Translator Disclaimer
13 May 2019 Evaluation of unsupervised optical flow methods for deep learning in real world datasets
Author Affiliations +
The creation of large labeled datasets for optical ow is often infeasible due to the difficulty associated with measuring dynamic objects in real scenes. Current datasets from real world scenes are often sparse in terms of ground truth. Generating synthetic datasets where ground truth can be easily obtained tends to be the easiest way to acquire the large labeled datasets required to achieve good performance. Often, the switch from synthetic to real world imagery leads to a drop-in performance. Recently with the development of differentiable image warping layers, unsupervised methods, which require no ground truth optical ow, can be applied to train a deep neural network (DNN) model for optical ow tasks, and this allows for training with un-labeled video. Brightness constancy assumption is the underlying principle that enables unsupervised learning of optical ow. Violations of the brightness constancy assumption of optical ow in particular at occlusions results in large outlier errors which are harmful to the learning process. The use of robust regression loss function and outlier prediction methods attempt to alleviate the problem of outliers. In this paper, we will conduct experiments to compare performance various unsupervised optical ow methods by exploring the performance of different robust cost functions, and outlier methods.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Diego Marez and Josh Harguess "Evaluation of unsupervised optical flow methods for deep learning in real world datasets", Proc. SPIE 10992, Geospatial Informatics IX, 109920N (13 May 2019);

Back to Top