Release Notes
V3.1.2 Change Logs (16/12/2022)
Prophesee Devices
Fixed license in source code header of a plugin file
In Windows installer, add deployment of a driver that enables firmware recovery for EVK3 and EVK4
OpenEB
Added code sample showing how to record a RAW file using the Python API
Split Tracking samples documentation into Generic Tracking and Spatter Tracking
Reviewed
RawReader Python class
to lower its memory consumptionFixed issue in pipeline
FrameDisplayStage
preventing it to work properly when instantiated several times in a rowMinor enhancements in Getting Started Guide for SDK in Python for better clarity
Metavision SDK
Fixed some includes in code samples for CV and Analytics module
Documentation
Enhanced Installation Guides: upgrade from previous version, dependencies installation, camera plugins configuration etc.
V3.1.1 Change Logs (23/11/2022)
Prophesee Devices
Fixed issue in Gen31-based EVKs plugins preventing to set bias_refr in some specific situations
OpenEB
In Core module, fixed issue in seek_event() Python function in RawReader module
Synchronization samples are now displaying master/slave information in window’s name
Metavision SDK
Added missing includes in some header files of CV module
Metavision Studio
Fixed bug resulting in Display Settings tuning lost when reading a RAW file multiple times
Documentation
Fixed list of required dependencies for OpenEB
Updated the information related to PyTorch installation
Added information on the loading order of camera plugins
Added note about Trigger In polarity inversion for EVK4 in Timing Interfaces page
Enhanced API documentation of BaseFrameGenerationAlgorithm in Python
V3.1.0 Change Logs (17/10/2022)
Prophesee Devices
Released new firmware for EVK3 and EVK4, upgrade is required (To have access to this page, request an account in the Knowledge Center)
Fixed error raised when activating Trigger In on EVK4
Fixed sensor configuration to avoid events being produced outside of ROI in some specific circumstances
Removed register address check against register map when reading and writing camera register using the Hardware Register facility
OpenEB
New version of the EVT3 decoder with protocol violation detection and mitigation
Metavision SDK
In ML module, fixed bugs in loading and filtering bounding boxes from box_processing.py
In ML module, fixed bugs in model inheritance of flow and detection module
In Calibration module, fixed issues with refinement mode in metavision_mono_calibration application and improved usability of show_calibrated_poses Python sample
Metavision Studio
Improved performance when streaming from live camera and RAW files
Added alert mechanism on errors raised by EVT3 protocol violation
Documentation
Pages on Cameras Synchronization and Timing Interfaces were fully revamped
Fixed some wrong references in Quick Start of ML module
V3.0.2 Change Logs (01/07/2022)
Prophesee Devices
Fixed clocking issue in IMX636-based EVKs plugins causing event timestamping to be faster than clock time
OpenEB
Integrate community contribution to pass a specific Python version when generating Makefile
Integrate community contribution to control the udev rules installation
V3.0.1 Change Logs (21/06/2022)
General
New version (1.1) of the Metavision License with updated information about the Source offer
OpenEB
Fixed Github Action CI
Documentation
Added list of supported cameras for OpenEB
Added some example videos in Core ML sample guides
Added missing steps for FFMPEG in the install guides
Fixed Trigger In channel ID for EVK3 Gen4.1
V3.0.0 Change Logs (31/05/2022)
General
Source code of Prophesee plugins is now distributed with OpenEB for devices based on Gen3.1, Gen4.1 and the latest IMX636 sensors
Full Python API and C++ API & samples are now distributed in pre-compiled Metavision SDK packages with free license
Metavision Studio can now be installed using dedicated packages for simplicity
Dedicated packages for pre-compiled Prophesee device plugins have been discontinued; these plugins are still installed using the packages for Metavision SDK or Metavision Studio
OpenEB
General changes
Introduced source code of plugins for devices based on Gen3.1, Gen4.1 and IMX636 sensors
Removed RAW plugins used to replay RAW recordings (replaced by the live device plugins)
New Core ML module open-sourcing core features for event-based machine learning
video_to_event simulator to generate events from frame-based data, including a GPU version to enable integrating event simulation directly in the training pipeline
event_to_video model plus inference and training pipelines, enabling reconstruction of grayscale data from events
Fixes
metavision_viewer_android sample in Driver module is not crashing anymore when loading a RAW recording
Incomplete RAW index files caused by app interruption during the generation is now detected and handled correctly
Metavision SDK
Full Python API and C++ API & samples are now distributed in pre-compiled Metavision SDK packages with free license
Upgraded the versions of the required dependencies for Python on Ubuntu and Windows and for C++ on Windows
Renamed show_extrinsics sample in Calibration module into show_calibrated_poses
Changed metavision_detection_and_tracking_pipeline app in the ML module into a sample to make deployment more flexible
Metavision Studio
Added tooltips and links to pages in the online documentation
Added an “auto” accumulation time option inferring accumulation time from the chosen framerate
Region of interest can now be defined interactively on display using the pointer
Interactively setting the threshold of the Event Trail Filter module does not disable silently this module anymore
Negative bias values can now be correctly entered using the keyboard
Various improvements of UI/UX
V2.3.2 Change Logs (31/03/2022)
OpenEB
Fixed pytest of Core module that relied on a recording outside datasets/openeb/ archive
Prophesee Devices
New feature
Introduced new plugin for IMX636-based EVK4 device
Bug fixes
Fixed bug preventing EVK3 Gen3.1 to stream when mode changed with set_mode_master and set_mode_standalone
Documentation
Enhanced user guide of Metavision Studio
Fixed minor errors in install guides of Metavision Essentials on Ubuntu and Windows
Added information on the classes of the C++ API in the Python bindings documentation
V2.3.1 Change Logs (31/01/2022)
OpenEB
Changes
Deprecated naming for classes TTrailFilterAlgorithm and TMostRecentTimestampBuffer, replaced by TrailFilterAlgorithmT and MostRecentTimestampBufferT.
