Central engineering reference and operations manual for the MRDT Autonomy Software.
View the Project on GitHub MissouriMRDT/Autonomy_Software
Return to RoveSoDocs Guides for Today, Tomorrow, and Forever.
The ObjectDetectionHandler (src/handlers/ObjectDetectionHandler.h & ObjectDetectionHandler.cpp) orchestrates all deep-learning prop and obstacle detection pipelines across active camera feeds.
OBJECTDETECT_TORCH_MODEL) onto GPU memory via CUDA (supporting both baseline bmp_v6 and competition-tuned bmp_v7 Tucumcari weights).ObjectDetector instances for assigned cameras (eHeadMainCam, eRearCam).RequestDetectionOverlayFrame()) displaying bounding boxes, class labels, and confidence scores.RecordingHandler configured in RecordingType::eObjectDetectionHandler mode to record annotated detection video.Access to detector instances is provided via the ObjectDetectors enumeration:
ObjectDetectors::eHeadMainCam: Primary detector analyzing the forward camera stream.ObjectDetectors::eRearCam: Secondary detector analyzing the rear camera stream when enabled.ObjectDetector executes on its own AutonomyThread<void>.constants::OBJECTDETECT_MAINCAM_MAX_FPS.objectdetectutils::Object structs, which ObjectDetectionChecker evaluates against requested leg types (Mallet, Water Bottle, Rock Pick).// Initialization in main.cpp
globals::g_pObjectDetectionHandler = new ObjectDetectionHandler();
globals::g_pObjectDetectionHandler->StartAllDetectors();
globals::g_pObjectDetectionHandler->StartRecording();
// Querying detection overlay for UI streaming:
cv::Mat cvAnnotatedFrame = globals::g_pObjectDetectionHandler->RequestDetectionOverlayFrame(
ObjectDetectionHandler::ObjectDetectors::eHeadMainCam
);