This module provides the APIs to initialize, query, and release the NVIDIA proprietary traffic sign classification deep neural network: SignNet. The data structures include dwTrafficSignalClass
, which defines the traffic sign state that the SignNet is trained to detect. dwSignNetModel
allows user to choose among SignNet models. And dwSignNetParams
, in addition to dwSignNetModel
, defines the SignNet model variant with specific precision and processor optimization to be loaded.
SignNet models currently cover three geographical regions: United States, European Union, and Japan with one model per country DW_SIGNNET_MODEL_US_V4
, DW_SIGNNET_MODEL_EU_V4
and DW_SIGNNET_MODEL_JP_V1
respectively.
It's possible to refer to the current model in use per country by using DW_SIGNNET_MODEL_XX_CURRENT
where XX
corresponds to US, EU or JP.
The image datasets used to train SignNet have been captured by a View Sekonix Camera Module (SF3325) with AR0231 RCCB sensor. The camera is mounted on a rig on top of the vehicle. Demo videos are captured at 2.3 MP and downsampled to 960 x 604. Eight cameras were used to collect the data for training the provided SignNet models. The following list shows the setup position and field of view (FOV) of each such camera:
Even though the SignNet DNN was trained with data from cameras setup pointing in various direction of the sensor rig it is recommeded to use it for the following directional and FoV setup:
For a list of traffic signs detected by each model see the pages below.
Model Name | Description |
---|---|
TrafficSign_US_v4 | SignNet model for US (v4.0) with HWISP support, 312 outputs and 272 distinct text labels |
TrafficSign_EU_v4 | SignNet model for EU (v4.0) with HWISP support, 242 outputs and 232 distinct text labels |
SignNet JP v1.0 | SignNet model for Japan (v1.0) with 184 outputs, and 151 distinct text labels |