Clarified documentation and standalone sample implementation for EVT3 decoder
Bug fixes
Fixed bug resulting in non-monotonic timestamps returned by successive calls to I_Decoder::get_last_timestamp() with some EVT3 recordings
Fixed behavior of TMostRecentTimestampBuffer::generate_img_time_surface() sometimes leading to erroneous results
Metavision Studio
Changes
Added dedicated support for IMX636 in Metavision Studio
Date time string used to name recordings is now using local-time instead of UTC time
Various improvements to UI
Bug fixes
Fixed bug resulting in last events in a recording to never be displayed
Metavision SDK
Python sample for ground plane calibration is now available in Essentials offer for Calibration module
Prophesee Devices
Introduced new plugin for IMX636-based EVK3 device
Documentation
Fixed the imports of EventBbox in detection_and_tracking notebook
Added torchmetrics, seaborn & sk-video to python_requirement.txt
Updated download links for CUDA 10.2 LibTorch to a fixed version
Fixed typos in the classification tutorial
V2.3.0 Change Logs (11/10/2021)
General
Released new firmware for EVK2, upgrade is required (contact us to get access to the page)
Upgraded required pybind11 version from 2.4.3 to 2.6.0 when building from sources
Reorganized the test dataset archive to enable partial downloads
Reviewed the Ubuntu packages architecture for Essentials. The install command is now
sudo apt -y install metavision-essentials
, which includes the Python packages for the default Python version of your system. For other Python versions, you can also specific packages, e.g. packagemetavision-essentials-python3.7
for Python 3.7.
OpenEB
New features
Added Github Action CI pipeline on OpenEB repository (https://github.com/prophesee-ai/openeb)
Introduced new RAW plugins, adding capability to use RAW recording as input to processing pipelines
Introduced new RAW recordings seek capability, in beta version
Introduced new adaptive-rate event-stream slicing adapting event iteration to scene dynamics
Added Python sample demonstrating usage of various event-based formats (CSV, ROSbag, AEDAT) as input to Python pipelines
Updates
Added access to the ERC API from the Camera class
Moved definition of EventBbox from ML module to OpenEB and introduced EventBboxNpyReader class to handle various input formats
Added possibility to change default color palette in Python binding of PeriodicFrameGenerationAlgorithm
Renamed Gen4.1 FO bias from bias_fo_p to bias_fo
Bug fixes
Metavision::Window does not crash anymore when requesting window sizes larger than the screen resolution
Metavision SDK
New features
Introduced Metavision Studio, a user-friendly viewer for live cameras and recordings
CV Module
ML Module
Calibration module
Introduced new camera / ground plane extrinsics calibration script
Added support for OpenCV FishEye calibration
Changes
Machine Learning
Added possibility in the detection & tracking pipeline in ML module to update box tracklet coordinates after each inference
Analytics
Optimized runtime of PSM algorithm in Analytics module
Bug fixes
The Python bindings of the AntiFlickerAlgorithm can now be used correctly
Prophesee Devices
New features
Added support for trigger/sync mode, temperature and illumination to EVK3 Gen4.1
Changes
Released new shared firmware for EVK3 Gen3.1/Gen4.1.
