ [ "", "inputAlignTo" ], { "blocking": false, "group": "", "id": 43, "name": "inputAlignTo", "queueSize": 1, "type": 3, "waitForMessage": true } ], [ [ "", "input" ], { "blocking": false, "group": "", "id": 42, "name": "input", "queueSize": 4, "type": 3, "waitForMessage": false } ], [ [ "", "outputAligned" ], { "blocking": false, "group": "", "id": 44, "name": "outputAligned", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthroughInput" ], { "blocking": false, "group": "", "id": 45, "name": "passthroughInput", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "ImageAlign", "parentId": 4, "properties": { "alignHeight": 0, "alignWidth": 0, "initialConfig": { "staticDepthPlane": 0 }, "interpolation": -1, "numFramesPool": 4, "numShaves": 2, "outKeepAspectRatio": true, "warpHwIds": [] } } ], [ 8, { "alias": "", "id": 8, "ioInfo": [ [ [ "", "inputTrackerFrame" ], { "blocking": false, "group": "", "id": 46, "name": "inputTrackerFrame", "queueSize": 4, "type": 3, "waitForMessage": true } ], [ [ "", "inputDetectionFrame" ], { "blocking": false, "group": "", "id": 47, "name": "inputDetectionFrame", "queueSize": 4, "type": 3, "waitForMessage": true } ], [ [ "", "inputDetections" ], { "blocking": false, "group": "", "id": 48, "name": "inputDetections", "queueSize": 4, "type": 3, "waitForMessage": true } ], [ [ "", "inputConfig" ], { "blocking": false, "group": "", "id": 49, "name": "inputConfig", "queueSize": 4, "type": 3, "waitForMessage": false } ], [ [ "", "passthroughDetections" ], { "blocking": false, "group": "", "id": 53, "name": "passthroughDetections", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "out" ], { "blocking": false, "group": "", "id": 50, "name": "out", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthroughTrackerFrame" ], { "blocking": false, "group": "", "id": 51, "name": "passthroughTrackerFrame", "queueSize": 8, "type": 0, "waitForMessage": false } ], [ [ "", "passthroughDetectionFrame" ], { "blocking": false, "group": "", "id": 52, "name": "passthroughDetectionFrame", "queueSize": 8, "type": 0, "waitForMessage": false } ] ], "logLevel": 3, "name": "ObjectTracker", "parentId": -1, "properties": { "detectionLabelsToTrack": [ 0 ], "maxObjectsToTrack": 60, "occlusionRatioThreshold": 0.20000000298023224, "trackerIdAssignmentPolicy": 1, "trackerThreshold": 0.0, "trackerType": 3, "trackingPerClass": true, "trackletBirthThreshold": 3, "trackletMaxLifespan": 120 } } ] ] } } ``` ## Source code #### Python ```python #!/usr/bin/env python3 import cv2 import depthai as dai import time fullFrameTracking = False useSpatialAssociation = False # Create pipeline with dai.Pipeline() as pipeline: # Define sources and outputs camRgb = pipeline.create(dai.node.Camera).build(dai.CameraBoardSocket.CAM_A) monoLeft = pipeline.create(dai.node.Camera).build(dai.CameraBoardSocket.CAM_B) monoRight = pipeline.create(dai.node.Camera).build(dai.CameraBoardSocket.CAM_C) stereo = pipeline.create(dai.node.StereoDepth) leftOutput = monoLeft.requestOutput((640, 400)) rightOutput = monoRight.requestOutput((640, 400)) leftOutput.link(stereo.left) rightOutput.link(stereo.right) spatialDetectionNetwork = pipeline.create(dai.node.SpatialDetectionNetwork).build(camRgb, stereo, "yolov6-nano") objectTracker = pipeline.create(dai.node.ObjectTracker) spatialDetectionNetwork.setConfidenceThreshold(0.6) spatialDetectionNetwork.input.setBlocking(False) spatialDetectionNetwork.setBoundingBoxScaleFactor(0.5) spatialDetectionNetwork.setDepthLowerThreshold(100) spatialDetectionNetwork.setDepthUpperThreshold(5000) labelMap = spatialDetectionNetwork.getClasses() objectTracker.setDetectionLabelsToTrack([0]) # track only person # possible tracking types: ZERO_TERM_COLOR_HISTOGRAM, ZERO_TERM_IMAGELESS, SHORT_TERM_IMAGELESS, SHORT_TERM_KCF objectTracker.setTrackerType(dai.TrackerType.SHORT_TERM_IMAGELESS) # take the smallest ID when new object is tracked, possible options: SMALLEST_ID, UNIQUE_ID objectTracker.setTrackerIdAssignmentPolicy(dai.TrackerIdAssignmentPolicy.SMALLEST_ID) if useSpatialAssociation: