FAST9 Feature Detector Sample

Table of Contents

• Description
• Running the Sample
• Output

Note

SW Release Applicability: This sample is available in both NVIDIA DriveWorks and NVIDIA DRIVE Software releases.

Description

The FAST9 Feature Detector sample demonstrates the feature detection capabilities using the FAST9 algorithm of the Features module. It loads a video stream and reads the images sequentially. For each frame, it detects feature points using the FAST9 algorithm.

Running the Sample

The FAST9 Feature Detector sample, sample_fast9_feature_detector, accepts the following optional parameters. If none are specified, it will perform detections on a supplied pre-recorded video.

./sample_fast9_feature_detector --video=[path/to/video.h264]
                                --maxFeatureCount=[even_number]
                                --pva=[0|1]
                                --pvaEngineNo=[0|1]
                                --scoreThreshold=[fp_number]
                                --NMSRadius=[0|1]
                                --usePinnedMemory=[0|1]

where

--video=[path/to/video.h264]
    Is the absolute or relative path of a h264 or RAW/LRAW video.
    Containers such as MP4, AVI, MKV, etc. are not supported.
    Default value: path/to/data/samples/sfm/triangulation/video_0.h264.

--maxFeatureCount=[even_number]
    Specifies the maximum number of features that can be stored.
    If using PVA to do fast9 feature detection, maxFeatureCount needs to
    be set as no more than 4096.
    Default value: 4096

--pva=[0|1]
    When set to 1, the fast9 feature detection algorithm is performed on PVA hardware.
    Otherwise, it is performed on GPU.
    Default value: 0

--pvaEngineNo=[0|1]
    If pva is set as 1, determines on which PVA the detector should run on.
    Default value: 0

--scoreThreshold=[fp_number]
    Defines the strength for which a point is classified as a corner.
    Default value: 56

--NMSRadius=[0|1]
    When set to 1, non-maximum suppression will be applied.
    Default value: 0

--usePinnedMemory=[0|1]
    When set to 1, it would use of PinnedMemory for faster CudaMemcpy.
    Default value: 0

Output

The sample creates a window, displays the video, and overlays the list of features. The current feature positions of the current frame will be overlaid by small squares.

FAST9 Sample Output

For more details see Single Camera Feature Tracking.