Released new EVK2 Processing System Linux Image for EVK2 version 1.6.0 (contact us to get access to the page)
Enforced min/max value range in biases for Gen3.1 and Gen4.1 sensors
Reworked EVK2 and EVK3 devices discovery and builder
Bug fixes
Device unplug/replug is no longer required after closing a live EVK2 stream on Windows, requires new EVK2 Processing System Linux Image v1.6.0 (contact us to get access to the page)
EVK3 Gen3.1 temperature and illumination measurements can now be used correctly
Documentation
Enhancement of installation and getting started pages
Enhancement of Python and C++ sample guides for SDK modules
Clarification of biases and triggers pages
V2.2.2 Change Logs (26/07/2021)
Cameras supported
New plugin for Prophesee EVK3 Gen4.1 camera with limited set of features (streaming, biases, ROI). This plugin does not support Monitoring events for Illumination and Temperature. External Trigger mechanism (Master/Slave mode, Trigger In, Trigger Out) is not yet supported as well.
Bug fixes
Machine Learning
Python package metavision_ml now deployed by Windows Essentials installer
The eval_coco_kpi sample does not fail anymore when no box is evaluated
Analytics
Vibration estimation is now using correct color map
Python Sample metavision_jet_monitoring_calibration now imports all the necessary modules
Miscellaneous
Enhancement of XYT Designer sample to show frame view next to events view
The install step after compilation now works without error on Python packages deployment path
Documentation
V2.2.1 Change Logs (11/06/2021)
Bug fixes
Prophesee Camera plugins
The ERC facility setter functions now saturates to a device-dependent maximum value
The AFK facility setter functions now preserves the anterior enable/disable status
The
stop
parameter in theset_frequency
AFK facility function is now correctly taken into accountThe initial event burst occurring in some situations with Gen3.1 devices is now fixed
Machine Learning
The Optical Flow model now directly predicts in absolute pixel values
The detection models have been renamed to clarify their specificities
The HDF5Iterator now correctly stops at the end of the input file and correctly supports the
start_ts
argumentThe train_detection sample now loads the right classes in finetuning mode and correctly supports the
just_val
flagThe export_detector sample can now be run from the build directory without installing first
The viz_video_to_event_simulator sample now correctly supports implicit input height & width
The colormaps used for visual flow visualizations are now consistent
Miscellaneous
The default installation path for Windows when building from source code with the deployment step is now
C:\Program Files\Prophesee
Documentation
Better coverage of HAL Python API
Enhancement of installation documentation
Fixed issues in Machine Learning tutorials
V2.2.0 Change Logs (29/03/2021)
Platforms supported
Ubuntu 20.04 is supported in addition to 18.04
New open-source distribution plan
New features
SDK samples are now available in Python
ML module is now partly available with Metavision Essentials
New modules
New code samples
Particle Size Measurement in Analytics module
HAL Plugin Sample in HAL module
Simple Windows in UI module
Changes in existing features
Changes in the SDK API:
refactored Frame Generators API
moved the
Metavision::FrameDisplayStage
to the UI module
Changes in the HAL API
Simplified usage of the Device class
Added function to open a Device instance from a stream
Clarified memory ownership of returned pointers
Restricted creation to be done only through DeviceDiscovery
Added new utilities
Added utility classes to identify and use RAW file headers
Added a functional HAL Plugin Sample
V2.1.0 Change Logs (22/09/2020)
Platforms supported
Ubuntu 16.04 is not supported anymore
Python 3 support in Metavision Designer (instead of Python 2)
New features
New Metavision SDK samples
Analytics samples: metavision_counting, metavision_generic_tracking
CV samples: metavision_noise_filtering, metavision_undistortion
Calibration applications: metavision_blinking_pattern_focus, metavision_mono_calibration
New Metavision Designer samples
Analytics samples: metavision_counting.py, metavision_generic_tracking.py
Metavision HAL (Hardware Abstraction Layer) with documented API, Prophesee camera plugins and code samples
Metavision Player (to visualize and record data streamed by event-based vision system)
Documentation online (no more delivered along with the software)
Deprecated features & software
EM events
IMU events
Prophesee Player (replaced by new Metavision Player software)
SDK samples using the engine “_engine_sample”
Changes in existing features
Multiple changes in the SDK and Designer API
SDK API: new modules organization in base, core, driver, cv
Designer API: new modules organization in base, core, engine, cv
SDK samples are not delivered as precompiled binaries (now, need to compile them)
SDK and Designer samples renaming
Simplifying datasets delivery (now, they can be downloaded from the public documentation)
ObjectPool moved from Metavision SDK Core module to Metavision SDK Base module. Use #include “metavision/sdk/base/utils/object_pool.h instead.