objectTracker.setSpatialAssociation(True) objectTracker.setSpatialAssociationWeight(0.5) objectTracker.setSpatialDistanceThreshold(1.5) objectTracker.setSpatialDepthAwareScale(0.1) preview = objectTracker.passthroughTrackerFrame.createOutputQueue() tracklets = objectTracker.out.createOutputQueue() if fullFrameTracking: camRgb.requestFullResolutionOutput().link(objectTracker.inputTrackerFrame) # do not block the pipeline if it's too slow on full frame objectTracker.inputTrackerFrame.setBlocking(False) objectTracker.inputTrackerFrame.setMaxSize(1) else: spatialDetectionNetwork.passthrough.link(objectTracker.inputTrackerFrame) spatialDetectionNetwork.passthrough.link(objectTracker.inputDetectionFrame) spatialDetectionNetwork.out.link(objectTracker.inputDetections) startTime = time.monotonic() counter = 0 fps = 0 color = (255, 255, 255) pipeline.start() while(pipeline.isRunning()): imgFrame = preview.get() track = tracklets.get() assert isinstance(imgFrame, dai.ImgFrame), "Expected ImgFrame" assert isinstance(track, dai.Tracklets), "Expected Tracklets" counter+=1 current_time = time.monotonic() if (current_time - startTime) > 1 : fps = counter / (current_time - startTime) counter = 0 startTime = current_time frame = imgFrame.getCvFrame() trackletsData = track.tracklets for t in trackletsData: roi = t.roi.denormalize(frame.shape[1], frame.shape[0]) x1 = int(roi.topLeft().x) y1 = int(roi.topLeft().y) x2 = int(roi.bottomRight().x) y2 = int(roi.bottomRight().y) try: label = labelMap[t.label] except: label = t.label cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"ID: {[t.id]}", (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, t.status.name, (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.rectangle(frame, (x1, y1), (x2, y2), color, cv2.FONT_HERSHEY_SIMPLEX) cv2.putText(frame, f"X: {int(t.spatialCoordinates.x)} mm", (x1 + 10, y1 + 65), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"Y: {int(t.spatialCoordinates.y)} mm", (x1 + 10, y1 + 80), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"Z: {int(t.spatialCoordinates.z)} mm", (x1 + 10, y1 + 95), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) if t.velocity is not None and t.speed is not None: cv2.putText(frame, f"Velocity X: {t.velocity.x:.2f} m/s", (x1 + 10, y1 + 110), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"Velocity Y: {t.velocity.y:.2f} m/s", (x1 + 10, y1 + 125), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"Velocity Z: {t.velocity.z:.2f} m/s", (x1 + 10, y1 + 140), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, f"Speed: {t.speed:.2f} m/s", (x1 + 10, y1 + 155), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255) cv2.putText(frame, "NN fps: {:.2f}".format(fps), (2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color) cv2.imshow("tracker", frame) if cv2.waitKey(1) == ord('q'): break ``` #### C++ ```cpp #include #include #include #include #include "depthai/pipeline/datatype/Tracklets.hpp" int main() { bool fullFrameTracking = false; bool useSpatialAssociation = false; // Create pipeline dai::Pipeline pipeline; // Define sources and outputs auto camRgb = pipeline.create()->build(dai::CameraBoardSocket::CAM_A); auto monoLeft = pipeline.create()->build(dai::CameraBoardSocket::CAM_B); auto monoRight = pipeline.create()->build(dai::CameraBoardSocket::CAM_C); // Create stereo node auto stereo = pipeline.create(); auto leftOutput = monoLeft->requestOutput(std::make_pair(640, 400)); auto rightOutput = monoRight->requestOutput(std::make_pair(640, 400)); leftOutput->link(stereo->left); rightOutput->link(stereo->right); // Create spatial detection network dai::NNModelDescription modelDescription{"yolov6-nano"}; auto spatialDetectionNetwork = pipeline.create()->build(camRgb, stereo, modelDescription); spatialDetectionNetwork->setConfidenceThreshold(0.6f); spatialDetectionNetwork->input.setBlocking(false); spatialDetectionNetwork->setBoundingBoxScaleFactor(0.5f); spatialDetectionNetwork->setDepthLowerThreshold(100); spatialDetectionNetwork->setDepthUpperThreshold(5000); // Create