diff --git a/modules/ANSODEngine/ANSODEngine.cpp b/modules/ANSODEngine/ANSODEngine.cpp index 0aede5d..4a925b2 100644 --- a/modules/ANSODEngine/ANSODEngine.cpp +++ b/modules/ANSODEngine/ANSODEngine.cpp @@ -594,18 +594,52 @@ namespace ANSCENTER } } - // Step 1: Convert Object[] → TrackerObject[] + // Adaptive padding: tiny objects produce near-zero inter-frame IoU, + // so ByteTrack/IoU matching drops them. We pad small boxes only + // when feeding the tracker; detections[i].box is never modified + // and the un-padded size is recovered for ghost rendering. + // Thresholds are internal by design — no user-facing knob. + constexpr int SMALL_THRESHOLD_PX = 32; // below this: full pad + constexpr int LARGE_THRESHOLD_PX = 96; // at/above this: no pad + constexpr float MAX_PAD_RATIO = 0.5f; // applied to smallest + auto computePadRatio = [](int maxDim) -> float { + if (maxDim >= LARGE_THRESHOLD_PX) return 0.0f; + if (maxDim <= SMALL_THRESHOLD_PX) return MAX_PAD_RATIO; + float t = static_cast(LARGE_THRESHOLD_PX - maxDim) / + static_cast(LARGE_THRESHOLD_PX - SMALL_THRESHOLD_PX); + return MAX_PAD_RATIO * t; + }; + auto padBox = [](const cv::Rect& b, float r) -> cv::Rect { + if (r <= 0.0f) return b; + int pw = static_cast(b.width * r); + int ph = static_cast(b.height * r); + return cv::Rect(b.x - pw, b.y - ph, + b.width + 2 * pw, b.height + 2 * ph); + }; + + // Step 1: Convert Object[] → TrackerObject[] using adaptive padding. + // paddedBoxes[i] mirrors detections[i] so step-3 matching happens + // in padded space without altering the original detection boxes. std::vector trackerInput; + std::vector paddedBoxes; trackerInput.reserve(detections.size()); + paddedBoxes.reserve(detections.size()); + int paddedCount = 0; for (const auto& obj : detections) { + int maxDim = std::max(obj.box.width, obj.box.height); + float ratio = computePadRatio(maxDim); + cv::Rect padded = padBox(obj.box, ratio); + paddedBoxes.push_back(padded); + if (ratio > 0.0f) ++paddedCount; + TrackerObject tobj{}; tobj.track_id = 0; tobj.class_id = obj.classId; tobj.prob = obj.confidence; - tobj.x = static_cast(obj.box.x); - tobj.y = static_cast(obj.box.y); - tobj.width = static_cast(obj.box.width); - tobj.height = static_cast(obj.box.height); + tobj.x = static_cast(padded.x); + tobj.y = static_cast(padded.y); + tobj.width = static_cast(padded.width); + tobj.height = static_cast(padded.height); tobj.left = tobj.x; tobj.top = tobj.y; tobj.right = tobj.x + tobj.width; @@ -613,20 +647,26 @@ namespace ANSCENTER tobj.object_id = camera_id; trackerInput.push_back(tobj); } + ANS_DBG("ANSOD_Tracker", + "this=%p cam=%s ApplyTracking dets=%d padded=%d", + (void*)this, camera_id.c_str(), + (int)detections.size(), paddedCount); - // Step 2: Run per-camera tracker + // Step 2: Run per-camera tracker (operates in padded space) auto trackerOutput = camera._tracker->UpdateTracker(0, trackerInput); - // Step 3: IoU-match tracked objects back to detections, assign trackId + // Step 3: IoU-match tracker output to detections in padded space, + // then assign trackId to the matching detection. detections[i].box + // remains the original un-padded box. for (const auto& tobj : trackerOutput) { cv::Rect trkBox(static_cast(tobj.x), static_cast(tobj.y), static_cast(tobj.width), static_cast(tobj.height)); float bestIoU = 0.f; int bestIdx = -1; - for (int i = 0; i < static_cast(detections.size()); ++i) { - cv::Rect inter = trkBox & detections[i].box; + for (int i = 0; i < static_cast(paddedBoxes.size()); ++i) { + cv::Rect inter = trkBox & paddedBoxes[i]; float interArea = static_cast(inter.area()); - float unionArea = static_cast(trkBox.area() + detections[i].box.area()) - interArea; + float unionArea = static_cast(trkBox.area() + paddedBoxes[i].area()) - interArea; float iou = (unionArea > 0.f) ? interArea / unionArea : 0.f; if (iou > bestIoU) { bestIoU = iou; @@ -638,15 +678,16 @@ namespace ANSCENTER } } - // Step 4: If stabilization enabled, inject ghost objects for unmatched tracker predictions + // Step 4: If stabilization enabled, inject ghost objects for unmatched + // tracker predictions. Ghost.box uses the last-known un-padded size + // from track history at the tracker's predicted center — so users + // never see the inflated padded box that lives inside the tracker. if (_stabilizationEnabled) { - // Collect trackIds already assigned to real detections std::set matchedTrackIds; for (const auto& det : detections) { if (det.trackId > 0) matchedTrackIds.insert(det.trackId); } - // Tracker-predicted objects not matched to any detection are "ghosts" for (const auto& tobj : trackerOutput) { if (tobj.track_id <= 0) continue; if (matchedTrackIds.count(tobj.track_id) > 0) continue; @@ -655,9 +696,26 @@ namespace ANSCENTER ghost.trackId = tobj.track_id; ghost.classId = tobj.class_id; ghost.confidence = tobj.prob; - ghost.box = cv::Rect( - static_cast(tobj.x), static_cast(tobj.y), - static_cast(tobj.width), static_cast(tobj.height)); + + // Prefer history's un-padded size; fall back to tracker box + // only when no history exists (brand-new track that ghosts + // before any confirmed real detection — rare edge case). + auto histIt = camera._trackHistories.find(tobj.track_id); + if (histIt != camera._trackHistories.end() && + histIt->second.lastBox.width > 0 && + histIt->second.lastBox.height > 0) { + const cv::Rect& last = histIt->second.lastBox; + int cx = static_cast(tobj.x + tobj.width * 0.5f); + int cy = static_cast(tobj.y + tobj.height * 0.5f); + ghost.box = cv::Rect(cx - last.width / 2, + cy - last.height / 2, + last.width, last.height); + } + else { + ghost.box = cv::Rect( + static_cast(tobj.x), static_cast(tobj.y), + static_cast(tobj.width), static_cast(tobj.height)); + } ghost.cameraId = camera_id; TagStabilized(ghost.extraInfo); detections.push_back(ghost); diff --git a/tests/ANSODEngine-UnitTest/ANSODEngine-UnitTest.cpp b/tests/ANSODEngine-UnitTest/ANSODEngine-UnitTest.cpp index ce79d7c..2e52bda 100644 --- a/tests/ANSODEngine-UnitTest/ANSODEngine-UnitTest.cpp +++ b/tests/ANSODEngine-UnitTest/ANSODEngine-UnitTest.cpp @@ -2196,11 +2196,25 @@ int VideoDetectorEngine_CPP(std::string modelFilePath, std::string videoFilePath int RTMPOSETest_CPP() { int modelType = 32; // ONNXRTMPOSE (use 33 for RTRTMPOSE) std::string modelFilePath = "E:\\Programs\\DemoAssets\\ANSAIModels\\PoseEstimationModels\\ANSRTMPOSE.zip"; - std::string videoFile = "E:\\Programs\\DemoAssets\\Videos\\rtmpose.mp4"; + std::string videoFile = "E:\\Programs\\DemoAssets\\Videos\\ANSOffice.mp4";// "E:\\Programs\\DemoAssets\\Videos\\rtmpose.mp4"; VideoDetectorEngine_CPP(modelFilePath, videoFile, modelType); return 0; } +// YOLO OD via the direct cv::Mat / typed-Object path. Use this to verify +// trackIds reach the overlay — the JPEG/JSON variant strips track_id in +// VectorDetectionToJsonString (ANSEngineCommon.cpp:1122-1123), so the +// JSON overlay always shows ":0". This _CPP path reads obj.trackId +// directly so adaptive-padding tracker output is visible. +int YOLO26ODYolo11Test_CPP() { + std::string modelFilePath = "C:\\Projects\\ANSVIS\\Models\\ANS_VehicleDetection_v2.0.zip"; + std::string videoFile = "C:\\ProgramData\\ANSCENTER\\Shared\\road.mp4"; + int modelType = 3; // auto-detect (matches YOLO26ODYolo11Test) + int modelDetectionType = 1; // object detection + VideoDetectorEngine_CPP(modelFilePath, videoFile, modelType, modelDetectionType); + return 0; +} + int RTMPOSETest() { int modelType = 33; // ONNX YOLO (30) RT YOLO (31) std::string onnxclmodelFilePath = "E:\\Programs\\DemoAssets\\ANSAIModels\\PoseEstimationModels\\ANSRTMPOSE.zip"; @@ -2215,8 +2229,8 @@ int main() //ALPROD_Test(); //FireNSmokeTest(); //ElasticGPUTest(); - - RTMPOSETest(); + RTMPOSETest_CPP(); + //RTMPOSETest(); //YOLO26SEGYolo11Test(); //YOLO26POSEYolo11Test(); //YOLO26CLYolo11Test();