CVC-12: Virtual Optical Flow Dataset

Date:28 May, 2016

CVC-12: Virtual Optical Flow Dataset

    The dataset contains synthetic image sequences of different driving scenarios. This dataset provides ground-truth optical flow for all the sequences. The dataset consists of sequences for scenarios of varying speed of the vehicle and road textures. Four speeds of the on-board camera vehicle and three different road textures are considered. Also sequences with complex motion of on-board camera vehicle with few moving vehicles in the scene are provided for all the combinations of speeds and textures. The speed is denoted Sx and Texture is denoted as Tx. The ground-truth is same for all the textured textured sequences of a particular speed. It includes a Matlab that can be used to read the ground-truth data.

    When using this dataset in your research, we will be happy if you cite us
    Naveen Onkarappa and Angel D. Sappa, “Speed and texture: an empirical study on optical flow accuracy in ADAS scenarios”, IEEE Transactions on Intelligent Transportation Systems, Vol. 15, No. 1, 2014, pp 136-147.

    Exampes

    Sequence of lowest speed (1x): There are 40 frames.

    S1T1S1T2S1T3S1 GTFlow

    Sequence of higher speed (2x): There are 20 frames.

    S1T1S1T2S1T3S1 GTFlow

    Sequence of higher speed (3x): There are 13 frames.

    S1T1S1T2S1T3S1 GTFlow

    Sequence of higher speed (4x): There are 10 frames.

    S1T1S1T2S1T3S1 GTFlow

    Complex sequence of lowest speed (1x): There are 10 frames.

    S1T1_ComplexS1T2_ComplexS1T3_ComplexS1_Complex_GTFlowS1_Complex_GTFlow_WithOccl

    Complex sequence of lowest speed (2x): There are 10 frames.

    S2T1_ComplexS2T2_ComplexS2T3_ComplexS2_Complex_GTFlowS2_Complex_GTFlow_WithOccl

    Complex sequence of lowest speed (3x): There are 10 frames.

    S3T1_ComplexS3T2_ComplexS3T3_ComplexS3_Complex_GTFlowS3_Complex_GTFlow_WithOccl

    Complex sequence of lowest speed (4x): There are 10 frames.

    S4T1_ComplexS4T2_ComplexS4T3_ComplexS4_Complex_GTFlowS4_Complex_GTFlow_WithOccl


    Download the dataset

    To download this file, please enter your name and email address below. We will send you an email with a link to your download.

    Your Name*

    Your Email*

    Your email will only be used (rarely) to keep you informed about updates/bugfixes. We will not sell or hand your information to any third party. By downloading this file you accept our licensing conditions.

    X