The ZED SDK allows you to add depth, motion sensing and spatial AI to your application. Available as a standalone installer, it includes applications, tools and sample projects with source code.
Maintenance mode versions (legacy)
These versions are too old and no longer fully supported, the AI module is running older version of models and performance and accuracy can be significantly lower.
Oct 9, 2021
ZED SDK 3.5 introduces a major improvement in the Body Tracking module which is now up to 2.5 faster and 30% more accurate and a new medium mode.
Besides, it also introduces a new way to retrieve detected objects in batches, powered by deep learning Re-Identification and appearance matching. This allows to keep the same ID for a detected object even if it has been occluded, hidden or out of the scene for some time.
Finally, the ZED SDK 3.5 adds the support of the upcoming ZED 2i.
sl::Camera::open() when camera was not properly detected.sl::DETECTION_MODEL::HUMAN_BODY_* models on Linux during model optimization.sl::Camera::open() when serial number is detected as 0. This previously returned sl::ERROR_CODE::SUCCESS even when the serial number was invalid. This now returns sl::ERROR_CODE::CAMERA_NOT_DETECTED.nvidia-encoder library that could potentially break the encoding in docker environment (Linux only, introduced in 3.5.3).--dc option when used for ZED 2i. It was reporting a wrong serial number.--cimu option for ZED 2 and ZED 2i. It now properly resets the runtime bias saved in memory.sl::Camera::open() function.sl::ERROR_CODE::END_OF_SVOFILE_REACHED was not reached, leading to a infinite loop.sl::Camera::setSVOPosition().sl::Camera::close() when using multiple cameras at the same time, especially when one camera was close before others.sl::Camera::open() function when using streaming input mode.sl::Camera::getSpatialMappingParameters() returning false values.MULTI_CLASS_BOX_XX or HUMAN_BODY_XX) when the depth sl::SENSING_MODE::FILL parameter was used.sl.Mat.get_value() function.FAST mode is now x5(jetson)/x1.5(desktop) faster compared to FAST v3.4.MEDIUM mode is x2(jetson) faster compared to FAST v3.4.MEDIUM mode is 28% more precise compared to FAST v3.4ACCURATE mode is now x2 faster compared to ACCURATE v3.4ACCURATE mode is now 10% more precise compared to ACCURATE v3.4sl::ObjectsBatch structure.sl::ObjectDetectionParameters::BatchParameters. See the API documentation for more information.sl::Camera::retrieveObjects() to ingest the live objects into the batching system.sl::Camera::getObjectsBatch(std::vector&).sl::ObjectsBatch is bound to a specific ID. it contains the list of timestamps, positions, bbox,... Each list have the exact same size.MULTI_CLASS models) which slighty improve runtime (5%) and accuracy (2.5%).MULTI_CLASS_BOX_MEDIUM mode, x2 faster compared to ACCURATE mode while being 20% more precise compared to FAST.sl::TRACKING_STATE::SEARCHING, in Object Detection module, leading to better recovery and avoid "flying" boxes.sl_zed static library to avoid performance and compatibility issues. To use the AI module in static compilation, the dynamic library of sl_ai will still be needed. JetPack 4.4 and 4.5 now have support for the static librarysl.Mat().set_value and sl.Mat().set_to functions.sl.Mat().get_data function for a Mat of type sl.MAT_TYPE.U16_C1.NONE.zedsrc to match the names in the ZED SDKDEPTH16_MM data type for depth (OPENNI MODE)zed-ros-examplesstart_object_detection service has been modified to match the new features:model parameter to choose the AI modelmax_range parameter to limit the detection rangesk_body_fitting parameter to enable Skeleton fitting for skeleton AI modelspeople -> mc_people to indicate that it is related to multiclass AI modelsvehicles -> mc_vehicles to indicate that it is related to multiclass AI modelsmc_bag parameter to enable bags detection with multiclass AI modelsmc_animal parameter to enable animals detection with multiclass AI modelsmc_electronics parameter to enable electronic devices detection with multiclass AI modelsmc_fruit_vegetable parameter to enable fruits and vegetables detection with multiclass AI modelsFor older releases and changelog, see the ZED SDK release archive.