object tracker auto objectTracker = pipeline.create(); objectTracker->setDetectionLabelsToTrack({0}); // track only person objectTracker->setTrackerType(dai::TrackerType::SHORT_TERM_IMAGELESS); objectTracker->setTrackerIdAssignmentPolicy(dai::TrackerIdAssignmentPolicy::SMALLEST_ID); if(useSpatialAssociation) { objectTracker->setSpatialAssociation(true); objectTracker->setSpatialAssociationWeight(0.5f); objectTracker->setSpatialDistanceThreshold(1.5f); objectTracker->setSpatialDepthAwareScale(0.1f); } // Create output queues auto preview = objectTracker->passthroughTrackerFrame.createOutputQueue(); auto tracklets = objectTracker->out.createOutputQueue(); // Link nodes if(fullFrameTracking) { camRgb->requestFullResolutionOutput()->link(objectTracker->inputTrackerFrame); objectTracker->inputTrackerFrame.setBlocking(false); objectTracker->inputTrackerFrame.setMaxSize(1); } else { spatialDetectionNetwork->passthrough.link(objectTracker->inputTrackerFrame); } spatialDetectionNetwork->passthrough.link(objectTracker->inputDetectionFrame); spatialDetectionNetwork->out.link(objectTracker->inputDetections); // Start pipeline pipeline.start(); // FPS calculation variables auto startTime = std::chrono::steady_clock::now(); int counter = 0; float fps = 0; cv::Scalar color(255, 255, 255); while(pipeline.isRunning()) { auto imgFrame = preview->get(); auto track = tracklets->get(); counter++; auto currentTime = std::chrono::steady_clock::now(); auto elapsed = std::chrono::duration_cast(currentTime - startTime).count(); if(elapsed >= 1) { fps = counter / static_cast(elapsed); counter = 0; startTime = currentTime; } cv::Mat frame = imgFrame->getCvFrame(); auto trackletsData = track->tracklets; for(const auto& t : trackletsData) { auto roi = t.roi.denormalize(frame.cols, frame.rows); int x1 = static_cast(roi.topLeft().x); int y1 = static_cast(roi.topLeft().y); int x2 = static_cast(roi.bottomRight().x); int y2 = static_cast(roi.bottomRight().y); std::string label; try { label = spatialDetectionNetwork->getClasses().value()[t.label]; } catch(...) { label = std::to_string(t.label); } cv::putText(frame, label, cv::Point(x1 + 10, y1 + 20), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, "ID: " + std::to_string(t.id), cv::Point(x1 + 10, y1 + 35), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, std::string(t.status == dai::Tracklet::TrackingStatus::LOST ? "LOST" : "TRACKED"), cv::Point(x1 + 10, y1 + 50), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::rectangle(frame, cv::Point(x1, y1), cv::Point(x2, y2), color, cv::FONT_HERSHEY_SIMPLEX); cv::putText(frame, "X: " + std::to_string(static_cast(t.spatialCoordinates.x)) + " mm", cv::Point(x1 + 10, y1 + 65), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, "Y: " + std::to_string(static_cast(t.spatialCoordinates.y)) + " mm", cv::Point(x1 + 10, y1 + 80), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, "Z: " + std::to_string(static_cast(t.spatialCoordinates.z)) + " mm", cv::Point(x1 + 10, y1 + 95), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); if(t.velocity && t.speed) { const auto& velocity = *t.velocity; cv::putText(frame, cv::format("Velocity X: %.2f m/s", velocity.x), cv::Point(x1 + 10, y1 + 110), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, cv::format("Velocity Y: %.2f m/s", velocity.y), cv::Point(x1 + 10, y1 + 125), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, cv::format("Velocity Z: %.2f m/s", velocity.z), cv::Point(x1 + 10, y1 + 140), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); cv::putText(frame, cv::format("Speed: %.2f m/s", *t.speed), cv::Point(x1 + 10, y1 + 155), cv::FONT_HERSHEY_TRIPLEX, 0.5, color); } } cv::putText(frame, "NN fps: " + std::to_string(fps).substr(0, 4), cv::Point(2, frame.rows - 4), cv::FONT_HERSHEY_TRIPLEX, 0.4, color); cv::imshow("tracker", frame); if(cv::waitKey(1) == 'q') { break; } } return 0; } ``` ### Need assistance? Head over to [Discussion Forum](https://discuss.luxonis.com/) for technical support or any other questions you might have.